Merge pull request 'test: cli.sh reads fixtures, not the host it happens to run on' (#137) from build/136-cli-hermetic into main

Reviewed-on: #137
Reviewed-by: grok-reviewer-andresmgsl <andres+3@heavyduty.builders>
Reviewed-by: kimi-reviewer-andresmgsl <andres+4@heavyduty.builders>
Reviewed-by: codex-reviewer-andresmgsl <andres+2@heavyduty.builders>

docs/templates/ci-box/install.sh

@@ -77,7 +77,12 @@ fetch_and_verify_sha256() {
   printf 'checksum verified (%s)\n' "$got"
 }
 
-BIN=/usr/local/bin/forgejo-runner
+# CIBOX_BIN is a TEST-ONLY override, in the same spirit as bootstrap-undo.sh's
+# RIG_FORGEJO_RUNNER_DIR: the production default is the only path the mechanism
+# ever uses, but test/cli.sh must be able to drive this script on a box that
+# already has a real runner installed. Without it the early-exit below fires
+# against the host and the checksum checks silently test nothing (#136).
+BIN="${CIBOX_BIN:-/usr/local/bin/forgejo-runner}"
 
 if [ -x "$BIN" ]; then
   exit 0

test/cli.sh

@@ -156,8 +156,9 @@ UNDO_FIX="$(mktemp -d)"
 UNDO_BIN="$UNDO_FIX/bin"
 UNDO_MARKER="$UNDO_FIX/role"
 UNDO_RUNNER="$UNDO_FIX/runner"
+UNDO_FJRUNNER="$UNDO_FIX/fjrunner"
 UNDO_CALLS="$UNDO_FIX/tailscale.calls"
-mkdir -p "$UNDO_BIN" "$UNDO_RUNNER"
+mkdir -p "$UNDO_BIN" "$UNDO_RUNNER" "$UNDO_FJRUNNER"
 cat > "$UNDO_BIN/tailscale" <<'SH'
 #!/usr/bin/env bash
 printf '%s\n' "$*" >> "$UNDO_CALLS"
@@ -169,8 +170,13 @@ if [ "${1:-}" = -u ]; then printf '0\n'; else exec /usr/bin/id "$@"; fi
 SH
 chmod +x "$UNDO_BIN/tailscale" "$UNDO_BIN/id"
 undo() {
+  # RIG_FORGEJO_RUNNER_DIR is as load-bearing as RIG_RUNNER_DIR: without it
+  # bootstrap-undo.sh scans /home/*/forgejo-runner/.runner and the systemd unit
+  # on the REAL box, so these checks fail on any machine that has actually been
+  # drilled or used as a ci-box — which is the machine that matters (#136).
   env PATH="$UNDO_BIN:$PATH" UNDO_CALLS="$UNDO_CALLS" \
     RIG_ROLE_MARKER="$UNDO_MARKER" RIG_RUNNER_DIR="$UNDO_RUNNER" \
+    RIG_FORGEJO_RUNNER_DIR="$UNDO_FJRUNNER" \
     "$ROOT/bin/rig" bootstrap --undo
 }
 undo_untouched() {
@@ -196,7 +202,8 @@ rm -f "$UNDO_RUNNER/.runner"
 check "bootstrap --undo: failed logout is loud" \
   1 "role marker kept" env TAILSCALE_LOGOUT_FAIL=1 PATH="$UNDO_BIN:$PATH" \
     UNDO_CALLS="$UNDO_CALLS" RIG_ROLE_MARKER="$UNDO_MARKER" \
-    RIG_RUNNER_DIR="$UNDO_RUNNER" "$ROOT/bin/rig" bootstrap --undo
+    RIG_RUNNER_DIR="$UNDO_RUNNER" RIG_FORGEJO_RUNNER_DIR="$UNDO_FJRUNNER" \
+    "$ROOT/bin/rig" bootstrap --undo
 check "bootstrap --undo: failed logout preserves the marker" 0 "" test -e "$UNDO_MARKER"
 : > "$UNDO_CALLS"
 check "bootstrap --undo: proven rig join succeeds" 0 "tailnet join removed" undo
@@ -3276,10 +3283,45 @@ cibox_src_matches_install() {
   # shellcheck source=/dev/null
   . "$ROOT/commands/lib/templates.sh"
   template_parse_env "$dir/template.env" >/dev/null || return 2
-  grep -qF "BIN=$TPL_CLI_SRC" "$dir/install.sh"
+  # BIN carries a test-only override (#136), so the agreement this asserts is
+  # with the DEFAULT — the only path the mechanism itself ever uses.
+  grep -qF "CIBOX_BIN:-$TPL_CLI_SRC" "$dir/install.sh"
 }
 check "ci-box: CLI_SRC is the path its install.sh installs" 0 "" cibox_src_matches_install
 
+# codex/kimi on !137: the two wiring lines this change exists to add could be
+# deleted tomorrow and the suite stayed 786/786 on any host without a real
+# Forgejo runner — hermetic today, unpinned. #136's task list names the guard
+# verbatim: "a check that fails if either group can see host state".
+#
+# These assert on the SUITE's own helpers, not the production knobs — the knobs
+# are already covered above. What must go red is a deletion on the test side,
+# because that is the regression that silently reintroduces host dependence.
+undo_is_sealed() {
+  sed -n '/^undo() {/,/^}/p' "$0" | grep -q 'RIG_FORGEJO_RUNNER_DIR='
+}
+cibox_run_is_sealed() {
+  sed -n '/^cibox_run() {/,/^}/p' "$0" | grep -q 'CIBOX_BIN='
+}
+check "hermetic: undo() seals the Forgejo-runner host scan" 0 "" undo_is_sealed
+check "hermetic: cibox_run() seals the real /usr/local/bin lookup" 0 "" cibox_run_is_sealed
+# The failed-logout check builds its own env rather than calling undo(), so it
+# needs the same seal — and it is the one that was missed first time round.
+inline_undo_is_sealed() {
+  # Locate the REAL check by line number and read only its own block. Anchoring
+  # on a string and grepping the whole file cannot work here: any pattern this
+  # function searches for necessarily appears inside this function, so the
+  # search matches itself and can never fail. kimi caught the first version of
+  # that on !137; the anchored second version had the identical flaw for the
+  # identical reason. head -1 takes the real check (~:202), never this body.
+  local start end
+  start="$(grep -n 'failed logout is loud' "$0" | head -1 | cut -d: -f1)"
+  [ -n "$start" ] || return 1
+  end=$((start + 5))
+  sed -n "${start},${end}p" "$0" | grep -q RIG_FORGEJO_RUNNER_DIR
+}
+check "hermetic: the hand-rolled undo invocation is sealed too" 0 "" inline_undo_is_sealed
+
 # Registration holds a credential, so it must NOT be in the definition: a
 # tenant install is creds-free by contract — box auto-runs it at mint, holding
 # nothing. Registration is the operator's separate, out-loud act.
@@ -3522,7 +3564,7 @@ chmod +x "$CBSTUB/install"
 
 cibox_run() { # cibox_run [VAR=val ...] — the REAL template install.sh, stubbed
   rm -f "$CBW/installed"
-  env PATH="$CBSTUB:$PATH" \
+  env PATH="$CBSTUB:$PATH" CIBOX_BIN="$CBW/bin-under-test" \
     CB_REDIRECT=https://code.forgejo.org/forgejo/runner/releases/tag/v9.9.9 \
     CB_PAYLOAD="$CBW/payload" "$@" bash "$CIBOX"
 }