#!/usr/bin/env bash
# reconcile.sh — A7 of the wake canon (EPIC #892, W5): the source-parity
# reconciler.
#
# CONTRACT ANCHORS (docs/scratchpads/heartbeat-planning/CONVERGED-DESIGN.md):
#   §4/G3  Source parity / reconciliation — the GO condition has TWO ordered
#          parts:
#            (i)  a source-coverage PARITY INVENTORY FIRST: a lane-by-lane
#                 DECLARED inventory of every operational source the lane
#                 depends on, so an OMITTED source cannot make the §4 vector pass
#                 VACUOUSLY. An incomplete / undeclared inventory FLAGS (it must
#                 NOT silently pass).
#            (ii) then a periodic full RECONCILE: enumerate declared+configured
#                 source state vs observed_seq/inbox => 0 UNACCOUNTED. Any source
#                 state not reflected in observed_seq/inbox is a gap => FLAG.
#   §4 vector  { source-parity inventory complete AND reconcile = 0 unaccounted }
#   §7-res5    FN-oracle + reconciliation are a real, NON-OPTIONAL operating cost.
#   W4 review division: the detector's first-seen-baseline does NOT wake; the
#          RECONCILER is what enumerates PRE-EXISTING / startup source state into
#          the durable store (at startup and periodically). Without it, state
#          that already existed when the detector first saw it (baselined
#          silently) would never enter the inbox and would be lost.
#
# SCOPE: calls the PUBLIC APIs of store.sh (cursors/drain/enqueue) only. It does
# NOT reimplement or modify the store, ack, digest, signer, or detector. It
# OBSERVES current source state through the SAME operator adapter contract the
# detector uses (WAKE_DETECTOR_SOURCE_CMD <kind> <id>, def on stdin), with the
# SAME fail-loud (G2a) discipline: a source error / ambiguous-empty is never
# silently "no state".
#
# CONTRACT NOTES (flagged, not silently guessed — see PR body):
#   * observed_seq allocation on enumeration: observed_seq is detector-owned
#     (§2.4). The store exposes no "allocate next seq" primitive, so the
#     reconciler enumerates using seqs drawn from the STORE's authoritative
#     observed_seq cursor (§2.4: "observed_seq is authoritative") + 1.. within a
#     pass. A dual-allocator collision window with the detector's private
#     counter is possible under true concurrency; in the per-host
#     single-instance model reconcile and poll are serialised. Unifying on a
#     single store-side allocator is tracked as a cross-wave follow-up.
#   * "accounted" is judged against observed_seq/inbox (§4/G3 wording) PLUS the
#     reconciler's OWN durable reconciled-state ledger — NOT the detector's
#     hash-file. Judging by the detector baseline would let a silent first-seen
#     baseline swallow a pre-existing obligation (the exact hole G3 closes).
#   * enumeration uses the non-coalescible fail-safe class `actionable` (§2.3)
#     so two distinct pre-existing obligations can never coalesce into one.
#
# Operator-agnostic: all state via XDG/env; no operator paths/names/secrets.
set -uo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
# shellcheck source=./_wake-common.sh disable=SC1091
. "$SCRIPT_DIR/_wake-common.sh"

STORE_SH="$SCRIPT_DIR/store.sh"
MANIFEST="$SCRIPT_DIR/manifest.txt"

STATE_DIR="$(wake_state_dir)"
# Reconciler-local state (its durable reconciled-state ledger) lives in its own
# subdir under the store's STATE_DIR so it never collides with store/detector.
RECON_DIR="$STATE_DIR/reconciler"

_need_jq() {
  command -v jq >/dev/null 2>&1 || {
    echo "reconcile.sh: jq is required" >&2
    exit 3
  }
}

_hash() {
  if command -v sha256sum >/dev/null 2>&1; then
    sha256sum | awk '{print $1}'
  elif command -v shasum >/dev/null 2>&1; then
    shasum -a 256 | awk '{print $1}'
  elif command -v openssl >/dev/null 2>&1; then
    openssl dgst -sha256 | awk '{print $NF}'
  else
    echo "reconcile.sh: no sha256 tool (sha256sum/shasum/openssl) available" >&2
    exit 3
  fi
}

usage() {
  cat >&2 <<'EOF'
Usage: reconcile.sh <command> [options]

Commands:
  inventory
        Part (i) — source-coverage PARITY INVENTORY. Prints a lane-by-lane
        declared inventory and FLAGS any incompleteness that could let the §4
        vector pass VACUOUSLY:
          * a declared operational source (repos/board_files/lane_anchors) that
            NO watch covers  (an OMITTED source);
          * a watch that references a source with no declared definition (dangling);
          * a lane with zero sources; an empty watch-list;
          * if a lane declares `required_sources`, any id missing from its sources.
        Exit 0 IFF the inventory is complete; non-zero (loud) on any flag.

  reconcile [--no-enumerate]
        Part (ii) — periodic full reconcile. Enumerates each covered source's
        CURRENT state and compares it against observed_seq/inbox (+ the
        reconciler's reconciled-state ledger). Any source state NOT reflected =>
        UNACCOUNTED => FLAG. Unless --no-enumerate, each unaccounted source is
        ENUMERATED into the durable store (the startup/pre-existing obligation
        path). Exit 0 IFF 0 unaccounted were FOUND this pass.

  check
        The full §4/G3 gate, side-effect-free: `inventory` AND
        `reconcile --no-enumerate`. Exit 0 IFF the inventory is complete AND 0
        unaccounted. Use this to evaluate the vector's G3 clause without writing.

Environment:
  WAKE_WATCH_LIST          Operator watch-list JSON (required).
  WAKE_DETECTOR_SOURCE_CMD Source adapter (required for reconcile/check; same
                           contract as the detector: <cmd> <kind> <id>, def on
                           stdin; exit!=0 or empty => FAIL LOUD).
  WAKE_STATE_HOME/WAKE_AGENT  store namespace (see store.sh).
EOF
}

_manifest_val() {
  local key="$1"
  [ -f "$MANIFEST" ] || return 0
  sed -n "s/^${key}=//p" "$MANIFEST" | head -n1 | tr -d '[:space:]'
}

# _load_watchlist — validate path + JSON + shape + Gate B schema range (mirrors
# the detector's fail-loud validation so the reconciler certifies the SAME
# watch-list the detector runs). Echoes validated JSON on stdout.
_load_watchlist() {
  _need_jq
  local wl="${WAKE_WATCH_LIST:-}"
  if [ -z "$wl" ]; then
    echo "reconcile.sh: WAKE_WATCH_LIST is not set (no watch-list to reconcile)" >&2
    return 2
  fi
  if [ ! -f "$wl" ]; then
    echo "reconcile.sh: watch-list not found: $wl" >&2
    return 2
  fi
  local json
  if ! json="$(jq -e . "$wl" 2>/dev/null)"; then
    echo "reconcile.sh: watch-list is not valid JSON: $wl" >&2
    return 2
  fi
  if ! printf '%s' "$json" | jq -e 'has("schema_version") and has("watches")' >/dev/null 2>&1; then
    echo "reconcile.sh: watch-list missing required 'schema_version' or 'watches'" >&2
    return 2
  fi
  local ver smin smax
  ver="$(printf '%s' "$json" | jq -r '.schema_version')"
  smin="$(_manifest_val schema_min)"
  smax="$(_manifest_val schema_max)"
  case "$ver" in
  '' | *[!0-9]*)
    echo "reconcile.sh: watch-list schema_version must be an integer (got '$ver')" >&2
    return 2
    ;;
  esac
  if [ -z "$smin" ] || [ -z "$smax" ]; then
    echo "reconcile.sh: manifest is missing schema_min/schema_max (cannot validate Gate B)" >&2
    return 2
  fi
  if [ "$ver" -lt "$smin" ] || [ "$ver" -gt "$smax" ]; then
    echo "reconcile.sh: FAIL LOUD (Gate B) — watch-list schema_version $ver is OUTSIDE the supported range [$smin, $smax]" >&2
    return 2
  fi
  printf '%s' "$json"
}

# _coll_for_kind KIND — the top-level collection a source kind is defined in.
_coll_for_kind() {
  case "$1" in
  repo) printf 'repos' ;;
  board_file) printf 'board_files' ;;
  lane_anchor) printf 'lane_anchors' ;;
  *) return 1 ;;
  esac
}

# --- part (i): source-coverage parity inventory ----------------------------

cmd_inventory() {
  local json
  json="$(_load_watchlist)" || exit $?

  local flags=0

  # An empty watch-list can never certify coverage of anything.
  local nwatch
  nwatch="$(printf '%s' "$json" | jq -r '.watches | length')"
  if [ "${nwatch:-0}" -eq 0 ]; then
    echo "reconcile.sh: FLAG (G3 parity) — watch-list declares NO watches; coverage is vacuous." >&2
    flags=$((flags + 1))
  fi

  echo "# source-coverage parity inventory (lane-by-lane)"

  # Per-lane declared inventory + empty-lane + required_sources checks.
  local nlanes li
  nlanes="$(printf '%s' "$json" | jq -r '.watches | length')"
  li=0
  while [ "$li" -lt "${nlanes:-0}" ]; do
    local lane nsrc
    lane="$(printf '%s' "$json" | jq -r --argjson i "$li" '.watches[$i].lane // "(unnamed)"')"
    nsrc="$(printf '%s' "$json" | jq -r --argjson i "$li" '.watches[$i].sources | length')"
    printf '  lane %s: %s declared source(s)\n' "$lane" "${nsrc:-0}"

    if [ "${nsrc:-0}" -eq 0 ]; then
      echo "reconcile.sh: FLAG (G3 parity) — lane '$lane' declares ZERO sources (empty coverage)." >&2
      flags=$((flags + 1))
    fi

    # required_sources (optional, additive; ignored by the detector). If the
    # operator declares the lane's true dependency set here, every id MUST be
    # covered by the lane's sources — an OMITTED dependency FLAGS.
    local missing
    missing="$(printf '%s' "$json" | jq -r --argjson i "$li" '
      (.watches[$i].required_sources // []) as $req
      | ($req - [ .watches[$i].sources[].id ]) | .[]')"
    if [ -n "$missing" ]; then
      local m
      while IFS= read -r m; do
        [ -n "$m" ] || continue
        echo "reconcile.sh: FLAG (G3 parity) — lane '$lane' requires source '$m' but it is OMITTED from the lane's watched sources (vacuous-pass prevented)." >&2
        flags=$((flags + 1))
      done <<EOF
$missing
EOF
    fi
    li=$((li + 1))
  done

  # Dangling: every watched (kind,id) MUST have a declared definition.
  local pairs kind id
  pairs="$(printf '%s' "$json" | jq -r '[ .watches[].sources[] | "\(.kind)\t\(.id)" ] | unique | .[]')"
  while IFS=$'\t' read -r kind id; do
    [ -n "$kind" ] || continue
    local coll def
    if ! coll="$(_coll_for_kind "$kind")"; then
      echo "reconcile.sh: FLAG (G3 parity) — unknown source kind '$kind' in a watch." >&2
      flags=$((flags + 1))
      continue
    fi
    def="$(printf '%s' "$json" | jq -c --arg c "$coll" --arg id "$id" '(.[$c] // []) | map(select(.id == $id)) | .[0] // empty')"
    if [ -z "$def" ]; then
      echo "reconcile.sh: FLAG (G3 parity) — watch references '$kind/$id' but no such entry is declared in '$coll' (dangling)." >&2
      flags=$((flags + 1))
    fi
  done <<EOF
$pairs
EOF

  # Omitted-from-coverage: every DECLARED operational source must be covered by
  # at least one watch. A declared-but-unwatched source is exactly the OMITTED
  # source that would let the vector pass VACUOUSLY (the detector never checks it).
  local coll kinds
  kinds="repos:repo board_files:board_file lane_anchors:lane_anchor"
  for coll in $kinds; do
    local cname ckind ids
    cname="${coll%%:*}"
    ckind="${coll##*:}"
    ids="$(printf '%s' "$json" | jq -r --arg c "$cname" '(.[$c] // [])[].id')"
    local sid covered
    while IFS= read -r sid; do
      [ -n "$sid" ] || continue
      covered="$(printf '%s' "$json" | jq -r --arg k "$ckind" --arg id "$sid" \
        '[ .watches[].sources[] | select(.kind==$k and .id==$id) ] | length')"
      if [ "${covered:-0}" -eq 0 ]; then
        echo "reconcile.sh: FLAG (G3 parity) — declared source '$ckind/$sid' is NOT covered by any watch (OMITTED from coverage; vacuous-pass prevented)." >&2
        flags=$((flags + 1))
      fi
    done <<EOF
$ids
EOF
  done

  if [ "$flags" -ne 0 ]; then
    echo "reconcile.sh: source-parity inventory INCOMPLETE — $flags flag(s). The §4 vector's G3 clause does NOT pass." >&2
    return 1
  fi
  echo "reconcile.sh: source-parity inventory COMPLETE (every declared source is covered; no dangling/empty/omitted)."
  return 0
}

# --- part (ii): full reconcile (0 unaccounted) -----------------------------

# _scope_anchor ANCHOR (content on stdin) — mirror of the detector's anchor
# scoping so the reconciler hashes the SAME region the detector would. Extract
# from the first line containing the anchor up to the next heading (or EOF).
_scope_anchor() {
  local anchor="$1"
  awk -v a="$anchor" '
    index($0, a) > 0 && !inzone { inzone=1; print; next }
    inzone && /^#/ { exit }
    inzone { print }
  '
}

# _recon_key KIND ID — stable per-source ledger key.
_recon_key() {
  printf '%s\037%s' "$1" "$2" | _hash
}

# _observe_source KIND ID DEF — observe current scoped state; echo the hash on
# success (rc 0). rc 1 = FAIL LOUD (source error / ambiguous-empty), same G2a
# discipline as the detector: an error is never silently "no state".
_observe_source() {
  local kind="$1" id="$2" def="$3"
  local anchor raw rc deftmp
  anchor="$(printf '%s' "$def" | jq -r '.anchor // empty')"
  mkdir -p "$RECON_DIR"
  # shellcheck disable=SC2154
  deftmp="$(mktemp "$RECON_DIR/${_wake_tmp_prefix}defXXXXXX")" || return 1
  printf '%s' "$def" >"$deftmp"
  raw="$("$WAKE_DETECTOR_SOURCE_CMD" "$kind" "$id" <"$deftmp" 2>/dev/null)"
  rc=$?
  rm -f "$deftmp"
  if [ "$rc" -ne 0 ]; then
    echo "reconcile.sh: FAIL LOUD (G2a) — source '$kind/$id' errored (adapter exit $rc). Cannot certify parity; not treated as 'no state'." >&2
    return 1
  fi
  if [ -z "$raw" ]; then
    echo "reconcile.sh: FAIL LOUD (G2a) — source '$kind/$id' returned AMBIGUOUS-EMPTY (empty-that-might-mean-hidden is never 'no state')." >&2
    return 1
  fi
  local scoped
  if [ -n "$anchor" ]; then
    scoped="$(printf '%s' "$raw" | _scope_anchor "$anchor")"
    if [ -z "$scoped" ]; then
      echo "reconcile.sh: FAIL LOUD (G2a) — source '$kind/$id' anchor '$anchor' not present (ambiguous section state)." >&2
      return 1
    fi
  else
    scoped="$raw"
  fi
  printf '%s' "$scoped" | _hash
}

# _inbox_has KIND ID HASH — true iff a pending inbox entry reflects this exact
# source state (observed_seq/inbox is the §4/G3 accounting universe).
_inbox_has() {
  local kind="$1" id="$2" h="$3" n
  n="$("$STORE_SH" drain 2>/dev/null | jq -s --arg k "$kind" --arg id "$id" --arg h "$h" \
    '[ .[] | select(.locators.kind==$k and .locators.id==$id and .locators.observed_hash==$h) ] | length' 2>/dev/null || echo 0)"
  [ "${n:-0}" -gt 0 ]
}

cmd_reconcile() {
  local enumerate=1
  while [ $# -gt 0 ]; do
    case "$1" in
    --no-enumerate)
      enumerate=0
      shift
      ;;
    *)
      echo "reconcile.sh reconcile: unknown option '$1'" >&2
      exit 2
      ;;
    esac
  done

  local json
  json="$(_load_watchlist)" || exit $?
  if [ -z "${WAKE_DETECTOR_SOURCE_CMD:-}" ]; then
    echo "reconcile.sh: WAKE_DETECTOR_SOURCE_CMD is not set (no adapter to observe source state)" >&2
    exit 2
  fi

  "$STORE_SH" init >/dev/null 2>&1 || true
  mkdir -p "$RECON_DIR"

  # Seq allocation base: the store's authoritative observed_seq (§2.4).
  local obs_base offset
  obs_base="$("$STORE_SH" cursors 2>/dev/null | sed -n 's/^observed_seq=//p')"
  case "$obs_base" in '' | *[!0-9]*) obs_base=0 ;; esac
  offset=0

  local pairs kind id failed=0 unaccounted=0 enumerated=0
  pairs="$(printf '%s' "$json" | jq -r '[ .watches[].sources[] | "\(.kind)\t\(.id)" ] | unique | .[]')"
  if [ -z "$pairs" ]; then
    echo "reconcile.sh: watch-list declares no sources under watches[].sources[]" >&2
    exit 2
  fi

  echo "# full reconcile (declared+configured source state vs observed_seq/inbox)"
  while IFS=$'\t' read -r kind id; do
    [ -n "$kind" ] || continue
    local coll def
    if ! coll="$(_coll_for_kind "$kind")"; then
      echo "reconcile.sh: FAIL LOUD — unknown source kind '$kind' in watch-list" >&2
      failed=1
      continue
    fi
    def="$(printf '%s' "$json" | jq -c --arg c "$coll" --arg id "$id" '(.[$c] // []) | map(select(.id == $id)) | .[0] // empty')"
    if [ -z "$def" ]; then
      echo "reconcile.sh: FAIL LOUD (G3 parity) — watch references '$kind/$id' but no such entry is declared in '$coll'" >&2
      failed=1
      continue
    fi

    local curhash key ledger accounted
    if ! curhash="$(_observe_source "$kind" "$id" "$def")"; then
      failed=1
      continue
    fi
    key="$(_recon_key "$kind" "$id")"
    ledger="$RECON_DIR/seen-$key"

    accounted=0
    # Reflected in the durable inbox (delivered, awaiting consume)?
    if _inbox_has "$kind" "$id" "$curhash"; then
      accounted=1
    # Or already reconciled to this exact state before (durable ledger)?
    elif [ -f "$ledger" ] && [ "$(tr -d '[:space:]' <"$ledger")" = "$curhash" ]; then
      accounted=1
    fi

    if [ "$accounted" -eq 1 ]; then
      printf '  %s/%s: ACCOUNTED\n' "$kind" "$id"
      continue
    fi

    # UNACCOUNTED: a source state not reflected in observed_seq/inbox => a gap.
    unaccounted=$((unaccounted + 1))
    printf '  %s/%s: UNACCOUNTED (current state not reflected in observed_seq/inbox)\n' "$kind" "$id" >&2

    if [ "$enumerate" -eq 1 ]; then
      # ENUMERATE the pre-existing/startup obligation into the durable store.
      # Allocate a seq from the store's authoritative observed_seq (see header
      # contract note). Class = non-coalescible fail-safe `actionable` (§2.3) so
      # distinct pre-existing obligations never collapse together.
      offset=$((offset + 1))
      local seq locators
      seq=$((obs_base + offset))
      locators="$(jq -cn --arg kind "$kind" --arg id "$id" --arg hash "$curhash" \
        --argjson sdef "$def" \
        '{kind:$kind, id:$id, observed_hash:$hash, reconciled:true}
           + ( $sdef | {repo, path, anchor, remote, branches} | with_entries(select(.value != null)) )')"
      if "$STORE_SH" enqueue --seq "$seq" --class actionable --locators "$locators" >/dev/null 2>&1; then
        printf '%s' "$curhash" | _atomic_write "$ledger"
        enumerated=$((enumerated + 1))
        printf '    -> enumerated into store as observed_seq=%s (class=actionable)\n' "$seq"
      else
        echo "reconcile.sh: enumerate FAILED for '$kind/$id' seq $seq" >&2
        failed=1
      fi
    fi
  done <<EOF
$pairs
EOF

  echo "reconcile.sh: UNACCOUNTED=$unaccounted ENUMERATED=$enumerated"
  if [ "$failed" -ne 0 ]; then
    echo "reconcile.sh: reconcile FAILED (a source could not be observed/enumerated)." >&2
    return 1
  fi
  if [ "$unaccounted" -ne 0 ]; then
    if [ "$enumerate" -eq 1 ]; then
      echo "reconcile.sh: FLAG — $unaccounted unaccounted source-state(s) found and enumerated. Re-run to confirm 0." >&2
    else
      echo "reconcile.sh: FLAG — $unaccounted unaccounted source-state(s) (audit mode; nothing enumerated)." >&2
    fi
    return 1
  fi
  echo "reconcile.sh: reconcile CLEAN — 0 unaccounted (every declared source state is reflected in observed_seq/inbox)."
  return 0
}

cmd_check() {
  # The full §4/G3 gate, side-effect-free.
  local rc=0
  cmd_inventory || rc=1
  cmd_reconcile --no-enumerate || rc=1
  if [ "$rc" -eq 0 ]; then
    echo "reconcile.sh: G3 GATE PASS — inventory complete AND 0 unaccounted."
  else
    echo "reconcile.sh: G3 GATE FAIL — inventory incomplete OR unaccounted state present." >&2
  fi
  return "$rc"
}

main() {
  [ $# -ge 1 ] || {
    usage
    exit 2
  }
  local cmd="$1"
  shift
  case "$cmd" in
  inventory) cmd_inventory "$@" ;;
  reconcile) cmd_reconcile "$@" ;;
  check) cmd_check "$@" ;;
  -h | --help | help) usage ;;
  *)
    echo "reconcile.sh: unknown command '$cmd'" >&2
    usage
    exit 2
    ;;
  esac
}

main "$@"