Merge pull request 'fix(forgejo-runner): the cache server can start' (#138) from build/135-runner-cache-dir into main

Reviewed-on: #138
Reviewed-by: kimi-reviewer-andresmgsl <andres+4@heavyduty.builders>
Reviewed-by: grok-reviewer-andresmgsl <andres+3@heavyduty.builders>
Reviewed-by: codex-reviewer-andresmgsl <andres+2@heavyduty.builders>

changelog.d/135.md

@@ -0,0 +1,3 @@
+### Fixed
+
+- Forgejo runners installed by rig can start their cache server — `$HOME/.cache` is created and punched through `ProtectHome` (#135)

commands/forgejo-runner-install.sh

@@ -397,6 +397,14 @@ fi
 # holds the UUID. assert_runner_instance's contract survives either way — it
 # asks about the instance, which both spellings record.
 install -d -m 0755 -o "$RUNNER_USER" -g "$RUNNER_GROUP" "$RUNNER_DIR"
+# forgejo-runner's cache server writes to $HOME/.cache, which ProtectHome makes
+# read-only below. Create it HERE, before the unit can reference it: a
+# ReadWritePaths entry naming a path that does not exist makes systemd refuse
+# to start the unit at all ("Failed to set up mount namespacing"), which is
+# worse than the disabled cache it was meant to fix. Measured on a live runner,
+# 2026-07-31 (#135). Root-owned would fail the same way under User=, so it
+# carries the runner's own ownership like RUNNER_DIR above.
+install -d -m 0755 -o "$RUNNER_USER" -g "$RUNNER_GROUP" "$USER_HOME/.cache"
 if [ -e "$RUNNER_DIR/.runner" ]; then
   log "already registered; skipping registration"
   # Registration was skipped, so the labels on the instance are the ones it was
@@ -461,7 +469,7 @@ NoNewPrivileges=true
 PrivateTmp=true
 ProtectSystem=full
 ProtectHome=read-only
-ReadWritePaths=${RUNNER_DIR}
+ReadWritePaths=${RUNNER_DIR} ${USER_HOME}/.cache
 
 [Install]
 WantedBy=multi-user.target

test/cli.sh

@@ -3350,6 +3350,27 @@ check "forgejo-runner: remove warns about an orphaned unit" 0 "orphaned unit" \
 check "forgejo-runner: remove never rm's an unguarded \$RUNNER_DIR path" 1 "" \
   grep -qE '^rm -f "\$RUNNER_DIR' "$ROOT/commands/forgejo-runner-remove.sh"
 
+# #135: ProtectHome=read-only made the whole home read-only and only RUNNER_DIR
+# was punched back through, so forgejo-runner could not create $HOME/.cache and
+# disabled its cache server on every install — actions/cache silently off, one
+# error line in the journal, and `status` reporting a healthy runner.
+#
+# BOTH halves are asserted because the obvious one-line version is WORSE than
+# the bug: listing the path in ReadWritePaths without creating it makes systemd
+# refuse to start the unit at all ("Failed to set up mount namespacing"),
+# measured on a live box. The directory must exist first.
+FRI="$ROOT/commands/forgejo-runner-install.sh"
+grep_cache_install() {
+  # shellcheck disable=SC2016 # $RUNNER_USER is literal text in the shipped file
+  grep -qE 'install -d .*-o "\$RUNNER_USER".*\.cache' "$FRI"
+}
+check "forgejo-runner: the cache dir is punched through ProtectHome" 0 "" \
+  grep -qE 'ReadWritePaths=.*\.cache' "$FRI"
+check "forgejo-runner: …and the install creates it, owned by the runner user" 0 "" \
+  grep_cache_install
+check "forgejo-runner: ProtectHome stays read-only (the cache is not an excuse to widen it)" 0 "" \
+  grep -qF 'ProtectHome=read-only' "$FRI"
+
 check "forgejo-runner: status --help exits 0" 0 "usage:" "$ROOT/commands/forgejo-runner-status.sh" --help
 check "forgejo-runner: remove --help exits 0" 0 "usage:" "$ROOT/commands/forgejo-runner-remove.sh" --help