Show what a run is doing, and record when one is cut short

A run that held back a blocker then upgraded 214 packages printed one line and
then nothing for nearly five minutes while pacman downloaded and installed. It
looked hung, so it got killed - during pacman's uninterruptible commit phase,
which meant the packages landed but our bookkeeping never did. The menu then
kept showing a failure from a previous run on a fully up-to-date machine.

pacman, the AUR helper and flatpak now stream their output when a person is
watching, and the progress bar is left enabled for that case. Timer runs are
unchanged: quiet, --noprogressbar, everything captured in the log.

Interactivity is decided once at startup rather than tested at the point of
use. cau_pacman_flags runs inside a process substitution, so its stdout is
always a pipe and a -t 1 check there would have silently always been false.

INT/TERM/HUP now record last_result=interrupted, so a run that is stopped says
so instead of leaving the previous verdict standing.

Makefile

@@ -8,7 +8,7 @@
 # Overridable so a packager can pass the version it is actually building
 # (`make VERSION=$pkgver`). The literal below is the fallback for builds
 # straight from a checkout, and is what a release tag has to carry.
-VERSION      ?= 1.0.3
+VERSION      ?= 1.0.6
 
 PREFIX       ?= /usr
 DESTDIR      ?=

po/cachy-auto-update.pot

@@ -243,3 +243,17 @@ msgstr ""
 
 msgid "pacman's lock file looks left over from an interrupted update. Updates are paused until it is cleared."
 msgstr ""
+
+msgid "Some packages were held back"
+msgstr ""
+
+#, c-format
+msgid "%s could not be updated and was skipped. Everything else is up to date."
+msgstr ""
+
+#, c-format
+msgid "Held back: %s"
+msgstr ""
+
+msgid "The last run was stopped before it finished."
+msgstr ""

po/de.po

@@ -244,3 +244,17 @@ msgstr "Paketdatenbank gesperrt"
 
 msgid "pacman's lock file looks left over from an interrupted update. Updates are paused until it is cleared."
 msgstr "Die Sperrdatei von pacman scheint von einem abgebrochenen Update übrig zu sein. Bis sie entfernt ist, pausieren die Updates."
+
+msgid "Some packages were held back"
+msgstr "Einige Pakete wurden zurückgehalten"
+
+#, c-format
+msgid "%s could not be updated and was skipped. Everything else is up to date."
+msgstr "%s konnte nicht aktualisiert werden und wurde übersprungen. Alles andere ist aktuell."
+
+#, c-format
+msgid "Held back: %s"
+msgstr "Zurückgehalten: %s"
+
+msgid "The last run was stopped before it finished."
+msgstr "Der letzte Lauf wurde abgebrochen, bevor er fertig war."

src/cachy-auto-update-run

@@ -63,6 +63,21 @@ fi
 cau_config_load
 cau_log_open
 
+# Record an interruption rather than leaving the previous run's verdict behind.
+# Without this, killing an interactive run leaves last_result at whatever it was
+# before - so the menu can keep reporting a problem from hours ago while the
+# machine is in fact fully up to date, which is worse than saying nothing.
+# pacman makes the commit phase itself uninterruptible, so the packages either
+# all landed or none did; only our own bookkeeping is at risk here.
+_cau_interrupted() {
+	cau_error "Update run interrupted ($1)"
+	cau_state_write last_result interrupted
+	exit 130
+}
+trap '_cau_interrupted SIGINT'  INT
+trap '_cau_interrupted SIGTERM' TERM
+trap '_cau_interrupted SIGHUP'  HUP
+
 # ---------------------------------------------------------------------------
 # Should this run happen at all?
 # ---------------------------------------------------------------------------
@@ -202,6 +217,22 @@ else
 	fi
 fi
 
+# Packages skipped so the rest of the upgrade could proceed. The notification
+# only fires when the set changes: a blocker waiting on an upstream fix would
+# otherwise produce the same message every single day.
+prev_held="$(cau_state_read held_back '')"
+if [[ -n $CAU_PACMAN_HELD ]]; then
+	cau_state_write held_back "$CAU_PACMAN_HELD"
+	cau_warn "Held back: $CAU_PACMAN_HELD"
+	if [[ $CAU_PACMAN_HELD != "$prev_held" && $CFG_NOTIFY_ERROR == yes ]]; then
+		cau_notify normal "Some packages were held back" \
+			"%s could not be updated and was skipped. Everything else is up to date." \
+			"$CAU_PACMAN_HELD"
+	fi
+else
+	cau_state_clear held_back
+fi
+
 if cau_pacman_reboot_needed; then
 	cau_state_write reboot_needed 1
 	cau_info "A kernel update needs a restart"

src/lib/common.sh

@@ -91,7 +91,14 @@ cau_msg_in() {
 # Output and logging
 # ---------------------------------------------------------------------------
 
-if [[ -t 1 && -z ${NO_COLOR:-} ]]; then
+# Is a person watching? Decided once, here, while stdout is still whatever the
+# process was started with. Testing `-t 1` at the point of use is unreliable:
+# any function called through $(...) or <(...) sees a pipe on stdout and would
+# conclude nobody is there.
+CAU_INTERACTIVE=''
+[[ -t 1 ]] && CAU_INTERACTIVE=1
+
+if [[ -n $CAU_INTERACTIVE && -z ${NO_COLOR:-} ]]; then
 	CAU_C_RESET=$'\033[0m'
 	CAU_C_BOLD=$'\033[1m'
 	CAU_C_DIM=$'\033[2m'
@@ -132,10 +139,19 @@ cau_log_open() {
 	CAU_LOG_OPEN=1
 }
 
-# Runs a command, streaming its combined output into the run log. Returns the
+# Runs a command, capturing its combined output in the run log. Returns the
 # command's exit status.
+#
+# When a person is watching - `cachy-auto-update run` from a terminal - the
+# output is shown as well. Building an AUR package or pulling a few hundred
+# megabytes of Flatpak can take minutes, and silence for that long is
+# indistinguishable from a hang.
 cau_run_logged() {
 	if [[ -n ${CAU_LOG_OPEN:-} ]]; then
+		if [[ -n $CAU_INTERACTIVE ]]; then
+			"$@" 2>&1 | tee -a "$CAU_RUNLOG"
+			return "${PIPESTATUS[0]}"
+		fi
 		"$@" >> "$CAU_RUNLOG" 2>&1
 	else
 		"$@" >&2
@@ -146,11 +162,18 @@ cau_run_logged() {
 # Terminal helpers for the CLI
 # ---------------------------------------------------------------------------
 
+# Set by cau_bad and cau_note. The menu redraws immediately after an action,
+# which would wipe the screen; this marks that something was printed that the
+# user still has to read, so only those cases wait for a keypress. A plain
+# success needs no acknowledgement - the status block at the top of the menu
+# already shows the new state.
+CAU_UI_NEEDS_ACK=''
+
 cau_say()  { printf '%s\n' "$*"; }
 cau_head() { printf '\n%s%s%s\n\n' "$CAU_C_BOLD$CAU_C_BLUE" "$*" "$CAU_C_RESET"; }
 cau_ok()   { printf '%s✔%s %s\n' "$CAU_C_GREEN" "$CAU_C_RESET" "$*"; }
-cau_bad()  { printf '%s✘%s %s\n' "$CAU_C_RED" "$CAU_C_RESET" "$*" >&2; }
+cau_bad()  { CAU_UI_NEEDS_ACK=1; printf '%s✘%s %s\n' "$CAU_C_RED" "$CAU_C_RESET" "$*" >&2; }
-cau_note() { printf '%s•%s %s\n' "$CAU_C_DIM" "$CAU_C_RESET" "$*"; }
+cau_note() { CAU_UI_NEEDS_ACK=1; printf '%s•%s %s\n' "$CAU_C_DIM" "$CAU_C_RESET" "$*"; }
 
 # ---------------------------------------------------------------------------
 # State files

src/lib/menu.sh

@@ -81,12 +81,23 @@ cau_ui_status() {
 		printf '\n  %s%s%s\n' "$CAU_C_YELLOW" \
 			"$(cau_msg "The last run reported a problem - see 'cachy-auto-update log'.")" \
 			"$CAU_C_RESET"
+	elif [[ $result == interrupted ]]; then
+		printf '\n  %s%s%s\n' "$CAU_C_YELLOW" \
+			"$(cau_msg "The last run was stopped before it finished.")" \
+			"$CAU_C_RESET"
 	fi
 	if [[ $reboot == 1 ]]; then
 		printf '\n  %s%s%s\n' "$CAU_C_YELLOW" \
 			"$(cau_msg "A restart is recommended to finish a kernel update.")" \
 			"$CAU_C_RESET"
 	fi
+
+	local held
+	held="$(cau_state_read held_back '')"
+	if [[ -n $held ]]; then
+		printf '\n  %s%s%s\n' "$CAU_C_YELLOW" \
+			"$(cau_msg "Held back: %s" "$held")" "$CAU_C_RESET"
+	fi
 }
 
 # cau_ui_status_conditions
@@ -152,17 +163,22 @@ cau_ui_menu() {
 		printf '%s\n' "$choice"
 
 		case "$choice" in
+			# The two switches flip and return straight to the menu, where the
+			# status block shows the result. Only a warning or an error holds
+			# the screen (see CAU_UI_NEEDS_ACK).
 			1)
+				CAU_UI_NEEDS_ACK=''
 				if [[ $CFG_ENABLED == yes ]]; then cau_do_disable; else cau_do_enable; fi
-				cau_pause
+				if [[ -n $CAU_UI_NEEDS_ACK ]]; then cau_pause; fi
 				;;
 			2)
+				CAU_UI_NEEDS_ACK=''
 				if [[ $CFG_NOTIFICATIONS == yes ]]; then
 					cau_do_notifications off
 				else
 					cau_do_notifications on
 				fi
-				cau_pause
+				if [[ -n $CAU_UI_NEEDS_ACK ]]; then cau_pause; fi
 				;;
 			3) cau_do_run --force; cau_pause ;;
 			4) cau_do_log; cau_pause ;;

src/lib/pkg_pacman.sh

@@ -10,15 +10,40 @@
 CAU_PACMAN_COUNT=0
 CAU_PACMAN_PENDING=''
 
+# Packages that had to be skipped so the rest of the upgrade could go through.
+CAU_PACMAN_HELD=''
+
 # Base flags for every unattended pacman invocation.
 cau_pacman_flags() {
-	printf '%s\n' --noconfirm --color never --noprogressbar --disable-download-timeout
+	printf '%s\n' --noconfirm --color never --disable-download-timeout
+
+	# A progress bar is worth having when somebody is watching a `run` from a
+	# terminal; in the timer's log it is only carriage-return noise.
+	[[ -n $CAU_INTERACTIVE ]] || printf '%s\n' --noprogressbar
+
 	local pkg
 	for pkg in $CFG_IGNORE_PKG; do
 		printf '%s\n' --ignore "$pkg"
 	done
 }
 
+# _cau_pacman_exec <logfile> <pacman args...>
+# Captures pacman's output for classification, and streams it as well when a
+# person is watching. Upgrading a few hundred packages takes minutes; without
+# this an interactive run shows one line and then nothing at all, which is
+# indistinguishable from a hang and invites someone to kill it mid-transaction.
+_cau_pacman_exec() {
+	local log="$1"
+	shift
+
+	if [[ -n $CAU_INTERACTIVE ]]; then
+		pacman "$@" 2>&1 | tee "$log"
+		return "${PIPESTATUS[0]}"
+	fi
+
+	pacman "$@" > "$log" 2>&1
+}
+
 # cau_pacman_pending
 # Fills CAU_PACMAN_PENDING and returns 1 when there is nothing to do.
 cau_pacman_pending() {
@@ -55,6 +80,8 @@ _cau_pacman_classify() {
 
 	if grep -qiE 'are in conflict|unresolvable package conflicts' "$log"; then
 		printf 'conflict\n'
+	elif grep -qiE 'could not satisfy dependencies|breaks dependency|unable to satisfy dependency' "$log"; then
+		printf 'dependency\n'
 	elif grep -qiE 'signature from .* is (unknown trust|marginal trust|invalid)|invalid or corrupted package \(PGP signature\)|key ".*" is unknown|keyring is not writable' "$log"; then
 		printf 'keyring\n'
 	elif grep -qiE 'exists in filesystem' "$log"; then
@@ -64,6 +91,25 @@ _cau_pacman_classify() {
 	fi
 }
 
+# _cau_pacman_blockers <logfile>
+# The packages standing in the way of an otherwise fine upgrade. pacman names
+# them in its dependency errors:
+#
+#   :: removing libperconaserverclient breaks dependency 'libperconaserverclient'
+#      required by heidisql-qt6-bin
+#   :: unable to satisfy dependency 'foo' required by bar
+#
+# In the first form the package being removed is the one to keep; in the second
+# it is the package that cannot be installed.
+_cau_pacman_blockers() {
+	local log="$1"
+
+	{
+		sed -nE "s/.*removing ([^ ]+) breaks dependency.*/\\1/p" "$log"
+		sed -nE "s/.*unable to satisfy dependency '[^']*' required by ([^ ]+).*/\\1/p" "$log"
+	} | grep -E '^[A-Za-z0-9@._+-]+$' | sort -u
+}
+
 # cau_pacman_update
 # Returns 0 on success (including "nothing to do"), 1 on a failure the user
 # needs to hear about. CAU_PACMAN_COUNT holds how many packages moved.
@@ -90,8 +136,17 @@ cau_pacman_update() {
 	mapfile -t flags < <(cau_pacman_flags)
 	log="$(mktemp)" || return 1
 
-	if pacman -Syu "${flags[@]}" > "$log" 2>&1; then
+	# Recovery loop rather than a single retry: fixing one problem regularly
+	# uncovers the next (a conflict resolved into a dependency error, say).
+	# Each remedy is applied at most once, so this always terminates.
+	local -a extra=() blockers=() tried=()
+	local attempt=0 b
+
+	while true; do
+		if _cau_pacman_exec "$log" -Syu "${flags[@]}" "${extra[@]}"; then
 			cat "$log" >> "$CAU_RUNLOG" 2>/dev/null
+			grep -E '^(removing|replacing) ' "$log" 2>/dev/null \
+				| while read -r line; do cau_info "  $line"; done
 			rm -f "$log"
 			return 0
 		fi
@@ -100,6 +155,11 @@ cau_pacman_update() {
 		kind="$(_cau_pacman_classify "$log")"
 		cau_warn "pacman -Syu failed ($kind)"
 
+		if (( ++attempt > 3 )) || [[ " ${tried[*]} " == *" $kind "* ]]; then
+			break
+		fi
+		tried+=("$kind")
+
 		case "$kind" in
 			keyring)
 				# A stale keyring is the one failure that is always safe to fix
@@ -111,12 +171,6 @@ cau_pacman_update() {
 				if (( ${#keyrings[@]} )); then
 					cau_run_logged pacman -Sy --noconfirm --color never "${keyrings[@]}" || true
 				fi
-			if pacman -Syu "${flags[@]}" > "$log" 2>&1; then
-				cat "$log" >> "$CAU_RUNLOG" 2>/dev/null
-				rm -f "$log"
-				return 0
-			fi
-			cat "$log" >> "$CAU_RUNLOG" 2>/dev/null
 				;;
 
 			conflict)
@@ -126,18 +180,29 @@ cau_pacman_update() {
 				# question bitmask: 4 = CONFLICT_PKG, 16 = REMOVE_PKGS.
 				if [[ $CFG_RESOLVE_CONFLICTS != yes ]]; then
 					cau_error "Package conflict requires a decision (AutoResolveConflicts is off)"
-				rm -f "$log"
+					break
-				return 1
 				fi
 				cau_info "Resolving package conflicts automatically and retrying"
-			if pacman -Syu "${flags[@]}" --ask=20 > "$log" 2>&1; then
+				extra+=(--ask=20)
-				cat "$log" >> "$CAU_RUNLOG" 2>/dev/null
+				;;
-				grep -E '^(removing|replacing) ' "$log" 2>/dev/null \
+
-					| while read -r line; do cau_info "  $line"; done
+			dependency)
-				rm -f "$log"
+				# Something installed still depends on a package the repos want
-				return 0
+				# to drop or replace - almost always an AUR package that has not
+				# caught up yet. Nothing here can fix that, and it is not worth
+				# failing over: letting one stuck package block every other
+				# update indefinitely is far worse on an unattended machine.
+				# Hold the blockers back and upgrade everything else.
+				mapfile -t blockers < <(_cau_pacman_blockers "$log")
+				if (( ${#blockers[@]} == 0 )); then
+					cau_error "Dependency problem with no package to hold back"
+					break
 				fi
-			cat "$log" >> "$CAU_RUNLOG" 2>/dev/null
+				for b in "${blockers[@]}"; do
+					extra+=(--ignore "$b")
+				done
+				CAU_PACMAN_HELD="${blockers[*]}"
+				cau_warn "Holding back ${blockers[*]} and retrying without them"
 				;;
 
 			filesystem)
@@ -145,13 +210,18 @@ cau_pacman_update() {
 				# silently clobber something the user put there deliberately, so
 				# this one stays a human decision.
 				cau_error "Files on disk conflict with the update; manual review needed"
-			rm -f "$log"
+				break
-			return 1
+				;;
+
+			*)
+				break
 				;;
 		esac
+	done
 
 	rm -f "$log"
 	CAU_PACMAN_COUNT=0
+	CAU_PACMAN_HELD=''
 	return 1
 }