#!/usr/bin/env bash
# The delta-inventory guard (#200, enforcing #197 D3's standing constraint).
#
#   Forge-specific behaviour lives in the files docs/UPSTREAM-SYNC.md names,
#   and nowhere else.
#
# WHY. This tree carries upstream's content plus a forge delta, forever — the
# sync is recurring and upstream is read-only (#197 D3). What makes that
# tractable is not luck: the 0.6.0 sync cost 18 conflict hunks across 10 files
# because the delta sits in six files upstream never touches. Scatter
# `forge_detect` into a seventh and every future sync pays for it, in a place
# nobody chose.
#
# So this fails on the PR that scatters it, rather than on the sync after next
# — the same reason changelog-monotonic guards a property no single tree can
# be asked about.
#
# IT RUNS OFFLINE, AND IT DOES NOT PASS BY ABSENCE. Tests must not need the
# network, and a guard that goes green when it cannot see its input is the
# blind-sweep shape this repo keeps writing issues about. So the inventory is
# read from the document and the tree is scanned for forge markers — both local
# — and a missing or empty `.upstream-ref` is a REFUSAL, not a skip.
set -u

ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
# shellcheck source=test/harness.sh
. "$ROOT/test/harness.sh"

DOC="$ROOT/docs/UPSTREAM-SYNC.md"
REF="$ROOT/.upstream-ref"

# --- the recorded upstream ref ------------------------------------------------

check "the sync document exists" 0 "" test -f "$DOC"
check "the upstream ref is recorded" 0 "" test -f "$REF"

# THE OBJECT IS MANDATORY. An earlier head accepted "UNVERIFIABLE-HERE" when
# upstream's commit was not in the local store, which contradicted this issue's
# own "must not pass by absence" and made the check decorative in exactly the
# environment it matters in (@codex-reviewer-andresmgsl, #200 review).
#
# "Runs offline" means the TEST reads local evidence, not that CI may omit the
# evidence and pass. ci.yml fetches the recorded object before running the
# suite; if it is missing here, that is a refusal.
recorded_ref() { grep -vE '^[[:space:]]*(#|$)' "$REF" | head -n1; }
ref_is_recorded() { [ -n "$(recorded_ref)" ]; }
check "...and is not blank — an unrecorded ref is a refusal, not a skip" 0 "" \
  ref_is_recorded
# Full 40, not a short prefix: a short SHA is ambiguous across a growing repo
# and cannot be compared byte-wise between the runbook, the CHANGELOG and here.
ref_is_full_sha() { printf '%s' "$(recorded_ref)" | grep -qE '^[0-9a-f]{40}$'; }
check "...and is a FULL 40-character SHA" 0 "" ref_is_full_sha

ref_object_present() { git -C "$ROOT" cat-file -e "$(recorded_ref)^{commit}" 2>/dev/null; }
check "the recorded commit is present locally — absent is a refusal, not a skip" 0 "" \
  ref_object_present
ref_is_ancestor() { git -C "$ROOT" merge-base --is-ancestor "$(recorded_ref)" HEAD 2>/dev/null; }
check "...and is an ancestor of HEAD, so main really carries what is recorded" 0 "" \
  ref_is_ancestor

# --- the inventory ------------------------------------------------------------

# The document's inventory table: the first `code` span of each table row in
# the "Where the forge delta lives" section.
inventory() {
  awk '/^## Where the forge delta lives/ { on = 1; next }
       on && /^## / { on = 0 }
       on && /^\| `/ { gsub(/^\| `/, ""); sub(/`.*$/, ""); print }' "$DOC"
}

inventory_size() { inventory | wc -l; }
inventory_is_populated() { [ "$(inventory_size)" -ge 6 ]; }
check "the inventory names at least the six known delta files" 0 "" \
  inventory_is_populated

# Exact for a file entry, `dir/` + one path separator for a directory entry.
# Prefix matching accepted `drills-old/x` for `drills/` and `lib/forge.sh.backup`
# for `lib/forge.sh` (@codex-reviewer-andresmgsl, #200 review).
in_inventory() { # $1 = repo-relative path
  local entry
  while IFS= read -r entry; do
    [ -n "$entry" ] || continue
    case "$entry" in
      */) case "$1" in "$entry"*) return 0 ;; esac ;;
      *)  [ "$1" = "$entry" ] && return 0 ;;
    esac
  done < <(inventory)
  return 1
}
check "a listed file is recognised" 0 "" in_inventory lib/forge.sh
check "...including one listed as a directory" 0 "" in_inventory drills/0.4.1.md
check "an unlisted file is not" 1 "" in_inventory lib/version.sh

# --- the scan -----------------------------------------------------------------

# What "forge-specific" means, mechanically: the selector's own verbs, the
# environment override that drives them, and — on a workflow, which has no
# shell to call the selector from — a forge decision written inline.
#
# The earlier version scanned only shell under lib/ actions/ bin/ .github/scripts.
# That missed three categories the inventory itself claims to govern: workflows,
# .github/labels.conf and drills/. Merged main already had blind spots there —
# labels.yml decides on GITHUB_SERVER_URL and declares a client, refs-guard.yml
# carries a positive GitHub-only scheduling decision
# (@codex-reviewer-andresmgsl, #200 review).
FORGE_MARKERS='forge_detect|forge_select|forge_preflight|forge_client|CEREMONY_FORGE\b|CEREMONY_FORGE_CLIENT|GITHUB_SERVER_URL|github\.server_url'

# SCAN_ROOT is a parameter so the teeth below can drive the REAL check against
# a constructed tree. The previous mutation proved the predicates and never
# invoked no_unlisted — the guard could have been `return 0` and still passed.
scan_root() { printf '%s' "${SCAN_ROOT:-$ROOT}"; }

# DISCOVERY IS DERIVED FROM THE TREE, not from a list of directories, depths
# and extensions. The earlier version hand-picked five globs and therefore
# could not see `actions/*/action.yml` — this repository's normal composite
# structure, where a client declaration is exactly a forge decision — or a
# workflow written `.yaml` rather than `.yml`. @codex-reviewer-andresmgsl
# constructed both and the guard stayed 21/21 green, which is the whole
# argument against maintaining a glob list.
#
# So: walk everything, then EXCLUDE by class, and let content classify the
# rest. Excluding is safer than including because a new file type arrives
# scanned rather than invisible.
#
#   test/         the harness stubs and asserts these tokens by design
#   changelog.d/  prose fragments
#   *.md          prose. `drills/` stays in the INVENTORY because its records
#                 are forge-specific by content, but a record mentioning a
#                 selector verb in prose is not a decision, and scanning prose
#                 for decisions is the mistake this guard's own comment
#                 handling exists to avoid.
#
# DISCOVERY IS GIT'S, NOT THE FILESYSTEM'S. An earlier head said "tracked" and
# used `find`, which walks the working directory and knows nothing about the
# index. That is not pedantry: `ci.yml` extracts shellcheck and actionlint
# tarballs INTO the checkout before the suite runs, and any developer cache
# sits there too. @codex-reviewer-andresmgsl reproduced a false red with one
# untracked file. `git ls-files -z` makes "tracked" executable rather than
# prose.
scanned_paths() {
  local root; root="$(scan_root)"
  git -C "$root" ls-files -z 2>/dev/null \
    | tr '\0' '\n' \
    | grep -vE '^(test/|changelog\.d/)' \
    | grep -vE '\.md$' \
    | sort
}

forge_specific_files() {
  local root rel; root="$(scan_root)"
  while IFS= read -r rel; do
    [ -n "$rel" ] || continue
    sed 's/[[:space:]]#.*$//; s/^[[:space:]]*#.*$//' "$root/$rel" 2>/dev/null \
      | grep -qE "$FORGE_MARKERS" && printf '%s\n' "$rel"
  done < <(scanned_paths)
  return 0
}

# A file that merely CALLS the shim is not where the forge is decided — every
# reconciler calls forge_preflight and that is the point of the shim. A file
# that DECLARES a client is a different thing and is NOT exempt: it is a
# deliberate forge-delta location and belongs in the inventory
# (@codex-reviewer-andresmgsl).
SHIM_CONSUMERS='actions/issueflow-reconcile/issueflow-reconcile.sh
actions/labels-reconcile/labels-reconcile.sh
actions/labels-scope/labels-scope.sh
lib/facts.sh
lib/ruling.sh
lib/attention.sh
.github/workflows/release.yml'

declares_a_client() {
  sed 's/[[:space:]]#.*$//; s/^[[:space:]]*#.*$//' "$(scan_root)/$1" \
    | grep -qE 'CEREMONY_FORGE_CLIENT[=:]'
}

unlisted_deciders() {
  local rel
  while IFS= read -r rel; do
    [ -n "$rel" ] || continue
    if grep -qxF "$rel" <<<"$SHIM_CONSUMERS" && ! declares_a_client "$rel"; then
      continue
    fi
    in_inventory "$rel" && continue
    printf '%s\n' "$rel"
  done < <(forge_specific_files)
}

no_unlisted() {
  local found
  found="$(unlisted_deciders)"
  [ -z "$found" ] || {
    printf 'forge-specific but not in docs/UPSTREAM-SYNC.md:\n' >&2
    printf '  %s\n' "$found" >&2
    return 1
  }
}
check "every forge-deciding file is named in the inventory" 0 "" no_unlisted

# --- teeth --------------------------------------------------------------------
# These drive the REAL top-level check against a constructed tree, via
# SCAN_ROOT. The earlier version asserted the predicates separately and never
# invoked no_unlisted — so the guard could have been replaced with `return 0`
# and both "must-fail" rows would still have passed
# (@codex-reviewer-andresmgsl, #200 review). A mutation test that cannot fail
# when the thing it guards is deleted is the shape this repo keeps filing
# issues about.

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

# A tiny GIT repository, because discovery is git's now: a fixture that is only
# a directory would be invisible to `ls-files` and every must-fail below would
# pass vacuously.
fixture_tree() { # -> a tracked tree with no forge-deciding files
  local t="$TMP/tree"
  rm -rf "$t"
  mkdir -p "$t/lib" "$t/.github/workflows"
  printf '#!/usr/bin/env bash\necho hello\n' >"$t/lib/plain.sh"
  printf 'name: ci\non: [push]\n' >"$t/.github/workflows/plain.yml"
  git -C "$t" init -q 2>/dev/null
  git -C "$t" add -A 2>/dev/null
  printf '%s' "$t"
}
track() { git -C "$root" add -A 2>/dev/null; }

root="$(fixture_tree)"
clean_tree_passes() { SCAN_ROOT="$root" no_unlisted; }
check "the guard is green on a tree with no forge decisions" 0 "" clean_tree_passes

# MUST FAIL: a shell file that decides the forge, in no inventory entry.
# shellcheck disable=SC2016 # fixture CONTENT: the literal text a scanned file would hold
printf '%s\n' '#!/usr/bin/env bash' 'case "$(forge_detect)" in forgejo) : ;; esac' \
  >"$root/lib/scattered.sh"
track; scattered_shell() { SCAN_ROOT="$root" no_unlisted; }
check "a new SHELL file deciding the forge fails the real guard" 1 "" scattered_shell
check "...and the failure names the file" 1 "lib/scattered.sh" scattered_shell
rm -f "$root/lib/scattered.sh"; track

# MUST FAIL on a NON-SHELL surface too, so coverage cannot regress to the old
# shell-only glob: a workflow deciding on the server URL.
# shellcheck disable=SC2016 # fixture CONTENT: the literal text a scanned file would hold
printf '%s\n' 'name: x' 'on: [push]' 'jobs:' '  j:' '    steps:' \
  '      - run: [ "$GITHUB_SERVER_URL" = https://github.com ] || exit 0' \
  >"$root/.github/workflows/scattered.yml"
track; scattered_workflow() { SCAN_ROOT="$root" no_unlisted; }
check "a new WORKFLOW deciding the forge fails it too" 1 "" scattered_workflow
check "...naming that file" 1 ".github/workflows/scattered.yml" scattered_workflow
rm -f "$root/.github/workflows/scattered.yml"; track

# @codex-reviewer-andresmgsl's two reproductions, verbatim as fixtures. Both
# passed the hand-picked-glob version 21/21, which is why discovery is derived
# from the tree now. Deleting a discovery class must make these red.
mkdir -p "$root/actions/unlisted-forge-decision"
printf '%s\n' 'name: x' 'runs:' '  using: composite' '  steps:' \
  '    - shell: bash' '      env:' '        CEREMONY_FORGE_CLIENT: gh' \
  '      run: true' >"$root/actions/unlisted-forge-decision/action.yml"
track; composite_action_seen() { SCAN_ROOT="$root" no_unlisted; }
check "a forge declaration in actions/*/action.yml fails the guard" 1 \
  "actions/unlisted-forge-decision/action.yml" composite_action_seen
rm -rf "$root/actions/unlisted-forge-decision"; track

# ...and a workflow written .yaml rather than .yml — `*.yml` was never a
# complete workflow surface.
# shellcheck disable=SC2016 # fixture CONTENT: the literal text a scanned file would hold
printf '%s\n' 'name: x' 'on: [push]' 'jobs:' '  j:' \
  "    if: github.server_url == 'https://github.com'" '    steps: []' \
  >"$root/.github/workflows/unlisted-forge-decision.yaml"
track; yaml_workflow_seen() { SCAN_ROOT="$root" no_unlisted; }
check "...and one in a .yaml workflow does too" 1 \
  ".github/workflows/unlisted-forge-decision.yaml" yaml_workflow_seen
rm -f "$root/.github/workflows/unlisted-forge-decision.yaml"; track
check "...leaving the fixture tree green again" 0 "" clean_tree_passes

# A declaration is a delta location even in a file that would otherwise read as
# a shim consumer, so the consumer allow-list cannot hide one.
mkdir -p "$root/lib"
printf '%s\n' '#!/usr/bin/env bash' 'CEREMONY_FORGE_CLIENT=gh' >"$root/lib/facts.sh"
track; declared_not_exempt() { SCAN_ROOT="$root" no_unlisted; }
check "a shim consumer that DECLARES a client is not exempt" 1 "lib/facts.sh" \
  declared_not_exempt
rm -f "$root/lib/facts.sh"; track
track
check "...and the tree is green again once it is gone" 0 "" clean_tree_passes

# UNTRACKED input is not source. ci.yml extracts shellcheck and actionlint
# tarballs into the checkout before the suite runs, and a developer cache sits
# there too; parsing either is a false red on something outside the repository
# property (@codex-reviewer-andresmgsl, #200 review — reproduced with one file).
printf 'CEREMONY_FORGE_CLIENT=gh\n' >"$root/local-tool-cache.txt"
check "an UNTRACKED marker-bearing file is ignored" 0 "" clean_tree_passes
check "...and is still ignored once it carries a decision" 0 "" clean_tree_passes
track
check "...but the moment it is TRACKED the guard sees it" 1 "local-tool-cache.txt" \
  clean_tree_passes
git -C "$root" rm -q --cached local-tool-cache.txt 2>/dev/null
rm -f "$root/local-tool-cache.txt"
check "...and removing it restores green" 0 "" clean_tree_passes

# Path matching, both boundaries.
check "a directory entry does not match a sibling with the same prefix" 1 "" \
  in_inventory drills-old/0.4.1.md
check "a file entry does not match a longer path" 1 "" in_inventory lib/forge.sh.backup
check "...while the real ones still match" 0 "" in_inventory drills/0.4.1.md

summary