.agents/skills/multi-agent-mux-update/SKILL.md

@@ -27,4 +27,4 @@ bash .agents/skills/multi-agent-mux-update/scripts/update.sh --yes
 | Monitor | stopped first, started again afterwards only if it ran (`MAM_NO_SUBSCRIBER_DAEMON=1`: not started). |
 | Install | the installer at `MAM_INSTALLER_URL` (default: Gitea `main`) runs in place; `.mam` is kept. On failure `.agents/`, `.mam_deploy/`, root files, `.venv`, the installer's `.mam` files and the registry are restored from `.mam/update-backup/`. |
 | Registry | converted by the new code (`lib_py.registry_format`); a failed conversion keeps the install and exits nonzero. |
-| Exit | `0` updated, `1` refused or failed, `2` bad arguments. |
+| Exit | `0` updated (or cancelled at the prompt), `1` refused or failed, `2` bad arguments; a failed registry conversion after a good install exits with the converter's nonzero code. |

.agents/skills/multi-agent-mux-update/scripts/install_phase.sh

@@ -81,7 +81,14 @@ MON="${3:-0}"
 TMPD="${4:-}"
 trap '[ -z "$TMPD" ] || rm -rf "$TMPD"' EXIT
 
-set_state installing || { echo "ERROR: cannot write $BK/state" >&2; release_marker; exit 1; }
+if ! set_state installing; then
+  # Nothing was installed yet: drop the backup and put the monitor back as phase 1 found it.
+  echo "ERROR: cannot write $BK/state; nothing was changed" >&2
+  rm -rf "$BK"
+  restart_old_monitor "$MON"
+  release_marker
+  exit 1
+fi
 URL="${MAM_INSTALLER_URL:-https://git.godopu.com/tmpl/multi-agent-mux/raw/branch/main/deploy/install.sh}"
 echo "install: $URL"
 irc=0

tests/test_issue72_update.py

@@ -702,6 +702,26 @@ def test_leftover_whose_restore_fails_is_kept_and_nothing_more_changes(box):
     assert not (box.mam / "update-in-progress").exists()
 
 
+def test_a_state_write_failure_before_the_install_changes_nothing_and_restarts_the_monitor(box):
+    real_mv = shutil.which("mv")
+    fake = box.bin / "mv"
+    fake.write_text("#!/usr/bin/env bash\n"
+                    "src=\"${@: -2:1}\"\n"
+                    "case \"$src\" in */update-backup/state.tmp) grep -qx installing \"$src\" && exit 1 ;; esac\n"
+                    "exec %s \"$@\"\n" % real_mv)
+    fake.chmod(0o755)
+    box.stub_monitor()
+    box.start_monitor()
+    box.installer("touch \"$ws/INSTALLER-RAN\"\n")
+    res = box.update()
+    assert res.returncode == 1, res.stdout + res.stderr
+    assert not (box.ws / "INSTALLER-RAN").exists()
+    assert box.monitor_starts() == 2, "the monitor it stopped is started again"
+    _until(lambda: bool(box.monitor_pids()))
+    assert not (box.mam / "update-backup").exists() and not (box.mam / "update-in-progress").exists()
+    assert "nothing was changed" in res.stderr
+
+
 def test_the_backup_lives_in_the_workspace_and_is_gone_after_success(box):
     box.installer("test -f \"$ws/.mam/update-backup/state\" && grep -qx installing \"$ws/.mam/update-backup/state\" "
                   "&& test -f \"$ws/.mam/update-backup/files/.agents/skills/lib.sh\" && touch \"$ws/../saw-backup\"\n")