#!/usr/bin/env bash
# Regression test for the two properties of ADR-0020 boundary-target resolution
# that decide whether the gate can be trusted at all.
#
#   1. MACHINE INDEPENDENCE. The resolution universe is derived by walking up
#      FROM THE TARGET FILE to an authoring root, and when one is found the
#      deployed .claude/ and .agents/ trees are deliberately NOT consulted. Those
#      trees are `apm install` output — gitignored, and present only on a machine
#      that has run it. Four cross-plugin targets in this repo resolved through
#      .claude/skills/ alone, so the same commit measured 2 dangling targets on a
#      developer machine and 6 on a fresh clone. A gate shipping hot with no
#      baseline cannot give two answers, so this file asserts the verdict is
#      identical with and without a deployed tree — on a synthetic fixture AND on
#      the real 39-skill corpus.
#
#   2. THE BARE-TARGET GRAMMAR RULE. A hyphenated token used as a compound
#      MODIFIER ("pre-commit hooks", "pull-request template") is prose, not a
#      route; a terminal one is a real target. Getting this wrong in either
#      direction is fatal: firing on prose makes the gate untrustworthy and it
#      gets turned off, while suppressing too much deletes the only two true
#      positives the corpus has. Both live true positives are BARE, which is why
#      the rule keys on the FOLLOWER TOKEN rather than on marking, and why they
#      are pinned by name below — a future false-positive fix must not be able to
#      quietly take them with it.
#
#   3. IN-SENTENCE CORROBORATION. Terminal position alone is not evidence of a
#      route: "run `pre-commit` instead", "see `commit-msg`", "use the clean-up
#      instead" and "run unit-tests" are all terminal, all prose, and all were
#      hard FAILs with no suppression mechanism anywhere in the gate. A
#      prose-form target therefore blocks only when its own sentence names
#      another target that RESOLVES; otherwise it is reported at SUGGESTION tier
#      and the commit proceeds. Route NOTATION (`/name`, `-> name`) is exempt
#      and always blocks. Both halves are asserted below: the prose class must
#      report-not-block, and the notation and corroborated forms must still
#      ERROR, or the fix would have eaten the gate rather than narrowed it.
set -euo pipefail

REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
HOOK="$REPO_ROOT/scripts/skill-size-check.sh"
PASS=0
FAIL=0

pass() { echo "  PASS: $1"; PASS=$((PASS + 1)); }
fail() { echo "  FAIL: $1"; FAIL=$((FAIL + 1)); }

TMPDIR_T="$(mktemp -d)"
trap 'rm -rf "$TMPDIR_T"' EXIT

# write_skill <skill-dir> <name> <desc>
write_skill() {
  mkdir -p "$1"
  {
    echo "---"
    echo "name: $2"
    echo "description: $3"
    echo "---"
    echo ""
    echo "Do the thing."
  } > "$1/SKILL.md"
}

# ---------------------------------------------------------------------------
# 1. Machine independence — synthetic fixture
# ---------------------------------------------------------------------------
# Two trees, identical except that one also carries a deployed .claude/ tree
# holding a skill and an agent that exist NOWHERE in plugins/. The subject routes
# to one name that lives in a sibling plugin (must resolve in both) and one that
# lives only in .claude/ (must DANGLE in both — an authoring root exists, so the
# deployed tree is not part of the universe).
#
# If the deployed tree were consulted, the second target would resolve on the
# machine that has run `apm install` and dangle on a fresh clone. That is the
# 2-vs-6 defect exactly, at fixture scale.
echo ""
echo "--- the same file gets the same verdict with and without a deployed .claude/ tree ---"
build_tree() {
  local root="$1"
  write_skill "$root/plugins/other-plugin/.apm/skills/cross-plugin-skill" cross-plugin-skill \
    "Use when doing the other thing. Do not use for anything else."
  write_skill "$root/plugins/subject-plugin/.apm/skills/my-skill" my-skill \
    "Use when doing the thing. Do not use for the other thing — use cross-plugin-skill or deployed-only-skill instead."
}
build_tree "$TMPDIR_T/no-claude"
build_tree "$TMPDIR_T/with-claude"
# The deployed tree, present only in the second root. Both a skill and an agent,
# because both are valid routing targets and both would leak.
mkdir -p "$TMPDIR_T/with-claude/.claude/skills/deployed-only-skill" \
         "$TMPDIR_T/with-claude/.claude/agents"
: > "$TMPDIR_T/with-claude/.claude/agents/deployed-only-agent.md"

run_subject() {
  local root="$1" out
  set +e
  out="$(bash "$HOOK" "$root/plugins/subject-plugin/.apm/skills/my-skill/SKILL.md" 2>&1)"
  set -e
  # Normalise the tree root out of the paths so the two runs are comparable.
  printf '%s\n' "$out" | sed "s#$root#<ROOT>#g"
}
NO_CLAUDE_OUT="$(run_subject "$TMPDIR_T/no-claude")"
WITH_CLAUDE_OUT="$(run_subject "$TMPDIR_T/with-claude")"

if [[ "$NO_CLAUDE_OUT" == "$WITH_CLAUDE_OUT" ]]; then
  pass "identical output with and without a deployed .claude/ tree"
else
  fail "the deployed .claude/ tree changed the verdict — without: [$NO_CLAUDE_OUT] with: [$WITH_CLAUDE_OUT]"
fi
# Identical-but-wrong is still possible (both could resolve everything, or
# neither could resolve anything), so the CONTENT is asserted too: the
# sibling-plugin name must resolve and the deployed-only name must not.
if [[ "$WITH_CLAUDE_OUT" == *"routes to 'deployed-only-skill'"* ]]; then
  pass "a name that exists only in .claude/ still dangles when an authoring root is present"
else
  fail "the deployed-only target did not dangle — the deployed tree is being read into the universe: $WITH_CLAUDE_OUT"
fi
if [[ "$WITH_CLAUDE_OUT" != *"routes to 'cross-plugin-skill'"* ]]; then
  pass "a name in a SIBLING PLUGIN resolves, so the comparison above is not 'nothing resolves'"
else
  fail "the sibling-plugin target dangled — the monorepo universe is not being built: $WITH_CLAUDE_OUT"
fi

# The other half of the rule: with NO authoring root, deployed trees ARE the
# universe. That is the consumer case, and without this the rule above could be
# implemented as "never read .claude/", which would leave consumers with no
# resolution at all.
echo ""
echo "--- with no authoring root, a deployed .claude/ tree IS the universe ---"
CONSUMER="$TMPDIR_T/consumer"
mkdir -p "$CONSUMER/.claude/skills/deployed-only-skill"
write_skill "$CONSUMER/.claude/skills/my-skill" my-skill \
  "Use when doing the thing. Do not use for the other thing — use deployed-only-skill instead."
set +e
CONSUMER_OUT="$(bash "$HOOK" "$CONSUMER/.claude/skills/my-skill/SKILL.md" 2>&1)"
CONSUMER_RC=$?
set -e
if [[ $CONSUMER_RC -eq 0 && "$CONSUMER_OUT" != *"routes to"* && "$CONSUMER_OUT" != *"DID NOT RUN"* ]]; then
  pass "a sibling in a deployed .claude/skills/ tree resolves when there is no authoring root"
else
  fail "the consumer path did not resolve through the deployed tree (exit $CONSUMER_RC): ${CONSUMER_OUT:-<empty>}"
fi

# ---------------------------------------------------------------------------
# 1b. Machine independence — the real corpus
# ---------------------------------------------------------------------------
# The fixture above proves the rule; this proves it at the scale where it broke.
#
# The A/B is built rather than borrowed. plugins/ is copied TWICE: once bare (a
# fresh clone), and once with a synthetic .claude/skills/ tree deployed beside it
# holding a directory for every name the corpus currently reports as dangling. If
# deployed trees leaked back into the universe, the second copy would resolve
# those names and report an empty dangling set while the first reported two —
# 2-vs-6, reproduced deterministically.
#
# Deliberately NOT keyed on whether THIS machine has run `apm install`. Doing that
# would make the suite fail on a fresh clone (where there is no .claude/ to
# contrast against) — a test of machine independence that is itself
# machine-dependent. The live tree is still compared, as a third data point, but
# nothing here requires it to be in either state.
echo ""
echo "--- the real corpus reports the same dangling targets with and without a deployed tree ---"
dangling_set() {
  local -a files=()
  local f
  # Collected with a `while read` loop, not `mapfile`: macOS ships bash 3.2,
  # which has no `mapfile`, and tests/test-vale-wrap.sh scans tests/*.sh for
  # exactly that hazard. `find` rather than a glob so both roots walk identically.
  while IFS= read -r f; do
    files+=("$f")
  done < <(find "$1" -path '*/.apm/skills/*/SKILL.md' | sort)
  if [[ ${#files[@]} -eq 0 ]]; then
    echo "NO-FILES-FOUND"
    return
  fi
  set +e
  bash "$HOOK" ${files[@]+"${files[@]}"} 2>&1 \
    | grep -oE "routes to '[^']+'" \
    | sed "s/routes to '//; s/'//" \
    | sort -u
  set -e
}
LIVE_DANGLING="$(dangling_set "$REPO_ROOT/plugins")"

FRESH_ROOT="$TMPDIR_T/fresh-clone"
mkdir -p "$FRESH_ROOT"
cp -R "$REPO_ROOT/plugins" "$FRESH_ROOT/plugins"
[[ -f "$REPO_ROOT/apm.yml" ]] && cp "$REPO_ROOT/apm.yml" "$FRESH_ROOT/apm.yml"
FRESH_DANGLING="$(dangling_set "$FRESH_ROOT/plugins")"

DEPLOYED_ROOT="$TMPDIR_T/deployed-clone"
mkdir -p "$DEPLOYED_ROOT/.claude/skills" "$DEPLOYED_ROOT/.claude/agents"
cp -R "$REPO_ROOT/plugins" "$DEPLOYED_ROOT/plugins"
[[ -f "$REPO_ROOT/apm.yml" ]] && cp "$REPO_ROOT/apm.yml" "$DEPLOYED_ROOT/apm.yml"
# Deploy exactly the names that currently dangle. That is the strongest possible
# bait: if the deployed tree were consulted, every one of them would resolve and
# the dangling set would collapse to empty.
DEPLOY_COUNT=0
while IFS= read -r name; do
  [[ -n "$name" ]] || continue
  mkdir -p "$DEPLOYED_ROOT/.claude/skills/$name"
  DEPLOY_COUNT=$((DEPLOY_COUNT + 1))
done <<< "$FRESH_DANGLING"
DEPLOYED_DANGLING="$(dangling_set "$DEPLOYED_ROOT/plugins")"

if [[ "$DEPLOY_COUNT" -gt 0 ]]; then
  pass "precondition: $DEPLOY_COUNT dangling name(s) deployed into the contrast tree's .claude/skills/, so the A/B has something to distinguish"
else
  fail "no dangling names to deploy — the corpus reports none, so this A/B distinguishes nothing. Deploy a known-absent name explicitly instead of deriving one."
fi
if [[ ! -d "$FRESH_ROOT/.claude" && ! -d "$FRESH_ROOT/.agents" ]]; then
  pass "precondition: the fresh-clone copy has no deployed tree of its own"
else
  fail "the fresh-clone copy picked up a deployed tree — it is not a fresh-clone fixture"
fi
if [[ "$FRESH_DANGLING" == "$DEPLOYED_DANGLING" ]]; then
  pass "deploying every dangling name into .claude/skills/ changes nothing: $(echo "$FRESH_DANGLING" | tr '\n' ' ')"
else
  fail "the corpus verdict depends on whether apm install has been run — fresh clone: [$(echo "$FRESH_DANGLING" | tr '\n' ' ')] with a deployed tree: [$(echo "$DEPLOYED_DANGLING" | tr '\n' ' ')]"
fi
# Third data point: whatever state THIS machine happens to be in, the live tree
# must agree with a bare copy of the same plugins/. No precondition on that state
# — see the section header.
if [[ "$LIVE_DANGLING" == "$FRESH_DANGLING" ]]; then
  pass "the live tree agrees with a bare copy (this machine $( [[ -d "$REPO_ROOT/.claude/skills" ]] && echo "HAS" || echo "has no" ) deployed .claude/skills/ tree)"
else
  fail "the live tree disagrees with a bare copy of the same plugins/ — live: [$(echo "$LIVE_DANGLING" | tr '\n' ' ')] fresh clone: [$(echo "$FRESH_DANGLING" | tr '\n' ' ')]"
fi

# ---------------------------------------------------------------------------
# 1c. The two live true positives, pinned by name
# ---------------------------------------------------------------------------
# ADR-0020 records these as real broken routing targets and splits fixing them
# into Gitea issue #100. Until that lands they are the ONLY evidence the dangling
# check finds anything at all in real prose, so they are asserted as an exact set
# rather than a "contains" — a false-positive fix that suppressed one of them
# would otherwise land green.
#
# `gitea-labels` is the subtler of the two and is worth keeping: it is not
# written anywhere as `gitea-labels`. gitea-issues' description says "Composes
# `gitea-labels-\n  milestones`" in a `>`-folded scalar, and the fold joins the
# lines into "gitea-labels- milestones" — the trailing hyphen is what keeps the
# token terminal and therefore danglable.
#
# WHEN ISSUE #100 IS FIXED: update EXPECTED_DANGLING to match. Do not delete the
# assertion — an empty expected set is fine and still pins that no NEW dangling
# target appeared.
echo ""
echo "--- the two live dangling targets in the corpus are exactly the two ADR-0020 records ---"
EXPECTED_DANGLING="$(printf '%s\n' gitea-labels neuledge-context)"
if [[ "$LIVE_DANGLING" == "$EXPECTED_DANGLING" ]]; then
  pass "the corpus dangling set is exactly {gitea-labels, neuledge-context}"
else
  fail "the corpus dangling set changed — expected [$(echo "$EXPECTED_DANGLING" | tr '\n' ' ')], got [$(echo "$LIVE_DANGLING" | tr '\n' ' ')]. If a retrofit fixed one, update EXPECTED_DANGLING; if a false-positive fix silently deleted one, that is the regression this asserts."
fi
for probe in \
  "plugins/bin/.apm/skills/research/SKILL.md:neuledge-context" \
  "plugins/gitea/.apm/skills/gitea-issues/SKILL.md:gitea-labels"; do
  probe_file="$REPO_ROOT/${probe%%:*}"
  probe_name="${probe##*:}"
  if [[ ! -f "$probe_file" ]]; then
    fail "the true-positive fixture ${probe%%:*} no longer exists — this pin has become vacuous"
    continue
  fi
  set +e
  probe_out="$(bash "$HOOK" "$probe_file" 2>&1)"
  set -e
  if [[ "$probe_out" == *"routes to '$probe_name'"* ]]; then
    pass "detects the dangling '$probe_name' target in ${probe%%:*}"
  else
    fail "did not detect the dangling '$probe_name' target in ${probe%%:*} — a false-positive fix has taken a true positive with it: $probe_out"
  fi
done

# ---------------------------------------------------------------------------
# 2. The bare-target grammar rule
# ---------------------------------------------------------------------------
# Every fixture is built inside a real plugin tree. In a bare temp directory the
# resolver would decline ("DID NOT RUN") and every must-not-error case would pass
# vacuously, proving nothing about extraction.
echo ""
echo "--- attributive compound modifiers are prose, not routing targets ---"
GRAMMAR_ROOT="$TMPDIR_T/grammar"
write_skill "$GRAMMAR_ROOT/plugins/p/.apm/skills/sibling-skill" sibling-skill \
  "Use when doing the other thing. Do not use for anything else."

# grammar_case <slug> <expect: silent|errors> <needle> <description>
grammar_case() {
  local slug="$1" mode="$2" needle="$3" desc="$4" out status=0
  write_skill "$GRAMMAR_ROOT/plugins/p/.apm/skills/$slug" "$slug" "$desc"
  set +e
  out="$(bash "$HOOK" "$GRAMMAR_ROOT/plugins/p/.apm/skills/$slug/SKILL.md" 2>&1)"
  status=$?
  set -e
  if [[ "$out" == *"DID NOT RUN"* ]]; then
    fail "\"$desc\" — the resolver declined, so this case asserts nothing about extraction: $out"
    return
  fi
  case "$mode" in
    silent)
      if [[ $status -eq 0 && -z "$out" ]]; then
        pass "not a dangling target: \"$desc\""
      else
        fail "\"$desc\" (exit $status, output: ${out:-<empty>})"
      fi
      ;;
    errors)
      if [[ $status -ne 0 && "$out" == *"$needle"* ]]; then
        pass "still a dangling target: \"$desc\""
      else
        fail "\"$desc\" should have ERRORed with $needle (exit $status, output: ${out:-<empty>})"
      fi
      ;;
    suggests)
      # Reported, not blocking. Both halves matter: an ERROR here would be the
      # unsuppressable false positive this tier exists to remove, and silence
      # would mean the gate stopped noticing the target at all.
      if [[ $status -eq 0 && "$out" == *"SUGGESTION"*"$needle"* && "$out" != *"ERROR"* ]]; then
        pass "reported but not blocking: \"$desc\""
      else
        fail "\"$desc\" should have exited 0 with a SUGGESTION naming $needle (exit $status, output: ${out:-<empty>})"
      fi
      ;;
  esac
}

# The four phrasings that were hard dangling FAILs with no suppression. All four
# are lifted from real descriptions in this corpus.
grammar_case fp-precommit-hooks silent "" \
  "Use when running the linter. Use pre-commit hooks instead of ad-hoc scripts."
grammar_case fp-pull-request silent "" \
  "Use when opening changes. Invoke the pull-request template instead of writing one by hand."
grammar_case fp-conventional silent "" \
  "Use when writing history. Use conventional-commits formatting rather than free-form messages."
grammar_case fp-prepush-backticked silent "" \
  "Use when checking a branch. Do not use for local edits — run the \`pre-push\` hooks instead."

echo ""
echo "--- a lone unresolvable token in terminal position is REPORTED, not blocking ---"
# The class this tier was added for. Every one of these is grammatically
# identical to a real broken route — "route verb + name + terminal" is also how
# prose cites a hook, a linter, a file format or an English compound — and every
# one of them was a hard FAIL with no suppression mechanism anywhere in the gate.
# The skills most exposed are exactly the ones the ADR-0020 retrofit sends
# authors back to rewrite first: pc-run, pc-author, vale-run, vale-config and the
# apm-* family are all ABOUT hyphenated tools.
grammar_case fp-precommit-terminal suggests "routes to 'pre-commit'" \
  "Use when running the linter. Do not use for running hooks — run \`pre-commit\` instead."
grammar_case fp-commit-msg suggests "routes to 'commit-msg'" \
  "Use when writing history. Do not use for the commit message — see \`commit-msg\`."
grammar_case fp-type-check suggests "routes to 'type-check'" \
  "Use when compiling. Do not use for type errors — run \`type-check\` first."
grammar_case fp-semantic-release suggests "routes to 'semantic-release'" \
  "Use when tagging a version. Instead, use \`semantic-release\`."
# Single-word tool names are the same defect: `eslint` in terminal position hit
# the marked-target path and hard-FAILed just as `pre-commit` did.
grammar_case fp-eslint suggests "routes to 'eslint'" \
  "Use when linting JS. Do not use for style — run \`eslint\` instead."
# Bare English compounds, which the backtick path never sees at all.
grammar_case fp-clean-up suggests "routes to 'clean-up'" \
  "Use when doing the thing. Do not use for the old flow — use the clean-up instead."
grammar_case fp-built-in suggests "routes to 'built-in'" \
  "Use when doing the thing. Do not use for the custom path — Instead, prefer the built-in."
grammar_case fp-write-up suggests "routes to 'write-up'" \
  "Use when doing the thing. Do not use for the summary — see the write-up."
grammar_case fp-front-end suggests "routes to 'front-end'" \
  "Use when doing the thing. Do not use for the API layer — use the front-end."
grammar_case fp-unit-tests suggests "routes to 'unit-tests'" \
  "Use when testing. Do not run end-to-end, run unit-tests."

echo ""
echo "--- terminal targets that resolve to nothing still ERROR ---"
# The controls. Without them the cases above are satisfied by a check that never
# fires, and the narrowing would have eaten the gate rather than sharpened it.
# Three forms, three code paths:
#   * route NOTATION — `/name` and `-> name` — is exempt from corroboration and
#     blocks on its own. Nobody writes `/pre-commit` or `-> pre-commit` to mean
#     the hook, so there is no ambiguity to resolve, and an author who wants a
#     route checked unconditionally has two ways to say so.
#   * a PROSE-form target — backticked or bare — blocks when its own sentence
#     names another target that resolves. `sibling-skill` is that corroborator
#     here; it is the same shape as both live true positives, which sit beside
#     `write-docs` and `gitea-labels-milestones` respectively.
grammar_case tp-arrow errors "routes to 'no-such-arrow-target'" \
  "Use when doing the thing. Not the other thing → no-such-arrow-target."
grammar_case tp-slash errors "routes to 'no-such-slash-skill'" \
  "Use when doing the thing. Do not use for improvements — use /no-such-slash-skill instead."
grammar_case tp-backticked errors "routes to 'no-such-backticked-skill'" \
  "Use when doing the thing. Do not use for improvements — use \`sibling-skill\` or \`no-such-backticked-skill\` instead."
grammar_case tp-bare-terminal errors "routes to 'no-such-bare-skill'" \
  "Use when doing the thing. Do not use for improvements — use sibling-skill or no-such-bare-skill instead."

# And the confirming half of the grammar rule: a compound-modifier target is
# CONFIRM-ONLY, not ignored. When the name does exist it still counts as a route
# — the rule suppresses the ERROR, it does not delete the target.
echo ""
echo "--- an attributive target that DOES resolve is still a route, not a discarded token ---"
write_skill "$GRAMMAR_ROOT/plugins/p/.apm/skills/attributive-subject" attributive-subject \
  "Use when doing the thing. Do not use for the other thing — use the sibling-skill helper instead."
set +e
ATTR_OUT="$(bash "$HOOK" "$GRAMMAR_ROOT/plugins/p/.apm/skills/attributive-subject/SKILL.md" 2>&1)"
ATTR_RC=$?
set -e
if [[ $ATTR_RC -eq 0 && -z "$ATTR_OUT" ]]; then
  pass "a resolving attributive target neither errors nor is reported"
else
  fail "an attributive target naming a REAL skill produced output (exit $ATTR_RC): $ATTR_OUT"
fi

echo ""
echo "Results: $PASS passed, $FAIL failed"
[[ $FAIL -eq 0 ]]