[codex] Add node reinstall command

docs/local-dev.md

@@ -134,3 +134,16 @@ amesh-node update
 Authenticated admins can also trigger the same node-side updater from the dashboard. The control plane sends a `node.update` command over the existing node websocket, the daemon runs `amesh-node update`, and a managed systemd service should restart back into the new binary after the process exits.
 - The dashboard only shows the update action when the node reports an installed release tag and that tag differs from the control plane's latest known GitHub release tag.
 - Daemon-triggered self-updates reuse the node's active `server`, `config`, and `state` paths and deliberately avoid `systemctl stop` during the update run. The daemon exits after the installer finishes and systemd restarts it into the new binary.
+
+## Remote reinstall
+
+```bash
+amesh-node reinstall
+```
+
+The shared CLI also exposes the same command as `amesh reinstall`.
+
+`reinstall` is the destructive recovery path for a stale or suspect node install. It stops and disables the managed user service, removes the node service file, durable node state, detected agent config, installed `amesh-node` and `amesh` binaries, and the managed `~/.local/share/amesh` payload, then runs the installer again from scratch.
+- Use `reinstall` when you suspect stale node state, stale detected agent inventory, or broken managed ACPX/node wiring.
+- `reinstall` preserves the user ACPX config at `~/.acpx/config.json`; it only wipes amesh-managed node artifacts.
+- On success, the installer re-detects agents, re-registers the node, rewrites the service, and starts the managed daemon again.

docs/testing.md

@@ -38,3 +38,5 @@
 - The web app also covers the top-bar MCP config panel so the copy-paste client snippets stay aligned with the server endpoint and scope headers.
 - The Go daemon owns table-driven tests for config loading, reconnect logic, update, detect, exposed-path command dispatch, and `acpx` process lifecycle including streamed output and cancellation.
 - The dev helper script also has a regression shell test for the stale local reconnect-token path, so local `pnpm dev:daemon` re-registers automatically after a fresh control-plane reset.
+- The Go daemon also covers the shared `reinstall` subcommand and verifies that reinstall mode passes the destructive reset flag through to the installer.
+- `scripts/test-install-amesh-node.sh` also covers remote self-update and full reinstall flows, including reinstall-time cleanup of stale node state, config, service, binaries, and managed amesh home.

install-amesh-node.sh

@@ -19,6 +19,7 @@ SERVER_URL="${SERVER_URL:-}"
 REGISTRATION_TOKEN="${REGISTRATION_TOKEN:-}"
 NODE_ID="${NODE_ID:-$(hostname)-amesh}"
 SELF_UPDATE="${AMESH_NODE_SELF_UPDATE:-0}"
+REINSTALL="${AMESH_NODE_REINSTALL:-0}"
 
 log() {
   printf '%s\n' "$*" >&2
@@ -220,6 +221,16 @@ main() {
   tmp_dir="$(mktemp -d)"
   trap 'rm -rf "${tmp_dir}"' EXIT
 
+  if [[ "$REINSTALL" == "1" ]]; then
+    log "reinstall requested; removing existing node install artifacts"
+    if command -v systemctl >/dev/null 2>&1; then
+      systemctl --user stop "$SERVICE_NAME" >/dev/null 2>&1 || true
+      systemctl --user disable "$SERVICE_NAME" >/dev/null 2>&1 || true
+    fi
+    rm -f "$SERVICE_PATH" "$STATE_PATH" "$CONFIG_PATH" "$binary_path" "$cli_binary_path"
+    rm -rf "$AMESH_HOME"
+  fi
+
   mkdir -p "${install_dir}"
   mkdir -p "${AMESH_HOME}"
   mkdir -p "$(dirname "$STATE_PATH")"

internal/app/app.go

@@ -47,6 +47,7 @@ type nodeUpdateOptions struct {
 	ConfigPath string
 	StatePath  string
 	SelfUpdate bool
+	Reinstall bool
 }
 
 type updateRunner func(ctx context.Context, stdout, stderr io.Writer, options nodeUpdateOptions) error
@@ -96,7 +97,7 @@ func Run(ctx context.Context, args []string) error {
 
 func run(ctx context.Context, args []string, update updateRunner, detect detectRunner) error {
 	if len(args) == 0 {
-		return errors.New("expected subcommand: register, run, detect, update, or acp")
+		return errors.New("expected subcommand: register, run, detect, update, reinstall, logs, or acp")
 	}
 
 	switch args[0] {
@@ -108,6 +109,8 @@ func run(ctx context.Context, args []string, update updateRunner, detect detectR
 		return runDetectCommand(ctx, args[1:], detect)
 	case "update":
 		return update(ctx, os.Stdout, os.Stderr, nodeUpdateOptions{})
+	case "reinstall":
+		return update(ctx, os.Stdout, os.Stderr, nodeUpdateOptions{Reinstall: true})
 	case "acp":
 		return runACPBridge(ctx, args[1:], os.Stdin, os.Stdout)
 	case "logs":
@@ -168,6 +171,15 @@ func runACPBridge(ctx context.Context, args []string, stdin io.Reader, stdout io
 }
 
 func runUpdate(ctx context.Context, stdout, stderr io.Writer, options nodeUpdateOptions) error {
+	return runInstaller(ctx, stdout, stderr, options, options.Reinstall)
+}
+
+func runReinstall(ctx context.Context, stdout, stderr io.Writer, options nodeUpdateOptions) error {
+	options.Reinstall = true
+	return runInstaller(ctx, stdout, stderr, options, true)
+}
+
+func runInstaller(ctx context.Context, stdout, stderr io.Writer, options nodeUpdateOptions, reinstall bool) error {
 	if _, err := exec.LookPath("bash"); err != nil {
 		return errors.New("required CLI missing: bash")
 	}
@@ -203,14 +215,24 @@ func runUpdate(ctx context.Context, stdout, stderr io.Writer, options nodeUpdate
 	if options.SelfUpdate {
 		cmd.Env = append(cmd.Env, "AMESH_NODE_SELF_UPDATE=1")
 	}
+	if reinstall {
+		cmd.Env = append(cmd.Env, "AMESH_NODE_REINSTALL=1")
+	}
 	if os.Getenv("INSTALL_DIR") == "" {
 		if installDir, ok := currentInstallDir(); ok {
 			cmd.Env = append(cmd.Env, "INSTALL_DIR="+installDir)
 		}
 	}
 
-	fmt.Fprintf(stdout, "updating amesh-node from %s\n", installerURL)
+	action := "updating"
+	if reinstall {
+		action = "reinstalling"
+	}
+	fmt.Fprintf(stdout, "%s amesh-node from %s\n", action, installerURL)
 	if err := cmd.Run(); err != nil {
+		if reinstall {
+			return fmt.Errorf("reinstall failed: %w", err)
+		}
 		return fmt.Errorf("update failed: %w", err)
 	}
 	return nil

internal/app/app_test.go

@@ -140,6 +140,30 @@ func TestRunDispatchesUpdateSubcommand(t *testing.T) {
 	}
 }
 
+func TestRunDispatchesReinstallSubcommand(t *testing.T) {
+	t.Parallel()
+
+	called := false
+	err := run(
+		context.Background(),
+		[]string{"reinstall"},
+		func(_ context.Context, _ io.Writer, _ io.Writer, options nodeUpdateOptions) error {
+			called = true
+			if !options.Reinstall {
+				t.Fatal("expected reinstall flag to be set")
+			}
+			return nil
+		},
+		func(context.Context, string) error { return nil },
+	)
+	if err != nil {
+		t.Fatalf("run() error = %v", err)
+	}
+	if !called {
+		t.Fatal("expected update runner to be called for reinstall")
+	}
+}
+
 func TestRunDispatchesDetectSubcommand(t *testing.T) {
 	t.Parallel()
 
@@ -282,6 +306,43 @@ func TestRunUpdatePassesRuntimeContextToInstaller(t *testing.T) {
 	}
 }
 
+func TestRunReinstallPassesResetModeToInstaller(t *testing.T) {
+	binDir := t.TempDir()
+	envLogPath := filepath.Join(t.TempDir(), "installer-env.log")
+	writeExecutable(t, filepath.Join(binDir, "curl"), fmt.Sprintf(`#!/bin/sh
+	printf 'AMESH_NODE_REINSTALL=%%s\nSERVER_URL=%%s\nSTATE_PATH=%%s\n' \
+	  "$AMESH_NODE_REINSTALL" "$SERVER_URL" "$STATE_PATH" > %q
+	printf '%%s\n' '#!/bin/sh'
+	printf '%%s\n' 'exit 0'
+`, envLogPath))
+	t.Setenv("PATH", binDir+string(os.PathListSeparator)+os.Getenv("PATH"))
+	t.Setenv("AMESH_INSTALL_URL", "https://example.invalid/install-amesh-node.sh")
+
+	var stdout bytes.Buffer
+	err := runReinstall(context.Background(), &stdout, io.Discard, nodeUpdateOptions{
+		ServerURL: "ws://example.invalid/ws?role=node",
+		StatePath: "/srv/amesh/node-state.json",
+	})
+	if err != nil {
+		t.Fatalf("runReinstall() error = %v", err)
+	}
+
+	bytes, err := os.ReadFile(envLogPath)
+	if err != nil {
+		t.Fatalf("read env log: %v", err)
+	}
+	got := string(bytes)
+	for _, want := range []string{
+		"AMESH_NODE_REINSTALL=1",
+		"SERVER_URL=ws://example.invalid/ws?role=node",
+		"STATE_PATH=/srv/amesh/node-state.json",
+	} {
+		if !strings.Contains(got, want) {
+			t.Fatalf("installer env = %q, want %q", got, want)
+		}
+	}
+}
+
 func TestRunDaemonSessionHandlesNodeDetect(t *testing.T) {
 	t.Parallel()
 

scripts/test-install-amesh-node.sh

@@ -326,3 +326,176 @@ if grep -F 'stop amesh-node' "$self_systemctl_log" >/dev/null 2>&1; then
   cat "$self_systemctl_log" >&2
   exit 1
 fi
+
+reinstall_stub_dir="$tmp_dir/reinstall-bin"
+mkdir -p "$reinstall_stub_dir"
+
+cat <<'EOF' >"$reinstall_stub_dir/curl"
+#!/usr/bin/env bash
+set -euo pipefail
+archive="${@: -1}"
+printf 'stub archive' >"$archive"
+EOF
+chmod +x "$reinstall_stub_dir/curl"
+
+cat <<'EOF' >"$reinstall_stub_dir/npm"
+#!/usr/bin/env bash
+set -euo pipefail
+exit 0
+EOF
+chmod +x "$reinstall_stub_dir/npm"
+
+cat <<'EOF' >"$reinstall_stub_dir/systemctl"
+#!/usr/bin/env bash
+set -euo pipefail
+printf '%s\n' "$*" >>"${SYSTEMCTL_LOG:?}"
+verb=
+for arg in "$@"; do
+  case "$arg" in
+    --user|--now|--quiet|--no-pager|--full)
+      continue
+      ;;
+    *)
+      verb="$arg"
+      break
+      ;;
+  esac
+done
+case "$verb" in
+  stop|disable|daemon-reload|enable|is-active)
+    if [[ "$verb" == "is-active" ]]; then
+      exit 0
+    fi
+    exit 0
+    ;;
+  *)
+    exit 99
+    ;;
+esac
+EOF
+chmod +x "$reinstall_stub_dir/systemctl"
+
+cat <<'EOF' >"$reinstall_stub_dir/uname"
+#!/usr/bin/env bash
+set -euo pipefail
+case "${1:-}" in
+  -m)
+    printf 'x86_64\n'
+    ;;
+  *)
+    printf 'Linux\n'
+    ;;
+esac
+EOF
+chmod +x "$reinstall_stub_dir/uname"
+
+cat <<'EOF' >"$reinstall_stub_dir/mktemp"
+#!/usr/bin/env bash
+set -euo pipefail
+dir="${TMPDIR:-/tmp}/amesh-test-reinstall"
+mkdir -p "$dir"
+printf '%s\n' "$dir"
+EOF
+chmod +x "$reinstall_stub_dir/mktemp"
+
+cat <<'EOF' >"$reinstall_stub_dir/tar"
+#!/usr/bin/env bash
+set -euo pipefail
+target_dir=
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    -C)
+      target_dir="$2"
+      shift 2
+      ;;
+    *)
+      shift
+      ;;
+  esac
+done
+mkdir -p "$target_dir"
+cat <<'BIN' >"$target_dir/amesh-node"
+#!/usr/bin/env bash
+set -euo pipefail
+exit 0
+BIN
+chmod +x "$target_dir/amesh-node"
+cat <<'BIN' >"$target_dir/amesh"
+#!/usr/bin/env bash
+set -euo pipefail
+exit 0
+BIN
+chmod +x "$target_dir/amesh"
+EOF
+chmod +x "$reinstall_stub_dir/tar"
+
+cat <<'EOF' >"$reinstall_stub_dir/install"
+#!/usr/bin/env bash
+set -euo pipefail
+src="${@: -2:1}"
+dest="${@: -1}"
+cp "$src" "$dest"
+chmod 0755 "$dest"
+EOF
+chmod +x "$reinstall_stub_dir/install"
+
+cat <<'EOF' >"$reinstall_stub_dir/node"
+#!/usr/bin/env bash
+set -euo pipefail
+case "${1:-}" in
+  -v)
+    printf 'v24.13.1\n'
+    ;;
+  -p)
+    printf '24\n'
+    ;;
+  *)
+    exit 0
+    ;;
+esac
+EOF
+chmod +x "$reinstall_stub_dir/node"
+
+reinstall_env_dir="$tmp_dir/reinstall-env"
+mkdir -p "$reinstall_env_dir/home/keep-me"
+mkdir -p "$reinstall_env_dir/bin"
+printf '{"old":true}\n' >"$reinstall_env_dir/agents.json"
+printf '{"nodeId":"node-a","reconnectToken":"token","serverUrl":"ws://saved.invalid/ws?role=node","configPath":"%s"}\n' "$reinstall_env_dir/agents.json" >"$reinstall_env_dir/node-state.json"
+printf '[Unit]\nDescription=old service\n' >"$reinstall_env_dir/amesh-node.service"
+printf 'old binary\n' >"$reinstall_env_dir/bin/amesh-node"
+printf 'old cli\n' >"$reinstall_env_dir/bin/amesh"
+printf 'stale managed home\n' >"$reinstall_env_dir/home/keep-me/stale.txt"
+
+reinstall_systemctl_log="$tmp_dir/reinstall-systemctl.log"
+reinstall_log="$tmp_dir/reinstall.log"
+if ! PATH="$reinstall_stub_dir:$PATH" \
+  SYSTEMCTL_LOG="$reinstall_systemctl_log" \
+  AMESH_NODE_REINSTALL='1' \
+  AMESH_VERSION_TAG='test-tag' \
+  INSTALL_DIR="$reinstall_env_dir/bin" \
+  AMESH_HOME="$reinstall_env_dir/home" \
+  ACPX_PREFIX="$reinstall_env_dir/acpx" \
+  ACPX_CONFIG_PATH="$reinstall_env_dir/acpx-config.json" \
+  CONFIG_PATH="$reinstall_env_dir/agents.json" \
+  STATE_PATH="$reinstall_env_dir/node-state.json" \
+  SERVICE_PATH="$reinstall_env_dir/amesh-node.service" \
+  NODE_ID='reinstall-node' \
+  SERVER_URL='wss://example.invalid/ws?role=node' \
+  REGISTRATION_TOKEN='token' \
+  bash <"$ROOT_DIR/install-amesh-node.sh" >"$reinstall_log" 2>&1; then
+  printf 'expected reinstall installer execution to succeed\n' >&2
+  cat "$reinstall_log" >&2
+  exit 1
+fi
+
+assert_contains 'stop amesh-node' "$reinstall_systemctl_log"
+assert_contains 'disable amesh-node' "$reinstall_systemctl_log"
+assert_contains 'enable --now amesh-node' "$reinstall_systemctl_log"
+if [[ -f "$reinstall_env_dir/home/keep-me/stale.txt" ]]; then
+  printf 'reinstall should remove previous managed amesh home\n' >&2
+  exit 1
+fi
+if grep -F '"old":true' "$reinstall_env_dir/agents.json" >/dev/null 2>&1; then
+  printf 'reinstall should replace stale agent config\n' >&2
+  exit 1
+fi