#!/usr/bin/env bash
###############################################################################
# conformance/run.sh — the single-command conformance runner (R-TEST-02/03/04)
#
# ONE command runs the suite (or a requirement-/layer-scoped subset) and always
# emits JUnit + a requirement-coverage report. Local runs and the in-cluster CI
# Chainsaw Job invoke this same script so results are identical (reproducibility).
#
#   ./run.sh                          # full suite; skips L1/L2/L3 if no cluster
#   ./run.sh --requirements R-NET-01,R-NET-06   # merge-gate subset (tagged)
#   ./run.sh --layer l2               # one layer (l0|l1|l2|l3|meta|all; l0/l1 need no cluster)
#   ./run.sh --requirements R-NET-01,R-NET-02 --layer l2   # intersect: tagged AND in layer
#   ./run.sh --layer l0 --requirements R-X --include-scope whole-repo
#                                     # UNION: the tagged subset PLUS every test that
#                                     #   DECLARES `conformance.home.k3s/scope: whole-repo`.
#                                     #   A whole-repo invariant must run on EVERY gate
#                                     #   invocation — see lib/common.sh's scope block for
#                                     #   why, and why a SKIP of one is exit 3, not green.
#   ./run.sh --coverage-only          # regenerate coverage report only (no cluster)
#   ./run.sh --status                 # DERIVED STATUS report only (no cluster): per
#                                     #   requirement, is it implemented, is it actually
#                                     #   reconciled by Flux, is its test executable or a
#                                     #   scaffold, and whether the committed run ledger
#                                     #   (runs/ledger.jsonl) actually proves it — see
#                                     #   lib/status.py. No ledger row => not-derivable.
#   ./run.sh --lint                   # structural-validate test defs (no cluster)
#   ./run.sh --print-selection        # print the test dirs the CURRENT selection resolves
#                                     #   to, one per line, and exit. Runs no check. This is
#                                     #   how a test can PROVE the selection includes it
#                                     #   (tests/l0-static/whole-repo-invariants-wired) without
#                                     #   executing the suite and recursing into itself.
#   ./run.sh --strict-coverage        # hygiene gate: fail on tag/annotation drift
#   ./run.sh --requirements R-NET-01  # ALSO asserts those IDs are covered (merge gate)
#   ./run.sh --require-all            # phase-exit: every requirement must be covered
#   ./run.sh --record                 # RUN AND CAPTURE: tee the whole run to
#                                     #   runs/<UTC>-<short-sha>/run.log, copy the JUnit
#                                     #   beside it, and append one ledger row per
#                                     #   testcase to runs/ledger.jsonl (lib/record_run.py)
#
# --record — PROOF-OF-PASS, CAPTURED AT RUN TIME (why it is a separate flag)
# --------------------------------------------------------------------------
# Without it, nothing about a green run ever reaches repo state: _artifacts/ is gitignored
# and the root .gitignore kills *.junit.xml globally, which is why `--status` reports
# PROVEN 0 for all 51 requirements. `--record` writes the one tracked thing that fixes
# that — `conformance/runs/` (see conformance/.gitignore for the negations).
#
# RECORDING IS DELIBERATELY EXPLICIT. A run that silently records itself is how a bad run
# becomes a permanent false proof, so the plain `./run.sh` writes no ledger row at all.
#
# BOTH FILES ARE KEPT, and the LOG is the load-bearing one. The L2/L3 tests self-skip
# GREEN: when a precondition is missing they echo e.g. `DR_RESTORE_SKIPPED_OK` and exit 0,
# and Chainsaw records `passed` exactly as on a real run. Chainsaw's JUnit carries no
# stdout, so the sentinel token in run.log is the ONLY thing that separates proven from
# skipped. A JUnit committed on its own would record a skip as proof of R-STATE-03.
#
# Artifacts (always written under conformance/_artifacts/, gitignored):
#   _artifacts/report.junit.xml        JUnit (Chainsaw output, or skipped-scaffold shim)
#   _artifacts/coverage/coverage.md    human coverage report
#   _artifacts/coverage/coverage.json  machine coverage report
#   _artifacts/status/status.md        human requirement-status report (--status)
#   _artifacts/status/status.json      machine requirement-status report (--status)
#
# Environment (both set ONLY by the in-cluster Job, incluster/chainsaw-job.yaml):
#   CONF_ARTIFACTS=<dir>           relocate the artifact tree off the default
#                                  conformance/_artifacts (the Job mounts a `results`
#                                  volume, which cannot sit inside the git-clone target).
#   CONF_EMIT_ARTIFACTS_TGZ=1      on exit — pass, fail or abort — print a delimited,
#                                  checksummed base64 tar of the artifact tree to STDOUT,
#                                  because `kubectl logs` is the only channel CI has out of
#                                  the Job (no pods/exec, no kubectl cp). See the RESULTS
#                                  TRANSPORT block below for the envelope and for the five
#                                  checks a collector MUST make. Never set this locally.
#
# Run ledger (TRACKED — commit these; --record only):
#   runs/<UTC>-<short-sha>/run.log            full tee'd run output (carries the sentinels)
#   runs/<UTC>-<short-sha>/report.junit.xml   the JUnit for that same run
#   runs/ledger.jsonl                         append-only, one row per testcase per run
#
# Phase 0: no cluster exists. The behavior tests are valid scaffolds that cannot
# execute yet, so run.sh emits a *skipped* JUnit and a coverage report, and exits
# green — the harness is proven reproducible while later phases fill in behavior.
###############################################################################
set -euo pipefail

CONF_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
export CONF_ROOT
# shellcheck source=lib/common.sh
source "${CONF_ROOT}/lib/common.sh"
# shellcheck source=versions.env
source "${CONF_ROOT}/versions.env"

# CONF_ARTIFACTS relocates the whole artifact tree. The in-cluster Job needs it (see
# incluster/chainsaw-job.yaml): its `results` volume cannot be mounted at the default
# path, because that path is inside the directory the init container `git clone`s into and
# a mounted-in directory would make the clone target non-empty. Unset everywhere else, so
# a local run is byte-identical to what it always was.
ARTIFACTS="${CONF_ARTIFACTS:-${CONF_ROOT}/_artifacts}"
COVERAGE_OUT="${ARTIFACTS}/coverage"
STATUS_OUT="${ARTIFACTS}/status"
JUNIT_OUT="${ARTIFACTS}/report.junit.xml"
PYTHON="${PYTHON:-python3}"

# Every argument as given, so `--record` can re-exec this script unchanged (minus itself)
# under `tee`. Captured BEFORE parsing so nothing is normalized away.
ORIG_ARGS=("$@")

LAYER="all"
REQS=""
INCLUDE_SCOPES=""   # --include-scope: scopes unioned into the selection (see lib/common.sh)
MODE="run"          # run | coverage-only | status | lint
STRICT_COVERAGE=0
REQUIRE_ALL=0
FORCE_NO_CLUSTER=0
RECORD=0

# Documented, out-of-scope coverage gaps exempt from the completeness gate: requirements
# owned by another workstream that WS-TEST does not yet scaffold. Listed here so the
# exemption is explicit and reviewable, not silent.
#
# EMPTY as of 2026-09-01. R-ENV-02 and R-GITOPS-01 were the last two entries — exempted
# because they were unscaffolded while the coarse path->requirement map keys clusters/*
# and ci/* to them, so any overlay/CI edit would have false-blocked. They now have a real
# verifying L0 test (tests/l0-static/flux-postbuild-substitution), which asserts the
# substitution mechanism that IS the "authored once, promoted" contract, so they are
# covered rather than exempt and the completeness gate can hold them to it. That test
# names its own limits in its header: it proves the STATIC property (no manifest renders
# an undefined variable), not the live-cluster half of either requirement.
#
# FOLLOW-UP (WS-TEST) — HALF DONE. The debt was "make the matcher stop keying on doc-header
# tokens so real requirements need not be exempted". The CONTENT-SCAN half is now fixed in
# ci/touched-requirements.sh: it scans the added/removed lines of the diff, and skips *.md, so
# a requirement named in a header or in prose no longer counts as a declaration. Consequence
# to be aware of: a manifest whose HEADER declares the requirements it serves no longer
# contributes those IDs unless the change actually touches a line carrying them — the
# authoritative signal is the `conformance.home.k3s/R-*` label on a test, which still is.
# The PATH-MAP half remains: ci/touched-requirements.sh keys clusters/* and ci/* to
# R-ENV-02 + R-GITOPS-01 wholesale, which is why those two must stay exempted here. Tighten
# the path map (or scaffold the two requirements) and this list empties.
#
# R-STATE-02 (node-loss) WAS listed here (owned by WS-STORAGE, "delivered with Longhorn/infra")
# but now has a real verifying L3 test — tests/l3-fault-injection/node-loss — so it is no
# longer a gap and has been removed from this list; the coverage report counts it as covered.
DOCUMENTED_GAPS=""

# Print the header block (line 2 through the closing `####` rule, which is dropped) as
# help. Bounded by the rule rather than a fixed line number so the header can grow.
usage() { sed -n '2,/^#####/p' "${BASH_SOURCE[0]}" | sed '$d' | sed 's/^# \{0,1\}//'; }

while [ $# -gt 0 ]; do
  case "$1" in
    --layer)          LAYER="$2"; shift 2 ;;
    --requirements)   REQS="$(conf_normalize_reqs "$2")"; shift 2 ;;
    --include-scope)  INCLUDE_SCOPES="${INCLUDE_SCOPES:+${INCLUDE_SCOPES},}$2"; shift 2 ;;
    --coverage-only)  MODE="coverage-only"; shift ;;
    --status)         MODE="status"; shift ;;
    --lint)           MODE="lint"; shift ;;
    --print-selection) MODE="print-selection"; shift ;;
    --strict-coverage) STRICT_COVERAGE=1; shift ;;
    --require-all)    REQUIRE_ALL=1; shift ;;
    --no-cluster)     FORCE_NO_CLUSTER=1; shift ;;
    --record)         RECORD=1; shift ;;
    -h|--help)        usage; exit 0 ;;
    *) echo "unknown arg: $1" >&2; usage; exit 2 ;;
  esac
done

mkdir -p "${ARTIFACTS}" "${COVERAGE_OUT}" "${STATUS_OUT}"

log() { printf '\033[1m[run.sh]\033[0m %s\n' "$*"; }

###############################################################################
# --record: capture this run as committed evidence, then hand it to the ledger.
#
# Implemented as a ONE-LEVEL re-exec of this same script under `tee`, so the run itself is
# byte-for-byte the ordinary run (same code path, same artifacts) and the log is the exact
# operator-visible output — no second, differently-behaving "recording mode" to drift.
# CONF_RECORD_CHILD guards against recursion.
#
# The recorder runs REGARDLESS of the run's exit status: a red run must be recorded as red
# (that is evidence too), and run.sh still exits with the child's real rc, so no gate is
# softened by recording. `${PIPESTATUS[0]}` is what carries that rc past `tee`.
###############################################################################
if [ "${RECORD}" = 1 ] && [ -z "${CONF_RECORD_CHILD:-}" ]; then
  case "${MODE}" in
    run) ;;
    # --record is about EVIDENCE OF A RUN. --coverage-only/--status/--lint execute no
    # test, so a ledger row from one of them would be a row about nothing.
    *) echo "--record captures a TEST RUN; --${MODE} executes none." >&2; exit 2 ;;
  esac
  RUN_SHA="$(git -C "${CONF_ROOT}" rev-parse --short HEAD 2>/dev/null || echo nogit)"
  RUN_ID="$(date -u +%Y%m%dT%H%M%SZ)-${RUN_SHA}"
  RUN_DIR="${CONF_ROOT}/runs/${RUN_ID}"
  mkdir -p "${RUN_DIR}"
  # Drop any JUnit left behind by a PREVIOUS run before starting, so this run dir can only
  # ever capture a report THIS run produced. Copying a stale artifact would pair someone
  # else's result with this run's log — a fabricated pairing, which is precisely the class
  # of false proof the ledger exists to prevent.
  rm -f "${JUNIT_OUT}"
  # Strip --record from the argv handed to the child; everything else passes through.
  CHILD_ARGS=()
  for a in ${ORIG_ARGS[@]+"${ORIG_ARGS[@]}"}; do
    [ "$a" = "--record" ] || CHILD_ARGS+=("$a")
  done
  log "RECORD: capturing this run to runs/${RUN_ID}/ (run.log + report.junit.xml)"
  set +e
  CONF_RECORD_CHILD=1 "${BASH_SOURCE[0]}" ${CHILD_ARGS[@]+"${CHILD_ARGS[@]}"} 2>&1 \
    | tee "${RUN_DIR}/run.log"
  RUN_RC=${PIPESTATUS[0]}
  set -e
  if [ -f "${JUNIT_OUT}" ]; then
    cp "${JUNIT_OUT}" "${RUN_DIR}/report.junit.xml"
  else
    log "RECORD: no ${JUNIT_OUT} was produced — the ledger step will SKIP (never green)."
  fi
  # Explicit, separate step: read the JUnit + the log and append one row per testcase.
  # rc 3 = inputs absent (nothing recorded, not green); it must not mask the run's own rc.
  # CONF_LEDGER exists so the harness's own tests can exercise this path without writing
  # to the real ledger; operators should never set it.
  "${PYTHON}" "${CONF_ROOT}/lib/record_run.py" \
    --run-dir "${RUN_DIR}" ${CONF_ENV:+--env "$CONF_ENV"} \
    --ledger "${CONF_LEDGER:-${CONF_ROOT}/runs/ledger.jsonl}" || true
  log "RECORD: run rc=${RUN_RC}. Commit conformance/runs/${RUN_ID}/ WITH its run.log and"
  log "RECORD: conformance/runs/ledger.jsonl — an uncommitted ledger proves nothing."
  exit "${RUN_RC}"
fi

###############################################################################
# RESULTS TRANSPORT (in-cluster only): a self-describing, truncation-detectable
# base64 tar of the artifact tree, printed to STDOUT. OFF unless CONF_EMIT_ARTIFACTS_TGZ=1.
#
# WHY THIS LIVES IN run.sh AND NOT IN THE JOB MANIFEST. The admission policy that bounds
# the CI trigger (platform/kyverno/admission/conformance-trigger-job-shape.yaml, Enforce +
# fail-closed) pins the Job's `command` to exactly ["./run.sh"], so no shell may wrap the
# suite to package artifacts afterwards. And the trigger identity deliberately holds NO
# pods/exec and cannot `kubectl cp` (R-SEC-02; docs/plans/l2-l3-conformance-ci-wiring.md
# §3.3 and §4), so `kubectl logs` is the ONLY channel out of the Job. The runner therefore
# has to put its own artifacts on its own stdout. It is an EXIT trap, so a FAILED run still
# ships its JUnit — the red report is the evidence the gate needs most.
#
# WHY THE ENVELOPE LOOKS LIKE THIS. `kubectl logs` is a lossy channel: `--tail`, a rotated
# CRI log file, a dropped watch, or CRI's per-line split can each deliver a mere PREFIX of
# the stream. base64 decodes a truncated stream without complaint, into a tar that gunzip
# may even partially unpack — silent, plausible garbage. So the envelope carries everything
# needed to PROVE completeness, and carries it TWICE:
#
#   === ARTIFACTS-TGZ-BASE64 BEGIN v1 rc=<rc> bytes=<n> lines=<l> sha256=<hex> ===
#   <base64 of the .tgz, wrapped at 76 columns>
#   === ARTIFACTS-TGZ-BASE64 END v1 rc=<rc> bytes=<n> lines=<l> sha256=<hex> ===
#
# THE COLLECTOR MUST DO ALL FIVE CHECKS, and treat any failure as a COLLECTION FAILURE —
# never as "no artifacts", never as a pass:
#   1. exactly one BEGIN line and exactly one END line;
#   2. the two header payloads (everything after BEGIN/END) byte-identical — a mismatch
#      means two interleaved or re-emitted envelopes in one log;
#   3. the count of body lines between them equals lines=;
#   4. the decoded byte count equals bytes=;
#   5. sha256 of the decoded bytes equals sha256=.
# No check is sufficient alone. A head-truncated log fails (1); a tail-truncated one fails
# (1); a dropped interior line fails (3) and (5); a corrupted line that preserves the line
# count fails (5). (1)+(2) are what make a partial log DETECTABLE rather than decodable,
# which is the whole design requirement.
#
# `rc=` is the suite's own exit code, carried INSIDE the envelope so CI can cross-check it
# against the Job's completion condition instead of trusting either signal alone.
#
# The archive holds the CONTENTS of the artifact tree (`tar -C "$ARTIFACTS" .`), not the
# directory itself: CONF_ARTIFACTS makes that directory's NAME environment-specific
# (`/results` in the Job, `conformance/_artifacts` locally), and an archive whose top-level
# entry changed with the environment would be a trap for the collector. It unpacks the
# contents wherever it likes.
#
# A packaging failure prints a single `... ERROR ...` marker and NOTHING else: no BEGIN, so
# the collector's check (1) fails and it cannot mistake the run for one with no artifacts.
###############################################################################
CONF_ARTIFACT_MARKER="ARTIFACTS-TGZ-BASE64"
CONF_ARTIFACT_ENVELOPE_VERSION="v1"

conf_emit_artifacts_tgz() {
  local rc="${1:-0}"
  # Disarm FIRST: this runs from the EXIT trap and re-arming would recurse on the `exit`
  # below. That explicit `exit "${rc}"` is also what guarantees this whole function cannot
  # change the run's verdict — nothing here can turn a red run green or a green run red.
  trap - EXIT
  (
    set +e
    local tmp tgz b64 bytes lines sha payload
    tmp="${TMPDIR:-/tmp}"
    tgz="${tmp}/conformance-artifacts.$$.tgz"
    b64="${tgz}.b64"
    if ! tar -czf "${tgz}" -C "${ARTIFACTS}" . 2>/dev/null; then
      printf '=== %s ERROR %s rc=%s reason=tar-failed path=%s ===\n' \
        "${CONF_ARTIFACT_MARKER}" "${CONF_ARTIFACT_ENVELOPE_VERSION}" "${rc}" "${ARTIFACTS}"
      rm -f "${tgz}"
      exit 0
    fi
    if ! base64 -w 76 < "${tgz}" > "${b64}" || ! command -v sha256sum >/dev/null 2>&1; then
      printf '=== %s ERROR %s rc=%s reason=encode-failed ===\n' \
        "${CONF_ARTIFACT_MARKER}" "${CONF_ARTIFACT_ENVELOPE_VERSION}" "${rc}"
      rm -f "${tgz}" "${b64}"
      exit 0
    fi
    bytes="$(wc -c < "${tgz}" | tr -d '[:space:]')"
    lines="$(wc -l < "${b64}" | tr -d '[:space:]')"
    sha="$(sha256sum "${tgz}" | cut -d' ' -f1)"
    payload="${CONF_ARTIFACT_ENVELOPE_VERSION} rc=${rc} bytes=${bytes} lines=${lines} sha256=${sha}"
    printf '=== %s BEGIN %s ===\n' "${CONF_ARTIFACT_MARKER}" "${payload}"
    cat "${b64}"
    printf '=== %s END %s ===\n' "${CONF_ARTIFACT_MARKER}" "${payload}"
    rm -f "${tgz}" "${b64}"
    exit 0
  )
  exit "${rc}"
}

# Armed here, AFTER the --record re-exec above, so the recorder's parent process never
# emits a second envelope into its child's tee'd log.
if [ "${CONF_EMIT_ARTIFACTS_TGZ:-0}" = 1 ]; then
  trap 'conf_emit_artifacts_tgz "$?"' EXIT
fi

# --- Coverage report is always produced (cluster-independent, R-TEST-04) --------------
gen_coverage() {
  # Pass --allow-gap only when there IS an exemption: an empty DOCUMENTED_GAPS means no
  # requirement is exempt, and handing the flag an empty string would be a silent no-op
  # that reads like an exemption in the CLI log.
  local flags=()
  [ -n "${DOCUMENTED_GAPS}" ] && flags+=(--allow-gap "${DOCUMENTED_GAPS}")
  [ "${STRICT_COVERAGE}" = 1 ] && flags+=(--strict)
  # A tagged subset run is also the merge gate: the touched requirements MUST be covered.
  [ -n "${REQS}" ] && flags+=(--require "${REQS}")
  [ "${REQUIRE_ALL}" = 1 ] && flags+=(--require-all)
  "${PYTHON}" "${CONF_ROOT}/lib/coverage.py" \
    --registry "${CONF_ROOT}/requirements/registry.yaml" \
    --tests "${CONF_ROOT}/tests" \
    --out "${COVERAGE_OUT}" \
    "${flags[@]}"
}

# --- Derived STATUS report (no cluster) ------------------------------------------------
# Coverage answers "does a tagged test EXIST?". Status answers the operator's question —
# "what is the real state of each requirement given what is actually in the repo?" — by
# deriving, per requirement: implementing artifact? reachable from a Flux Kustomization
# (reconciled, not merely authored)? tagged test that is EXECUTABLE rather than a TODO
# scaffold? It REFUSES to derive whether a test passed: nothing tracked in git records a
# run result, and a status report that defaults to green is worse than none.
gen_status() {
  "${PYTHON}" "${CONF_ROOT}/lib/status.py" \
    --repo "$(cd "${CONF_ROOT}/.." && pwd)" \
    --registry "${CONF_ROOT}/requirements/registry.yaml" \
    --tests "${CONF_ROOT}/tests" \
    --out "${STATUS_OUT}" \
    ${CONF_ENV:+--env "$CONF_ENV"} \
    "$@"
}

# --- Structural lint (no cluster): parse each test def and check the tag convention ----
lint_tests() {
  log "Linting test definitions (structural, no cluster)"
  local rc=0 f
  if command -v chainsaw >/dev/null 2>&1; then
    # Prefer chainsaw's own linter when the pinned binary is available.
    while IFS= read -r f; do
      chainsaw lint test --file "$f" >/dev/null || { echo "LINT FAIL: $f" >&2; rc=1; }
    done < <(conf_all_test_files)
  else
    log "chainsaw not on PATH; falling back to structural check"
    # Minimal YAML-shape check: kind Test + at least one requirement label per file.
    while IFS= read -r f; do
      grep -Eq '^kind:\s*Test' "$f" || { echo "LINT FAIL (no kind: Test): $f" >&2; rc=1; }
      grep -Eq "^[[:space:]]*${CONF_LABEL_PREFIX}/R-[A-Z0-9]+-[0-9]+:" "$f" \
        || { echo "LINT FAIL (no requirement label): $f" >&2; rc=1; }
    done < <(conf_all_test_files)
  fi
  return $rc
}

# --- Select which test directories Chainsaw should run --------------------------------
# Requirement-scoped selection, then the DECLARED-SCOPE union on top:
#
#   (--requirements ∩ --layer)  ∪  (--include-scope ∩ --layer)
#
# The left half is R-TEST-03's touched subset. The right half is the fix for its blind
# spot: an invariant that quantifies over the whole tracked tree cannot be selected BY the
# requirements a change touches, because the change most likely to break it touches none of
# them. See lib/common.sh's scope block for the incidents. The union is fail-closed by
# construction — it can only ADD tests to a run, never remove one.
select_dirs() {
  {
    requirement_scoped_dirs
    # The scope union is still LAYER-bounded: `--layer l0` must not pull a whole-repo-scoped
    # L2 test into an offline run. With no --layer (all), nothing is bounded away.
    if [ -n "${INCLUDE_SCOPES}" ]; then
      if [ "${LAYER}" != all ]; then
        comm -12 \
          <(conf_dirs_for_scopes "${INCLUDE_SCOPES}") \
          <(conf_dirs_for_layer "${LAYER}")
      else
        conf_dirs_for_scopes "${INCLUDE_SCOPES}"
      fi
    fi
  } | sort -u
}

# The pre-existing requirement/layer selection, unchanged:
# --requirements AND --layer together => intersection (tests carrying the tag
# AND living in that layer subtree). Either alone keeps its prior meaning, so
# this is backward compatible (LAYER defaults to "all"). Both helpers emit
# sorted, de-duplicated dirs, so `comm -12` yields the intersection.
requirement_scoped_dirs() {
  if [ -n "${REQS}" ] && [ "${LAYER}" != all ]; then
    comm -12 \
      <(conf_dirs_for_requirements "${REQS}") \
      <(conf_dirs_for_layer "${LAYER}")
  elif [ -n "${REQS}" ]; then
    conf_dirs_for_requirements "${REQS}"
  else
    conf_dirs_for_layer "${LAYER}"
  fi
}

# --- HEAVY tests: the storage/VM/DR tests whose KubeVirt-CDI imports + Longhorn volume ops
#     spike embedded-etcd I/O on the small dev VMs. Run SERIALLY (parallel=1) in their own
#     pass so their etcd spikes never coincide with ANOTHER test's setup — the coincidence
#     that made a single heavy test's apiserver blip fail-close Kyverno admission and abort
#     every in-flight test's 0.01s setup (see config/chainsaw-config.yaml). Keyed by the test
#     DIRECTORY basename (stable); override via CONF_HEAVY_TESTS to add/remove without code
#     changes. Listed here even for tests still scaffolded (vm-lifecycle, dr-restore, ...) so
#     the serialization is already correct the moment they grow real KubeVirt/Longhorn bodies.
CONF_HEAVY_TESTS="${CONF_HEAVY_TESTS:-vm-lifecycle vm-data-survival vm-default-deny data-survival dr-restore node-loss}"

conf_is_heavy_dir() {
  # $1 = test dir; true if its basename is in the heavy set.
  local base t
  base="$(basename "$1")"
  for t in ${CONF_HEAVY_TESTS}; do [ "$base" = "$t" ] && return 0; done
  return 1
}

# One Chainsaw invocation over a specific set of dirs, at a given parallelism, writing to a
# named report file. Returns chainsaw's rc (0=all passed) WITHOUT aborting run.sh (callers
# collect both passes' rc so a light-pass failure still lets the heavy pass run, and vice
# versa). failFast stays false (config) so every test in the pass runs regardless.
run_chainsaw_pass() {
  local report_name="$1" parallel="$2"; shift 2
  local -a dirs=("$@")
  local -a test_dir_args=()
  local d
  for d in "${dirs[@]}"; do test_dir_args+=(--test-dir "$d"); done
  # Chainsaw writes JUnit per config/chainsaw-config.yaml (report.* under _artifacts).
  # --report-path is passed ABSOLUTE (overriding the config's relative `_artifacts`) so the
  # report write succeeds regardless of the caller's CWD. --report-name/--parallel override
  # the config per-pass so the two passes don't clobber each other's report and the heavy
  # pass forces serial execution.
  local rc=0
  chainsaw test \
    --config "${CONF_ROOT}/config/chainsaw-config.yaml" \
    --report-path "${ARTIFACTS}" \
    --report-name "${report_name}" \
    --parallel "${parallel}" \
    "${test_dir_args[@]}" || rc=$?
  return $rc
}

# --- Execute the Chainsaw suite against a live cluster ---------------------------------
# Split into a LIGHT pass (concurrent, config parallelism) and a HEAVY pass (serial,
# parallel=1). Robust single-pass green: the heavy etcd spikes are isolated in time from the
# light tests' setup, so a heavy test's transient apiserver blip can no longer cascade into
# mass fail-closed setup-aborts of unrelated tests. The two JUnit reports are stitched back
# into the one stable artifact CI collects (report.junit.xml) via lib/merge_junit.py, so the
# split is invisible to everything downstream.
run_chainsaw() {
  local -a dirs
  mapfile -t dirs < <(select_dirs)
  if [ "${#dirs[@]}" -eq 0 ]; then
    log "No tests match the selection (layer=${LAYER} reqs='${REQS}')."
    return 0
  fi

  local -a light=() heavy=()
  local d
  for d in "${dirs[@]}"; do
    if conf_is_heavy_dir "$d"; then heavy+=("$d"); else light+=("$d"); fi
  done

  mkdir -p "${ARTIFACTS}"
  local light_report="${ARTIFACTS}/chainsaw-report-light.xml"
  local heavy_report="${ARTIFACTS}/chainsaw-report-heavy.xml"
  rm -f "${light_report}" "${heavy_report}"
  local light_rc=0 heavy_rc=0

  # Determine the light pass's parallelism from the shared config (single source of truth),
  # falling back to 2 if unreadable — so bumping the config on prod-class hw needs no run.sh edit.
  local light_parallel
  light_parallel="$(sed -nE 's/^[[:space:]]*parallel:[[:space:]]*([0-9]+).*/\1/p' \
                      "${CONF_ROOT}/config/chainsaw-config.yaml" | head -1)"
  [ -n "${light_parallel}" ] || light_parallel=2

  if [ "${#light[@]}" -gt 0 ]; then
    log "LIGHT pass: ${#light[@]} test(s), parallel=${light_parallel} (pinned ${CHAINSAW_VERSION})"
    run_chainsaw_pass "chainsaw-report-light" "${light_parallel}" "${light[@]}" || light_rc=$?
  else
    log "LIGHT pass: no tests selected."
  fi

  if [ "${#heavy[@]}" -gt 0 ]; then
    log "HEAVY pass: ${#heavy[@]} test(s) SERIAL (parallel=1) — ${heavy[*]##*/}"
    run_chainsaw_pass "chainsaw-report-heavy" 1 "${heavy[@]}" || heavy_rc=$?
  else
    log "HEAVY pass: no heavy tests selected."
  fi

  # Stitch both passes' JUnit into the one stable artifact CI collects.
  "${PYTHON}" "${CONF_ROOT}/lib/merge_junit.py" \
    --out "${JUNIT_OUT}" --name chainsaw-report \
    "${light_report}" "${heavy_report}"

  # Overall result is the union: fail if EITHER pass had a failing/erroring test. Real
  # failures still surface (nothing is masked); the split only changes WHEN heavy tests run.
  if [ "${light_rc}" -ne 0 ] || [ "${heavy_rc}" -ne 0 ]; then
    log "Chainsaw reported failures (light rc=${light_rc}, heavy rc=${heavy_rc})."
    return 1
  fi
  return 0
}

# --- L0/L1: the cluster-INDEPENDENT layers (docs/14) ------------------------------------
# docs/14 puts TWO layers in CI without a cluster:
#   L0 static/policy  tests/l0-static/**   each dir carries a `check.sh`        (repo invariants)
#   L1 rendering      tests/l1-rendering/** each dir carries a `render-check.sh` (render == golden)
# Both are executed directly here and emit a REAL pass/fail JUnit, instead of being skipped
# with the cluster-gated layers. Honors the same --layer/--requirements selection as the rest
# of the suite (select_dirs), filtered to those two subtrees.
OFFLINE_SUBTREES='/l0-static/|/l1-rendering/'

offline_selected_dirs() {
  select_dirs | grep -E "${OFFLINE_SUBTREES}" || true
}

# True when EVERY requested layer is cluster-independent, so the offline result is the
# whole result and run.sh must exit on it (the ci/l0.sh + ci/l1.sh merge-gate paths).
layers_are_offline_only() {
  local l
  [ "${LAYER}" = all ] && return 1
  for l in ${LAYER//,/ }; do
    case "$l" in l0|l1) ;; *) return 1 ;; esac
  done
  return 0
}

# Markdown one-liner per executed offline check, for the CI step summary. Written next to
# the JUnit; ci/l0.sh + ci/l1.sh splice it into $GITHUB_STEP_SUMMARY so the gate output still
# NAMES every check that ran (that is what the deleted per-check gate stages did, one hard-coded
# `summary` line each — now generated for all of them, whole-repo-scoped ones marked as such).
: "${OFFLINE_SUMMARY_OUT:=${ARTIFACTS}/offline-summary.md}"

run_offline_checks() {
  local -a dirs
  mapfile -t dirs < <(offline_selected_dirs)
  if [ "${#dirs[@]}" -eq 0 ]; then
    log "No L0/L1 offline checks match the selection (layer=${LAYER} reqs='${REQS}')."
    return 0
  fi
  # Declared scopes are passed through so the runner knows WHICH cases must not be allowed to
  # report a SKIP as green (rc 3). See lib/common.sh's scope block and run_l1_offline.py.
  local -a scope_args=() s
  for s in ${INCLUDE_SCOPES//,/ }; do scope_args+=(--unwired-scope "$s"); done
  log "Running ${#dirs[@]} offline L0/L1 check(s) (no cluster; docs/14)."
  [ -n "${INCLUDE_SCOPES}" ] && log "  unconditional (declared scope ${INCLUDE_SCOPES}): $(conf_dirs_for_scopes "${INCLUDE_SCOPES}" | xargs -n1 basename 2>/dev/null | tr '\n' ' ')"
  "${PYTHON}" "${CONF_ROOT}/lib/run_l1_offline.py" \
    --junit "${JUNIT_OUT}" --label-prefix "${CONF_LABEL_PREFIX}" \
    --scope-annotation "${CONF_SCOPE_ANNOTATION}" \
    --summary-out "${OFFLINE_SUMMARY_OUT}" \
    ${scope_args[@]+"${scope_args[@]}"} "${dirs[@]}"
}

###############################################################################
# Main
###############################################################################
# --print-selection is deliberately handled FIRST: it resolves the selection and exits,
# writing nothing and running no check. A test that asserts "the gate's selection cannot
# filter me out" needs to ask that question without executing the suite it is part of.
if [ "${MODE}" = "print-selection" ]; then
  select_dirs
  exit 0
fi

log "Coverage report first (always)"
gen_coverage

case "${MODE}" in
  coverage-only)
    log "coverage-only: done. See ${COVERAGE_OUT}/coverage.md"
    exit 0
    ;;
  status)
    # rc: 0 report written, 1 a derivation/strict failure, 3 a check could not run
    # (SKIPPED, never counted as green — ci/lib.sh convention). Propagated as-is.
    rc=0
    # --strict-coverage is the harness's hygiene switch; apply it to status too.
    status_flags=()
    [ "${STRICT_COVERAGE}" = 1 ] && status_flags+=(--strict)
    gen_status ${status_flags[@]+"${status_flags[@]}"} || rc=$?
    log "status: done. See ${STATUS_OUT}/status.md"
    exit "${rc}"
    ;;
  lint)
    lint_tests
    log "lint: done."
    exit 0
    ;;
esac

# L0 static + L1 rendering are cluster-independent (docs/14): run the selected offline
# checks and treat their result as authoritative REGARDLESS of cluster availability. An
# offline check failure is a real failure (nothing cluster-gated about it), so it always blocks.
# rc 3 is the harness-wide SKIPPED/not-run code (ci/README.md): NOT a pass, NOT a fail. The
# offline runner returns it when a test carrying a --unwired-scope scope SKIPPED — a whole-repo
# invariant reporting "nothing to audit" means the subtree it audits is gone, which the gate
# must see as UNWIRED. It is propagated verbatim so ci/l0.sh can set the gate's own rc=3,
# exactly as the deleted per-check stages did.
OFFLINE_RC=0
run_offline_checks || OFFLINE_RC=$?
if layers_are_offline_only; then
  # Offline-only run (the ci/l0.sh + ci/l1.sh merge-gate paths): the offline result IS the result.
  case "${OFFLINE_RC}" in
    0) log "Done (offline ${LAYER}). JUnit: ${JUNIT_OUT} | Coverage: ${COVERAGE_OUT}/coverage.md" ;;
    3) log "Offline ${LAYER}: a scope-declared check SKIPPED — UNWIRED, not green (rc=3). JUnit: ${JUNIT_OUT}" ;;
    *) log "Offline ${LAYER} checks FAILED (rc=${OFFLINE_RC}). JUnit: ${JUNIT_OUT}" ;;
  esac
  exit "${OFFLINE_RC}"
fi
if [ "${OFFLINE_RC}" -eq 3 ]; then
  log "Offline L0/L1: a scope-declared check SKIPPED — UNWIRED, not green (rc=3)."
  exit 3
fi
if [ "${OFFLINE_RC}" -ne 0 ]; then
  log "Offline L0/L1 checks FAILED (rc=${OFFLINE_RC}) — blocking (not cluster-gated)."
  exit "${OFFLINE_RC}"
fi

# run mode: need a cluster for L2/L3. Without one (Phase 0), emit skipped JUnit for the
# cluster-gated layers. (L1 already ran offline above and passed.)
if [ "${FORCE_NO_CLUSTER}" = 1 ] || ! conf_cluster_reachable; then
  log "No reachable cluster — emitting SKIPPED JUnit scaffold for L2/L3 (Phase 0 behavior)."
  log "NOTE: the offline L0/L1 results above already ran for real; this shim covers L2/L3 only."
  log "Also running structural lint so scaffolds stay valid."
  lint_tests || { log "lint failed"; exit 1; }
  "${PYTHON}" "${CONF_ROOT}/lib/emit_skipped_junit.py" \
    --tests "${CONF_ROOT}/tests" --out "${JUNIT_OUT}"
  log "Done (scaffold mode). JUnit: ${JUNIT_OUT} | Coverage: ${COVERAGE_OUT}/coverage.md"
  exit 0
fi

command -v chainsaw >/dev/null 2>&1 || {
  echo "ERROR: cluster reachable but 'chainsaw' (${CHAINSAW_VERSION}) not on PATH." >&2
  echo "Install the pinned binary or run via the in-cluster Job (incluster/)." >&2
  exit 3
}
run_chainsaw
log "Done. JUnit: ${JUNIT_OUT} | Coverage: ${COVERAGE_OUT}/coverage.md"