Merge pull request 'fix: slim ubuntu-latest default; install shellcheck in ci.yml (#144)' (#146) from build/144-default-labels-option-b into main

Reviewed-on: heavy-duty/rig#146
Reviewed-by: codex-reviewer-andresmgsl <andres+2@heavyduty.builders>
Reviewed-by: cluade-reviewer-andresmgsl <andres+1@heavyduty.builders>
Reviewed-by: kimi-reviewer-andresmgsl <andres+4@heavyduty.builders>

.github/workflows/ci.yml

@@ -26,7 +26,21 @@ jobs:
         # The file list is printed so under-coverage shows up in the log, and
         # the comm below turns under-coverage into a failure rather than a
         # thing someone has to notice: every tracked `.sh` must be in the set.
+        #
+        # Install shellcheck when missing (#144). rig's default Forgejo label
+        # maps ubuntu-latest to catthehacker's act-22.04 (slim), which does not
+        # ship shellcheck; GitHub-hosted ubuntu-latest does. The conditional
+        # keeps each forge from paying for the other.
+        #
+        # sudo: load-bearing on GitHub (job runs as `runner` with passwordless
+        # sudo) and a no-op on act-22.04 (jobs run as uid 0; the image has no
+        # `runner` account). Do not delete it as "dead weight" — that breaks
+        # the GitHub half the day that image stops preinstalling shellcheck.
         run: |
+          if ! command -v shellcheck >/dev/null 2>&1; then
+            sudo apt-get update
+            sudo apt-get install -y shellcheck
+          fi
           shopt -s globstar dotglob
           files=(bin/* **/*.sh)
           printf 'shellcheck: %s\n' "${files[@]}"

changelog.d/144.md

@@ -0,0 +1,8 @@
+### Added
+
+- Default Forgejo runner labels include opt-in `ubuntu-latest-full` for the GitHub-parity image (#144)
+
+### Fixed
+
+- `ci.yml` installs `shellcheck` when the runner image lacks it, so Forgejo's slim `ubuntu-latest` can run `check` (#144)
+- Plain `rig forgejo-runner install` warns when recorded labels are a retired rig default, without nagging custom `--labels` (#144)

commands/forgejo-runner-install.sh

@@ -31,7 +31,32 @@ die()  { printf 'rig-forgejo-runner: ERROR: %s\n' "$1" >&2; exit "${2:-1}"; }
 # on the box itself. No docker-in-docker: the guide this came from stacks a
 # privileged dind sidecar with a plaintext tcp://…:2375 daemon to isolate jobs
 # from a shared CI server, and inside a box that boundary is already paid for.
-DEFAULT_LABELS='ubuntu-latest:docker://ghcr.io/catthehacker/ubuntu:act-22.04,docker:docker://node:22-bookworm'
+#
+# WHY act-22.04 (slim) for ubuntu-latest, not full-22.04 — measured 2026-08-01
+# against ghcr manifests (#144):
+#   act-22.04:  ~0.55 GB compressed / ~2.2 GB on disk — no shellcheck
+#   full-22.04: ~18.67 GB compressed / ~54.5 GB on disk — has shellcheck 0.8.0
+# A normal box-class ci tenant cannot hold 54.5 GB (typical free space ~34 GB).
+# So ubuntu-latest stays slim, and workflows must not assume GitHub-image tools
+# (rig's own ci.yml installs shellcheck when missing). Operators who need the
+# full tool surface opt in with runs-on: ubuntu-latest-full — that label is
+# inert until matched, so boxes that never ask pay nothing.
+DEFAULT_LABELS='ubuntu-latest:docker://ghcr.io/catthehacker/ubuntu:act-22.04,ubuntu-latest-full:docker://ghcr.io/catthehacker/ubuntu:full-22.04,docker:docker://node:22-bookworm'
+
+# labels_are_a_retired_default <recorded>
+#
+# True when <recorded> is a past DEFAULT_LABELS value rig has shipped — the
+# only plain-converge case that should warn about re-registration (#144).
+# Custom operator maps (drill's Leg 3, any --labels) must return false so a
+# bare re-run stays quiet. One pattern per past default; add when the string
+# changes. Extracted and driven by test/cli.sh — a grep pin alone cannot prove
+# the match is exact.
+labels_are_a_retired_default() {
+  case "${1:-}" in
+    'ubuntu-latest:docker://ghcr.io/catthehacker/ubuntu:act-22.04,docker:docker://node:22-bookworm') return 0 ;;
+    *) return 1 ;;
+  esac
+}
 
 # fetch_and_verify_sha256 <asset-url> <file> <sumfile> <label>
 #
@@ -93,8 +118,10 @@ usage: rig forgejo-runner install --instance <url> [options]
                         time). Pin it for a deterministic, auditable install.
   --name <name>         runner name (default: this host's hostname)
   --labels <csv>        runner labels; replaces the default. The default maps
-                        ubuntu-latest and docker onto container images, so a
-                        workflow written for GitHub runs unchanged.
+                        ubuntu-latest (slim act image), ubuntu-latest-full
+                        (opt-in parity image), and docker onto containers so
+                        a workflow written for GitHub runs; full tools need
+                        runs-on: ubuntu-latest-full or an install step.
   --user <name>         unprivileged service user (default: the tenant user
                         `ci` when it exists, else forgejo-runner; created if
                         absent; never root)
@@ -408,14 +435,29 @@ install -d -m 0755 -o "$RUNNER_USER" -g "$RUNNER_GROUP" "$USER_HOME/.cache"
 if [ -e "$RUNNER_DIR/.runner" ]; then
   log "already registered; skipping registration"
   # Registration was skipped, so the labels on the instance are the ones it was
-  # registered with — NOT whatever this invocation was passed. Say so when the
-  # operator explicitly asked for different ones, rather than letting the
-  # request evaporate. Only when EXPLICIT: comparing the default against a
-  # runner registered with custom labels would warn on every plain converge.
-  if [ "$LABELS_EXPLICIT" -eq 1 ] && [ -r "$RUNNER_DIR/.rig-labels" ]; then
+  # registered with — NOT whatever this invocation was passed. Forgejo owns
+  # labels from registration time; a re-run never rewrites them.
+  #
+  # Two warn paths (#144):
+  #   EXPLICIT --labels that differs → operator asked and it was not applied.
+  #   Plain converge whose recorded labels match a known *retired* default →
+  #   rig's default map moved (e.g. added ubuntu-latest-full). Without this
+  #   the operator re-runs install, sees "already registered", and believes
+  #   they have the new default while Forgejo still holds the old set.
+  #
+  # Do NOT warn on every RECORDED != current default: that fires forever for
+  # any runner the operator deliberately gave custom --labels (drill's Leg 3
+  # registers drill:docker://node:22-bookworm). The old LABELS_EXPLICIT-only
+  # gate existed to avoid that noise; retired-default matching keeps the
+  # silence for intentional maps and still catches silent drift off a past
+  # rig default. Re-register only to pick up labels the old set never had —
+  # nothing matching the recorded set is broken by the map change alone.
+  if [ -r "$RUNNER_DIR/.rig-labels" ]; then
     RECORDED="$(cat "$RUNNER_DIR/.rig-labels")"
-    if [ "$RECORDED" != "$LABELS" ]; then
+    if [ "$LABELS_EXPLICIT" -eq 1 ] && [ "$RECORDED" != "$LABELS" ]; then
       warn "--labels was not applied: this runner is already registered, and Forgejo owns its labels from registration time. It still has: ${RECORDED}. Labels are what 'runs-on' matches, so changing them means re-registering: 'rig forgejo-runner remove' then install again with the labels you want."
+    elif [ "$LABELS_EXPLICIT" -eq 0 ] && labels_are_a_retired_default "$RECORDED"; then
+      warn "this runner was registered with an older rig default label set. The current default adds ubuntu-latest-full (the GitHub-parity image). Labels are fixed at registration, so picking it up means re-registering: 'rig forgejo-runner remove' then install again. Nothing you run today is affected — re-register only if you want the new label."
     fi
   fi
 else

test/cli.sh

@@ -3349,12 +3349,22 @@ check "forgejo-runner: --version refuses a path, not a release number" 2 "releas
   "$FR" --instance https://f.example.com --version ../../etc/passwd
 check "forgejo-runner: --version refuses a non-numeric pin" 2 "release number like" \
   "$FR" --instance https://f.example.com --version latest
-# Reaching the root check is the proof a good pin got THROUGH validation: this
-# runs as a normal user in CI, so "must run as root" is the next gate down.
-check "forgejo-runner: a plain release number passes validation" 1 "must run as root" \
-  "$FR" --instance https://f.example.com --version 12.13.2
-check "forgejo-runner: a leading v is stripped before that check" 1 "must run as root" \
-  "$FR" --instance https://f.example.com --version v12.13.2
+# Reaching a gate AFTER --version parsing is the proof a good pin got THROUGH
+# validation. Which gate depends on the uid: non-root hits "must run as root";
+# act/Forgejo jobs run as uid 0 (no `runner` account — #144), so they sail past
+# the root check and hit the unattended-token refuse instead. Both prove the
+# same thing. GitHub-hosted ubuntu-latest is non-root and takes the first arm.
+if [ "$(id -u)" -ne 0 ]; then
+  check "forgejo-runner: a plain release number passes validation" 1 "must run as root" \
+    "$FR" --instance https://f.example.com --version 12.13.2
+  check "forgejo-runner: a leading v is stripped before that check" 1 "must run as root" \
+    "$FR" --instance https://f.example.com --version v12.13.2
+else
+  check "forgejo-runner: a plain release number passes validation" 1 "FORGEJO_RUNNER_TOKEN is unset" \
+    env -u FORGEJO_RUNNER_TOKEN "$FR" --instance https://f.example.com --version 12.13.2
+  check "forgejo-runner: a leading v is stripped before that check" 1 "FORGEJO_RUNNER_TOKEN is unset" \
+    env -u FORGEJO_RUNNER_TOKEN "$FR" --instance https://f.example.com --version v12.13.2
+fi
 # A schemeless host and a repo URL are the two ways an operator mis-states the
 # instance, and only one of them would fail loudly on its own — a repo URL
 # registers somewhere subtly wrong instead. Both refuse by name.
@@ -3704,6 +3714,44 @@ check "forgejo-runner: an explicit --labels on a rerun warns it was not applied"
   grep -o -- "--labels was not applied" "$FR"
 check "forgejo-runner: that warning is gated on --labels being EXPLICIT" 0 "LABELS_EXPLICIT" \
   grep -o "LABELS_EXPLICIT" "$FR"
+# #144 option B: plain converge warns only for known *retired* defaults — not
+# for every RECORDED != current default (that would noise custom --labels
+# forever, including drill's Leg 3). Drive the recogniser against fixtures
+# (test/drill.sh extraction pattern) so a dead matcher cannot greppen green.
+check "forgejo-runner: plain converge warns on a known retired default label set" 0 "registered with an older rig default label set" \
+  grep -o "registered with an older rig default label set" "$FR"
+check "forgejo-runner: that warn says re-register only if you want the new label" 0 "re-register only if you want the new label" \
+  grep -o "re-register only if you want the new label" "$FR"
+PRE_144_LABELS='ubuntu-latest:docker://ghcr.io/catthehacker/ubuntu:act-22.04,docker:docker://node:22-bookworm'
+CURRENT_LABELS="$(sed -n "s/^DEFAULT_LABELS='\\(.*\\)'$/\\1/p" "$FR")"
+RETIRED_FNS="$(mktemp)"
+awk '/^labels_are_a_retired_default\(\) \{/,/^\}/' "$FR" > "$RETIRED_FNS"
+check "extraction guards the awk: labels_are_a_retired_default() landed" 0 "labels_are_a_retired_default() {" \
+  grep -F 'labels_are_a_retired_default() {' "$RETIRED_FNS"
+# shellcheck source=/dev/null
+. "$RETIRED_FNS"
+check "retired-default: the pre-#144 default is recognised" 0 "" \
+  labels_are_a_retired_default "$PRE_144_LABELS"
+check "retired-default: the CURRENT default is not drift" 1 "" \
+  labels_are_a_retired_default "$CURRENT_LABELS"
+check "retired-default: an operator's own --labels map is never drift" 1 "" \
+  labels_are_a_retired_default 'drill:docker://node:22-bookworm'
+check "retired-default: a near-miss of a past default is not a match" 1 "" \
+  labels_are_a_retired_default "${PRE_144_LABELS} "
+rm -f "$RETIRED_FNS"
+# Default map: slim ubuntu-latest (act), opt-in full, docker — pin the three
+# so a silent drop of the full rider or a flip back to full-as-default fails.
+check "forgejo-runner: DEFAULT_LABELS maps ubuntu-latest to act-22.04 (slim)" 0 "ubuntu-latest:docker://ghcr.io/catthehacker/ubuntu:act-22.04" \
+  grep -o "ubuntu-latest:docker://ghcr.io/catthehacker/ubuntu:act-22.04" "$FR"
+check "forgejo-runner: DEFAULT_LABELS offers ubuntu-latest-full as opt-in" 0 "ubuntu-latest-full:docker://ghcr.io/catthehacker/ubuntu:full-22.04" \
+  grep -o "ubuntu-latest-full:docker://ghcr.io/catthehacker/ubuntu:full-22.04" "$FR"
+check "forgejo-runner: DEFAULT_LABELS comment records the slim/full size measurement" 0 "54.5 GB" \
+  grep -o "54.5 GB" "$FR"
+# ci.yml must install shellcheck when the image lacks it (#144 option B).
+check "ci.yml: shellcheck step installs the tool when missing" 0 "command -v shellcheck" \
+  grep -o "command -v shellcheck" "$ROOT/.github/workflows/ci.yml"
+check "ci.yml: shellcheck install uses sudo (GitHub path; no-op on act as root)" 0 "sudo apt-get install -y shellcheck" \
+  grep -o "sudo apt-get install -y shellcheck" "$ROOT/.github/workflows/ci.yml"
 # The GitHub sibling is the precedent this restores — pin that it still scopes
 # its own write, so the two cannot drift apart again.
 gh_labels_write_is_scoped() {