fix(maestro): always probe tmux during recovery

#164 skipped the tmux probe whenever the stored boot id differed from the
current one, assuming a changed boot id proves the tmux server is gone. It
does not: a restored state directory, a VM or container snapshot rollback,
or a truncated boot_id file all change it while tmux keeps running with
live sessions. Every one of those sessions was then registered Dormant and
stranded — resume respawns `maestro-<id>`, which collides with the name
tmux still holds, so it failed 502 forever.

Recovery now always runs `tmux list-sessions`, the single source of truth
for liveness the rest of the daemon assumes. The boot id keeps its other
job: telling a reboot from a restart in recovery's log.

The #164 test asserted the old behaviour with tmux still alive, so it is
replaced by one asserting the session is adopted Running, plus one covering
a real reboot — boot id changed and the tmux server dead — still going
dormant.

Refs #174

crates/maestro-config/src/lib.rs

@@ -129,6 +129,80 @@ pub struct DaemonSection {
     /// `Some(0)` disables history entirely (no log written, no recents read).
     #[serde(default)]
     pub spawn_history_days: Option<u32>,
+    /// What recovery does with sessions that outlived their tmux server —
+    /// after a host reboot, or any restart that finds a sidecar with no pane
+    /// (#167). Default [`ResumeOnBoot::Dormant`].
+    #[serde(default, deserialize_with = "deserialize_resume_on_boot")]
+    pub resume_on_boot: Option<ResumeOnBoot>,
+}
+
+impl DaemonSection {
+    /// The configured `[daemon].resume_on_boot`, or the safe default:
+    /// recovered-but-dead sessions wait for the operator.
+    pub fn resume_on_boot(&self) -> ResumeOnBoot {
+        self.resume_on_boot.unwrap_or_default()
+    }
+}
+
+/// `[daemon].resume_on_boot` — what recovery does with a session whose tmux
+/// pane is gone but whose sidecar is still on disk (#167).
+///
+/// Resuming agents unattended seconds after a reboot is a foot-gun: they run
+/// with whatever flags they were spawned with, with nobody watching. So the
+/// default waits for a human, and `auto` is opted into per host.
+#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
+pub enum ResumeOnBoot {
+    /// Register each one `Dormant` and wait for the operator to resume it.
+    #[default]
+    Dormant,
+    /// Resume each one during recovery, on the same path a client's
+    /// `POST /api/sessions/:id/resume` takes.
+    Auto,
+    /// Prune the sidecars instead: a reboot is a clean slate.
+    Never,
+}
+
+/// Every `[daemon].resume_on_boot` name and its variant, in documentation
+/// order.
+pub const RESUME_ON_BOOT_POLICIES: &[(&str, ResumeOnBoot)] = &[
+    ("dormant", ResumeOnBoot::Dormant),
+    ("auto", ResumeOnBoot::Auto),
+    ("never", ResumeOnBoot::Never),
+];
+
+impl ResumeOnBoot {
+    /// The name this policy is spelled with in the config file and in logs.
+    pub fn as_str(&self) -> &'static str {
+        match self {
+            ResumeOnBoot::Dormant => "dormant",
+            ResumeOnBoot::Auto => "auto",
+            ResumeOnBoot::Never => "never",
+        }
+    }
+}
+
+fn deserialize_resume_on_boot<'de, D>(deserializer: D) -> Result<Option<ResumeOnBoot>, D::Error>
+where
+    D: Deserializer<'de>,
+{
+    let raw = Option::<String>::deserialize(deserializer)?;
+    raw.map(|name| {
+        RESUME_ON_BOOT_POLICIES
+            .iter()
+            .find(|(n, _)| *n == name)
+            .map(|(_, policy)| *policy)
+            .ok_or_else(|| {
+                let known = RESUME_ON_BOOT_POLICIES
+                    .iter()
+                    .map(|(n, _)| format!("{n:?}"))
+                    .collect::<Vec<_>>()
+                    .join(", ");
+                D::Error::custom(format!(
+                    "invalid [daemon].resume_on_boot {name:?}; expected one of {known}"
+                ))
+            })
+    })
+    .transpose()
 }
 
 /// `[tui]` — `maestro tui` settings (NAP-275 epic, phase 2 NAP-277).
@@ -775,4 +849,27 @@ bind_addr = "127.0.0.1:9090"
         );
         assert_eq!(cfg.resolve_daemon_url(None), "http://explicit:1");
     }
+
+    #[test]
+    fn resume_on_boot_defaults_to_dormant_and_parses_every_policy() {
+        assert_eq!(
+            MaestroConfigFile::default().daemon.resume_on_boot(),
+            ResumeOnBoot::Dormant,
+            "an absent policy is the safe one"
+        );
+        for (name, expected) in RESUME_ON_BOOT_POLICIES {
+            let cfg = file_with(&format!("[daemon]\nresume_on_boot = \"{name}\"\n"));
+            assert_eq!(cfg.daemon.resume_on_boot(), *expected, "{name}");
+            assert_eq!(expected.as_str(), *name);
+        }
+    }
+
+    #[test]
+    fn resume_on_boot_rejects_an_unknown_policy() {
+        let err = toml::from_str::<MaestroConfigFile>("[daemon]\nresume_on_boot = \"maybe\"\n")
+            .expect_err("unknown policy must not silently fall back");
+        let msg = err.to_string();
+        assert!(msg.contains("resume_on_boot"), "{msg}");
+        assert!(msg.contains("\"auto\""), "{msg}");
+    }
 }

crates/maestro-daemon/src/boot_id.rs

@@ -2,10 +2,13 @@
 //!
 //! `/proc/sys/kernel/random/boot_id` is fixed for the life of the kernel and
 //! changes on every boot. [`SessionManager::recover`] compares it against the
-//! value it stored on the previous run: a difference means every session from
-//! before is provably dead, so the tmux probe can be skipped and those
-//! sessions registered dormant directly instead of relying on tmux reporting
-//! an empty list.
+//! value it stored on the previous run and logs which of the two it was.
+//!
+//! It does not decide liveness (#174). A boot id changes without the tmux
+//! server dying whenever the state directory is restored, a VM or container
+//! snapshot is rolled back, or the `boot_id` file is truncated — so recovery
+//! always probes `tmux list-sessions` and the boot id only says whether a
+//! server that did not answer is coming back.
 
 use std::path::Path;
 

crates/maestro-daemon/src/cli.rs

@@ -87,7 +87,10 @@ async fn run(config_override: Option<PathBuf>) -> Result<(), Box<dyn Error>> {
     .with_boot_id(
         config.boot_id_path(),
         std::sync::Arc::new(crate::boot_id::ProcBootId),
-    );
+    )
+    // #167: recovery needs the presets to resolve a resumed session's command,
+    // so `auto` runs the same resume a client's POST would.
+    .with_resume_policy(config.resume_on_boot, config.spawn_presets.clone());
     // Spawned sessions learn where to report back (#103). Derived from the
     // configured bind address; set before any spawn can happen.
     manager.set_daemon_url(format!("http://{}", config.bind_addr));

crates/maestro-daemon/src/config.rs

@@ -97,6 +97,10 @@ pub struct DaemonConfig {
     /// never binds it itself; it serves it so the web client and the TUI read
     /// one knob.
     pub leader: String,
+    /// What recovery does with sessions whose tmux pane is gone but whose
+    /// sidecar survives (#167): `[daemon].resume_on_boot`, default
+    /// [`maestro_config::ResumeOnBoot::Dormant`].
+    pub resume_on_boot: maestro_config::ResumeOnBoot,
 }
 
 impl DaemonConfig {
@@ -149,6 +153,8 @@ pub fn load_config(path: &Path, env: EnvOverrides) -> Result<DaemonConfig, Confi
     // validation (#22/#26).
     let spawn_presets = file.spawn.resolve()?;
 
+    let resume_on_boot = daemon.resume_on_boot();
+
     let hostname = daemon.hostname.unwrap_or_else(system_hostname);
     let home_dir = dirs::home_dir()
         .map(|p| p.to_string_lossy().into_owned())
@@ -209,6 +215,7 @@ pub fn load_config(path: &Path, env: EnvOverrides) -> Result<DaemonConfig, Confi
         project_scan_depth,
         hooks_auto_install: file.hooks.auto_install(),
         leader: file.tui.leader().to_string(),
+        resume_on_boot,
     })
 }
 
@@ -289,6 +296,34 @@ auto_install = false
         assert!(!cfg.hooks_auto_install);
     }
 
+    #[test]
+    fn resume_on_boot_defaults_to_dormant_and_reads_the_file() {
+        let dir = tempfile::tempdir().unwrap();
+        let path = dir.path().join("config.toml");
+        std::fs::write(&path, "").unwrap();
+        assert_eq!(
+            load_config(&path, EnvOverrides::default())
+                .unwrap()
+                .resume_on_boot,
+            maestro_config::ResumeOnBoot::Dormant
+        );
+
+        std::fs::write(
+            &path,
+            r#"
+[daemon]
+resume_on_boot = "auto"
+"#,
+        )
+        .unwrap();
+        assert_eq!(
+            load_config(&path, EnvOverrides::default())
+                .unwrap()
+                .resume_on_boot,
+            maestro_config::ResumeOnBoot::Auto
+        );
+    }
+
     #[test]
     fn empty_file_defaults_everything() {
         let dir = tempfile::tempdir().unwrap();

crates/maestro-daemon/src/session.rs

@@ -12,6 +12,7 @@ use std::sync::Arc;
 use std::time::Duration;
 
 use chrono::Utc;
+use maestro_config::ResumeOnBoot;
 use maestro_protocol::{
     ActivityState, CatalogEvent, CreateSessionRequest, ErrorInfo, NameSource, Session,
     SessionStatus, WorktreeSpec, NAME_KEY, NAME_SOURCE_KEY,
@@ -195,6 +196,11 @@ struct Inner {
     /// reboot detection is unwired, which behaves exactly like a boot id
     /// that could never be read: always fall back to probing tmux.
     boot_id: Option<BootIdConfig>,
+    /// What recovery does with a session whose pane is gone (#167), and the
+    /// presets an `auto` resume resolves its command from. Defaults to
+    /// [`ResumeOnBoot::Dormant`] with no presets: register and wait.
+    resume_policy: ResumeOnBoot,
+    resume_presets: Vec<maestro_protocol::SpawnPreset>,
 }
 
 /// Where recovery persists the boot id it last saw, and how it reads the
@@ -253,6 +259,8 @@ impl SessionManager {
                 viewports: Mutex::new(Viewports::new()),
                 next_viewport: AtomicU64::new(0),
                 boot_id: None,
+                resume_policy: ResumeOnBoot::default(),
+                resume_presets: Vec::new(),
             }),
         }
     }
@@ -297,6 +305,26 @@ impl SessionManager {
         self
     }
 
+    /// Wire the `[daemon].resume_on_boot` policy (#167) and the spawn presets
+    /// an `auto` resume resolves each session's command from. Builder, called
+    /// once right after construction like the other `with_*` methods. Without
+    /// it, recovery behaves as [`ResumeOnBoot::Dormant`].
+    ///
+    /// # Panics
+    ///
+    /// If the handle has already been cloned.
+    pub fn with_resume_policy(
+        mut self,
+        policy: ResumeOnBoot,
+        presets: Vec<maestro_protocol::SpawnPreset>,
+    ) -> Self {
+        let inner = Arc::get_mut(&mut self.inner)
+            .expect("with_resume_policy must be called before the SessionManager is cloned");
+        inner.resume_policy = policy;
+        inner.resume_presets = presets;
+        self
+    }
+
     /// Set the daemon's own HTTP base URL (#103), exported to every session
     /// spawned afterwards as `MAESTRO_URL`. Unlike the `with_*` builders this
     /// is a plain setter: the daemon runner learns its bound address after
@@ -819,20 +847,20 @@ impl SessionManager {
     /// that no longer exists are still adopted — the spec does not require
     /// us to repair them.
     ///
-    /// #164: when the kernel's boot id has changed since the last run, the
-    /// tmux probe below is skipped entirely — a reboot kills the tmux server,
-    /// so every previous session is already dead and there is nothing tmux
-    /// could truthfully adopt. [`Self::register_dormant`] then registers all
-    /// of them directly.
+    /// #164/#174: the kernel's boot id says whether the host rebooted since
+    /// the last run, but it never decides which sessions are alive —
+    /// `tmux list-sessions` does, always, which is what the rest of the
+    /// daemon assumes. A boot id can change without the tmux server dying
+    /// (a restored state directory, a VM or container snapshot restore, a
+    /// truncated `boot_id` file); skipping the probe then registered every
+    /// live session `Dormant`, and resume could never bring one back because
+    /// the tmux name was still taken. The boot id is now only a signal that a
+    /// tmux server which did not answer is not coming back, and it names
+    /// itself in recovery's log.
     pub async fn recover(&self) -> Result<usize, SessionError> {
         tokio::fs::create_dir_all(&self.inner.fifo_dir).await?;
         let rebooted = self.check_boot_id().await;
-        let live = if rebooted {
-            // #164: every session from the previous boot is provably dead —
-            // no tmux server survives a reboot — so there is nothing to gain
-            // from asking it and no session it could honestly report back.
-            Vec::new()
-        } else {
+        let live = {
             let tmux = self.inner.tmux.clone();
             tmux_blocking(move || tmux.list_sessions()).await?
         };
@@ -912,7 +940,9 @@ impl SessionManager {
     ///
     /// A missing stored value (first run) or an unreadable current one
     /// (non-Linux, restricted `/proc`, unwired in this build) both read as
-    /// "no reboot", which is today's behaviour: fall back to probing tmux.
+    /// "no reboot". Either way the tmux probe runs (#174): the answer only
+    /// tells recovery whether a tmux server that did not answer is coming
+    /// back, never which sessions are alive.
     async fn check_boot_id(&self) -> bool {
         let Some(cfg) = &self.inner.boot_id else {
             return false;
@@ -959,7 +989,8 @@ impl SessionManager {
     /// `rebooted` (#164) only changes what gets logged: a detected reboot
     /// names the count even when it is zero, so the operator sees that
     /// recovery told a reboot from a restart instead of a log that stays
-    /// silent either way.
+    /// silent either way. It never decides membership — everything here got
+    /// here by tmux not holding it (#174).
     async fn register_dormant(&self, rebooted: bool) {
         let stored = match self.inner.sidecar.load_all() {
             Ok(stored) => stored,
@@ -970,6 +1001,7 @@ impl SessionManager {
         };
         let mut registered = Vec::new();
         let mut pruned = 0usize;
+        let mut discarded = 0usize;
         {
             let mut sessions = self.inner.sessions.lock().await;
             for mut session in stored {
@@ -984,6 +1016,16 @@ impl SessionManager {
                     pruned += 1;
                     continue;
                 }
+                if self.inner.resume_policy == ResumeOnBoot::Never {
+                    // #167: this host wants a reboot to be a clean slate, so
+                    // the sidecar goes the way #163's does — nothing is
+                    // registered and the next recovery finds nothing.
+                    if let Err(e) = self.inner.sidecar.delete(session.id) {
+                        tracing::warn!(error = ?e, id = %session.id, "recover: failed to prune sidecar under resume_on_boot=never");
+                    }
+                    discarded += 1;
+                    continue;
+                }
                 let id = session.id;
                 session.status = SessionStatus::Dormant;
                 session.foreground = None;
@@ -1025,12 +1067,45 @@ impl SessionManager {
         if pruned > 0 {
             tracing::info!(pruned, "pruned sidecars whose cwd no longer exists");
         }
+        let resumable: Vec<Uuid> = registered.iter().map(|s| s.id).collect();
         for session in registered {
             let _ = self
                 .inner
                 .events
                 .send(CatalogEvent::SessionAdded { session });
         }
+
+        // #167: say which policy ran and how many sessions it acted on, so a
+        // host that resumes agents unattended says so in its own log. The
+        // match is exhaustive on purpose: a fourth policy must decide what it
+        // does here rather than inherit whichever arm happened to be last.
+        match self.inner.resume_policy {
+            ResumeOnBoot::Dormant => tracing::info!(
+                policy = ResumeOnBoot::Dormant.as_str(),
+                sessions = resumable.len(),
+                "resume_on_boot: sessions left dormant for the operator"
+            ),
+            ResumeOnBoot::Never => tracing::info!(
+                policy = ResumeOnBoot::Never.as_str(),
+                sessions = discarded,
+                "resume_on_boot: pruned the sidecars of sessions with no live pane"
+            ),
+            ResumeOnBoot::Auto => {
+                tracing::info!(
+                    policy = ResumeOnBoot::Auto.as_str(),
+                    sessions = resumable.len(),
+                    "resume_on_boot: resuming sessions with no live pane"
+                );
+                let presets = self.inner.resume_presets.clone();
+                for id in resumable {
+                    // The same call the client's POST /api/sessions/:id/resume
+                    // makes — one resume path, not two.
+                    if let Err(e) = self.resume(id, &presets).await {
+                        tracing::warn!(error = %e, id = %id, "resume_on_boot=auto: resume failed; session stays dormant");
+                    }
+                }
+            }
+        }
     }
 
     /// Forward keystrokes to a session's pane. A dead or dormant session is
@@ -1657,6 +1732,7 @@ async fn mark_session_dead(inner: &Arc<Inner>, id: Uuid) {
             // The tree is settled (removed); a stale "in the way" would
             // describe something the session no longer holds.
             session.blocked_work = None;
+            session.worktree = None;
             let mut sessions = inner.sessions.lock().await;
             if let Some(record) = sessions.get_mut(&id) {
                 record.session.worktree = None;

crates/maestro-daemon/tests/resume_policy.rs

@@ -0,0 +1,161 @@
+//! `[daemon].resume_on_boot` (#167): what recovery does with sessions whose
+//! tmux pane is gone but whose sidecar survived, against real tmux.
+//!
+//! The default is deliberately the timid one. Resuming agents unattended
+//! seconds after a reboot is a foot-gun, so `auto` is opted into per host and
+//! `never` throws the sidecars away instead.
+
+mod common;
+
+use std::collections::HashMap;
+use std::sync::Arc;
+use std::time::Duration;
+
+use common::{wait_for_async, DaemonFixture};
+use maestro_config::ResumeOnBoot;
+use maestro_daemon::SessionManager;
+use maestro_protocol::{CreateSessionRequest, Session, SessionStatus, SpawnPreset};
+use tempfile::TempDir;
+
+/// A fresh manager over the same tmux server, sidecars and fifos — what the
+/// daemon builds after a restart — carrying `policy`.
+fn revive(fx: &DaemonFixture, policy: ResumeOnBoot, presets: Vec<SpawnPreset>) -> SessionManager {
+    SessionManager::new(
+        Arc::new(fx.tmux.tmux.clone()),
+        maestro_daemon::sidecar::SidecarStore::new(fx.sidecar_dir()),
+        maestro_daemon::worktree::WorktreeManager::new(None),
+        fx.fifo_dir(),
+    )
+    .with_resume_policy(policy, presets)
+}
+
+/// A preset whose `resume_command` touches a marker file, so a test can see
+/// that the resumed session ran the resume command rather than the original.
+fn marker_preset(command: &str, marker_dir: &TempDir) -> Vec<SpawnPreset> {
+    vec![SpawnPreset {
+        id: "agent".into(),
+        label: "Agent".into(),
+        command: command.into(),
+        resume_command: Some(format!(
+            "sh -c 'touch {}/resumed; sleep 30'",
+            marker_dir.path().display()
+        )),
+    }]
+}
+
+async fn create(fx: &DaemonFixture, cwd: &TempDir, command: &str) -> Session {
+    fx.manager
+        .create(CreateSessionRequest {
+            cwd: cwd.path().to_path_buf(),
+            command: command.into(),
+            env: HashMap::new(),
+            metadata: HashMap::new(),
+            worktree: None,
+        })
+        .await
+        .expect("create")
+}
+
+/// The default: a reboot leaves the session listed but not running, waiting
+/// for the operator.
+#[tokio::test]
+async fn dormant_is_the_default_and_leaves_the_session_waiting() {
+    let fx = DaemonFixture::new();
+    let cwd = TempDir::new().unwrap();
+    let session = create(&fx, &cwd, "sleep 30").await;
+    fx.tmux.tmux.kill_server().expect("kill tmux server");
+
+    let revived = revive(&fx, ResumeOnBoot::Dormant, Vec::new());
+    revived.recover().await.expect("recover");
+
+    assert_eq!(
+        revived.status(session.id).await,
+        Some(SessionStatus::Dormant)
+    );
+    assert!(fx
+        .sidecar_dir()
+        .join(format!("{}.json", session.id))
+        .exists());
+    assert!(
+        fx.tmux.tmux.list_sessions().expect("list").is_empty(),
+        "nothing was respawned"
+    );
+}
+
+/// `auto` brings each one back itself, down the same path a client's resume
+/// takes: same uuid, same sidecar, the preset's `resume_command`.
+#[tokio::test]
+async fn auto_resumes_every_dormant_session_during_recovery() {
+    let fx = DaemonFixture::new();
+    let cwd = TempDir::new().unwrap();
+    let markers = TempDir::new().unwrap();
+    let session = create(&fx, &cwd, "sleep 30").await;
+    fx.tmux.tmux.kill_server().expect("kill tmux server");
+
+    let revived = revive(&fx, ResumeOnBoot::Auto, marker_preset("sleep 30", &markers));
+    revived.recover().await.expect("recover");
+
+    assert_eq!(
+        revived.status(session.id).await,
+        Some(SessionStatus::Running),
+        "auto resumed it"
+    );
+    assert_eq!(
+        fx.tmux.tmux.list_sessions().expect("list"),
+        vec![session.id],
+        "back under the same uuid"
+    );
+    let stored = maestro_daemon::sidecar::SidecarStore::new(fx.sidecar_dir())
+        .read(session.id)
+        .expect("read sidecar")
+        .expect("same sidecar");
+    assert_eq!(stored.created_at, session.created_at);
+    assert_eq!(stored.command, "sleep 30", "the original command is kept");
+
+    // It really ran the preset's resume command, not the spawn command.
+    let marker = markers.path().join("resumed");
+    wait_for_async(Duration::from_secs(5), || {
+        let marker = marker.clone();
+        async move { marker.exists() }
+    })
+    .await;
+    assert!(marker.exists(), "resume_command ran");
+}
+
+/// `never` makes a reboot a clean slate: the sidecars go, and the session is
+/// not listed at all.
+#[tokio::test]
+async fn never_prunes_the_sidecars_instead() {
+    let fx = DaemonFixture::new();
+    let cwd = TempDir::new().unwrap();
+    let session = create(&fx, &cwd, "sleep 30").await;
+    fx.tmux.tmux.kill_server().expect("kill tmux server");
+
+    let revived = revive(&fx, ResumeOnBoot::Never, Vec::new());
+    revived.recover().await.expect("recover");
+
+    assert!(!revived.has(session.id).await, "not listed");
+    assert!(
+        !fx.sidecar_dir()
+            .join(format!("{}.json", session.id))
+            .exists(),
+        "sidecar pruned"
+    );
+    assert!(fx.tmux.tmux.list_sessions().expect("list").is_empty());
+}
+
+/// The policy only decides what happens to sessions that lost their pane. A
+/// session tmux still holds is adopted running by the first pass under every
+/// policy — including `never`, which must not delete a live session's sidecar.
+#[tokio::test]
+async fn the_policy_leaves_sessions_tmux_still_holds_alone() {
+    let fx = DaemonFixture::new();
+    let cwd = TempDir::new().unwrap();
+    let live = create(&fx, &cwd, "sleep 30").await;
+
+    let revived = revive(&fx, ResumeOnBoot::Never, Vec::new());
+    assert_eq!(revived.recover().await.expect("recover"), 1);
+
+    assert_eq!(revived.status(live.id).await, Some(SessionStatus::Running));
+    assert!(fx.sidecar_dir().join(format!("{}.json", live.id)).exists());
+}

crates/maestro-daemon/tests/session_manager.rs

@@ -9,6 +9,7 @@ use std::sync::Arc;
 use std::time::Duration;
 
 use common::{init_bare_repo, init_repo, push_all_to_origin, wait_for_async, DaemonFixture};
+use maestro_daemon::sidecar::SidecarStore;
 use maestro_daemon::SessionError;
 use maestro_protocol::CreateSessionRequest;
 use maestro_protocol::{CatalogEvent, SessionStatus, WorktreeSpec};
@@ -325,12 +326,14 @@ fn revive_with_boot_id(
     )
 }
 
-/// #164: a changed boot id means every session from the previous boot is
-/// already dead, so recovery must not trust tmux to say so — it skips the
-/// probe outright. Proven by leaving the tmux session alive: if the probe
-/// ran, it would come back `Running`, not `Dormant`.
+/// #174: a boot id can change without the tmux server dying — a restored
+/// state directory, a VM or container snapshot restore, a truncated
+/// `boot_id` file. `tmux list-sessions` stays the single source of truth for
+/// liveness, so a session tmux still holds is adopted `Running` no matter
+/// what the boot id says. Registering it dormant instead stranded it: resume
+/// would collide with the tmux name still in use and fail forever.
 #[tokio::test]
-async fn recover_skips_tmux_probe_when_boot_id_changed() {
+async fn recover_adopts_live_session_when_boot_id_changed() {
     let fx = DaemonFixture::new();
     let cwd = TempDir::new().unwrap();
     let s = fx
@@ -348,15 +351,15 @@ async fn recover_skips_tmux_probe_when_boot_id_changed() {
     let boot_id_path = fx.state_dir.path().join("boot_id");
     std::fs::write(&boot_id_path, "previous-boot").unwrap();
 
-    // tmux session is still alive — a probe would find it if one ran.
+    // tmux session is still alive: the probe runs and finds it.
     let revived = revive_with_boot_id(&fx, boot_id_path.clone(), Some("current-boot"));
     let adopted = revived.recover().await.expect("recover");
-    assert_eq!(adopted, 0, "reboot detected: nothing adopted live");
+    assert_eq!(adopted, 1, "tmux still holds the session; adopt it");
 
     let snap = revived.snapshot().await;
     assert_eq!(snap.len(), 1);
     assert_eq!(snap[0].id, s.id);
-    assert_eq!(snap[0].status, SessionStatus::Dormant);
+    assert_eq!(snap[0].status, SessionStatus::Running);
 
     // The current boot id is now the stored one, for the next comparison.
     assert_eq!(
@@ -365,6 +368,38 @@ async fn recover_skips_tmux_probe_when_boot_id_changed() {
     );
 }
 
+/// #164, still true after #174: a real reboot takes the tmux server with it,
+/// so the probe comes back empty and every sidecar is registered dormant.
+#[tokio::test]
+async fn recover_registers_dormant_when_boot_id_changed_and_tmux_gone() {
+    let fx = DaemonFixture::new();
+    let cwd = TempDir::new().unwrap();
+    let s = fx
+        .manager
+        .create(CreateSessionRequest {
+            cwd: cwd.path().to_path_buf(),
+            command: "sleep 30".into(),
+            env: HashMap::new(),
+            metadata: HashMap::new(),
+            worktree: None,
+        })
+        .await
+        .expect("create");
+
+    let boot_id_path = fx.state_dir.path().join("boot_id");
+    std::fs::write(&boot_id_path, "previous-boot").unwrap();
+    fx.tmux.tmux.kill_server().expect("kill tmux server");
+
+    let revived = revive_with_boot_id(&fx, boot_id_path, Some("current-boot"));
+    let adopted = revived.recover().await.expect("recover");
+    assert_eq!(adopted, 0, "no tmux server survived the reboot");
+
+    let snap = revived.snapshot().await;
+    assert_eq!(snap.len(), 1);
+    assert_eq!(snap[0].id, s.id);
+    assert_eq!(snap[0].status, SessionStatus::Dormant);
+}
+
 /// #164: an unchanged boot id is a plain restart — recovery probes tmux as
 /// before and adopts the still-live session `Running`.
 #[tokio::test]
@@ -1304,6 +1339,65 @@ async fn natural_exit_of_a_pristine_worktree_removes_it() {
     );
 }
 
+/// #172: `mark_session_dead` clears the worktree off the in-memory record
+/// when a pristine tree settles, but the local `session` clone it writes to
+/// the sidecar and broadcasts must be cleared the same way — otherwise the
+/// sidecar keeps naming a tree the daemon just removed, and a recovery from
+/// that sidecar advertises a branch and path that no longer exist.
+#[tokio::test]
+async fn natural_exit_of_a_pristine_worktree_clears_it_from_the_sidecar() {
+    let fx = DaemonFixture::new();
+    let repo = TempDir::new().unwrap();
+    init_repo(repo.path());
+    let wt_path = repo.path().join("worktrees").join("feat").join("sidecar");
+
+    let s = fx
+        .manager
+        .create(CreateSessionRequest {
+            cwd: repo.path().to_path_buf(),
+            command: "sleep 30".into(),
+            env: HashMap::new(),
+            metadata: HashMap::new(),
+            worktree: Some(WorktreeSpec {
+                base_repo: repo.path().to_path_buf(),
+                branch: "feat/sidecar".into(),
+                create_branch: true,
+            }),
+        })
+        .await
+        .expect("create");
+
+    // Push everything so the branch has no unpushed commits: fully pristine.
+    let origin = TempDir::new().unwrap();
+    init_bare_repo(origin.path());
+    push_all_to_origin(repo.path(), origin.path());
+
+    fx.tmux.tmux.kill_session(s.id).expect("kill tmux directly");
+    fx.manager.start_liveness_watcher(Duration::from_millis(50));
+    wait_for_async(Duration::from_secs(3), || async {
+        fx.manager.status(s.id).await == Some(SessionStatus::Dead)
+    })
+    .await;
+    wait_for_async(Duration::from_secs(3), || async {
+        fx.manager.is_settled(s.id).await == Some(true)
+    })
+    .await;
+
+    assert!(
+        !wt_path.exists(),
+        "a pristine worktree leaves nothing behind"
+    );
+
+    let sidecar = SidecarStore::new(fx.sidecar_dir())
+        .read(s.id)
+        .expect("sidecar read")
+        .expect("sidecar exists");
+    assert!(
+        sidecar.worktree.is_none(),
+        "the sidecar must not keep naming a worktree the daemon already removed"
+    );
+}
+
 fn run_git_in(dir: &std::path::Path, args: &[&str]) {
     let out = Command::new("git")
         .arg("-C")

docs/INSTALL.md

@@ -243,6 +243,26 @@ Pick `/tmp` if the daemon must outlive your login session and you can't run
 tmux sockets with it). The env var `MAESTRO_DAEMON_TMUX_TMPDIR` takes
 precedence over the file.
 
+## What happens to sessions after a reboot
+
+A host reboot kills the tmux server, so every session the daemon knew is dead
+while its record on disk survives. What recovery does with those is
+`[daemon].resume_on_boot`:
+
+```toml
+[daemon]
+resume_on_boot = "dormant"   # "dormant" (default) | "auto" | "never"
+```
+
+- `dormant` — the sessions are listed but not running, and you resume the ones
+  you want from the web UI or the TUI.
+- `auto` — the daemon resumes them all itself during startup. Only pick this
+  on a host where restarting every agent unattended is safe: they come back on
+  the flags they were spawned with, with nobody watching.
+- `never` — the records are deleted and a reboot is a clean slate.
+
+See `docs/RESTART.md` for the full contract.
+
 ## What the systemd unit looks like
 
 The wizard writes a *user* unit (`systemctl --user`), since `maestro daemon`

docs/PREVIEW.md

@@ -47,6 +47,7 @@ Web client (`--preview` and friends in `web/src/styles.css`):
 | The canvas | A `preview` chip, top right, and a dashed inset ring. |
 | A throwaway tab | Dashed border, italic label. |
 | The sidebar row being previewed | Filled with the preview hue, over whatever open state the row already had — but the row of the session already showing in the pane keeps its accent fill, since previewing it changes nothing on screen. |
+| The sidebar row of the session the operator picked | Keeps its accent fill for the whole preview. A preview never moves the accent; only opening another session does. |
 | A hovered sidebar row, and the keyboard cursor on a session | A lighter wash of the same hue, because both are what previews a row. |
 
 Rows say it with fill, not with an edge — see the tier ladder in

docs/RESTART.md

@@ -75,7 +75,13 @@ A daemon restart leaves tmux alone, so recovery re-adopts every
 beyond the reconnect above.
 
 A **host reboot** is different: it kills the tmux server, so there is nothing
-to adopt while every session's sidecar is still on disk. Recovery makes a
+to adopt while every session's sidecar is still on disk. Recovery always asks
+tmux — `tmux list-sessions` is the single source of truth for liveness, and the
+kernel's `boot_id` only tells a reboot from a restart in the log (#164, #174).
+A boot id changes without the tmux server dying whenever the state directory is
+restored, a VM or container snapshot is rolled back, or the `boot_id` file is
+truncated; a session tmux still holds is adopted `Running` in every one of
+those cases. Recovery makes a
 second pass over those sidecars and registers each as a `Dormant` session
 (#162) — id, name, cwd, command, worktree and `created_at` intact. A dormant
 session has no pane and no PTY bridge: it cannot be attached to, typed into or
@@ -96,6 +102,38 @@ neither is something a respawn could fix. The other thing to do with a dormant
 session is dismiss it, which removes the sidecar so the next recovery does not
 bring it back.
 
+## What recovery does with them: `resume_on_boot`
+
+Whether a recovered-but-dead session is left dormant at all is the operator's
+call, per host, via `[daemon].resume_on_boot` (#167):
+
+| value       | what recovery does                                                    |
+| ----------- | --------------------------------------------------------------------- |
+| `"dormant"` | **Default.** Register each one dormant and wait for the operator.      |
+| `"auto"`    | Resume each one during recovery, itself.                               |
+| `"never"`   | Prune the sidecars instead — a reboot is a clean slate.                |
+
+`dormant` is the default because resuming agents unattended is a foot-gun:
+they come back on whatever flags they were spawned with, seconds after a
+reboot, with nobody watching. `auto` exists for hosts where that is known to
+be safe, and it is opted into rather than inherited.
+
+`auto` calls the same `resume` the client's `POST /api/sessions/:id/resume`
+does — same uuid, same sidecar, the preset's `resume_command` — so there is
+one resume path and not two. A session that fails to resume is logged and
+stays dormant; the rest still come back.
+
+`never` prunes the same way #163 does for a missing `cwd`: the sidecar is
+deleted and nothing is registered, so the session is not listed and the next
+recovery does not find it. Whatever worktree it owned is left on disk.
+
+The policy only decides the fate of sessions with no live pane. A session
+tmux still holds is adopted `Running` by the first pass under every policy,
+including `never`.
+
+Recovery logs the policy that ran and the number of sessions it acted on, so
+a host that resumes agents unattended says so in its own journal.
+
 Attaching to a session that has no bridge answers `409 not_attachable`, not
 `404 unknown_session`: the session exists, and a client that cannot tell "gone"
 from "not running" cannot offer the resume.

web/src/fastForward.test.ts

@@ -34,12 +34,14 @@ describe("resolveFastForward (#67)", () => {
     const res = resolveFastForward(projects, presets, "amber-falcon");
     expect(res.project?.path).toBe("/repos/fresh");
     expect(res.command).toBe("aider");
-    expect(res.name).toBe("amber-falcon");
+    expect(res.handle).toBe("amber-falcon");
 
     const req = buildFastForwardRequest(res)!;
     expect(req.cwd).toBe("/repos/fresh");
     expect(req.command).toBe("aider");
-    expect(req.metadata).toEqual({ name: "amber-falcon" });
+    // No name (#131): the daemon names the session after its first prompt,
+    // and a name here would collide with the branch handle.
+    expect(req.metadata).toBeUndefined();
     expect(req.worktree).toEqual({
       base_repo: "/repos/fresh",
       branch: "amber-falcon",
@@ -88,9 +90,9 @@ describe("resolveFastForward (#67)", () => {
     expect(buildFastForwardRequest(res)).toBeNull();
   });
 
-  it("downgrades to a draft when the generated name is missing", () => {
+  it("downgrades to a draft when the generated handle is missing", () => {
     const res = resolveFastForward([project({ last_command: "claude" })], presets);
-    expect(res.name).toBeUndefined();
+    expect(res.handle).toBeUndefined();
     expect(buildFastForwardRequest(res)).toBeNull();
   });
 
@@ -108,6 +110,17 @@ describe("resolveFastForward (#67)", () => {
     });
   });
 
+  it("seeds the handle as the branch and leaves the name field empty (#131)", () => {
+    const res = resolveFastForward(
+      [project({ path: "/repos/p", base_repo: "/repos/p", last_command: "aider" })],
+      presets,
+      "amber-falcon",
+    );
+    const seed = fastForwardSeed(res);
+    expect(seed.name).toBe("");
+    expect(seed.worktreeBranch).toBe("amber-falcon");
+  });
+
   it("leaves the worktree default alone when not even a project resolved", () => {
     // Not `false`: the form defaults the toggle on and a false would stick,
     // so the fallback draft would disagree with a normally-opened draft and

web/src/fastForward.ts

@@ -10,19 +10,21 @@ import { sortProjects } from "./projectList.js";
 export interface FastForwardResolution {
   project?: Project;
   command?: string;
-  name?: string;
+  /** A generated handle for the worktree branch (#131). Not a session name:
+   *  the fast path names no session. */
+  handle?: string;
 }
 
 /** The defaults: the currently focused session's project when it's still a
  *  known project, else the most recent one (fresh-first, same ordering the
  *  picker shows) — so `N` lands where the operator currently is, matching
  *  what plain `n` seeds from `spawnSimilarProjectSeed`. Its last command
- *  falls back to the first non-custom preset, and the name is freshly
- *  generated when the daemon supplied one. */
+ *  falls back to the first non-custom preset, and the branch handle is
+ *  freshly generated when the daemon supplied one. */
 export function resolveFastForward(
   projects: Project[],
   presets: SpawnPreset[],
-  name?: string,
+  handle?: string,
   focusedCwd?: string,
 ): FastForwardResolution {
   const project =
@@ -30,41 +32,45 @@ export function resolveFastForward(
   const lastCommand = project?.last_command?.trim();
   const command =
     lastCommand || presets.find((p) => p.command !== "")?.command || undefined;
-  return { project, command, name: name || undefined };
+  return { project, command, handle: handle || undefined };
 }
 
 /** The immediate spawn request — worktree on, new branch named after the
- *  generated session name — or `null` when any default is missing. */
+ *  generated handle — or `null` when any default is missing.
+ *
+ *  The request carries no name (#131): the daemon assigns a provisional one
+ *  and replaces it once the session sees its first prompt. A name here would
+ *  also collide with the branch handle's own session. */
 export function buildFastForwardRequest(
   res: FastForwardResolution,
 ): CreateSessionRequest | null {
-  const { project, command, name } = res;
-  if (!project || !command?.trim() || !name) return null;
+  const { project, command, handle } = res;
+  if (!project || !command?.trim() || !handle) return null;
   return {
     cwd: project.path,
     command,
-    metadata: { name },
     worktree: {
       base_repo: project.base_repo ?? project.path,
-      branch: name,
+      branch: handle,
       create_branch: true,
     },
   };
 }
 
 /** Seed for the fallback spawn form: whatever did resolve goes into the
- *  form; the rest stays with its own defaults. */
+ *  form; the rest stays with its own defaults. The name field stays empty
+ *  (#131) — the handle seeds the branch, not the session name. */
 export function fastForwardSeed(res: FastForwardResolution) {
   return {
     cwd: res.project?.path ?? "",
     command: res.command ?? "",
-    name: res.name ?? "",
+    name: "",
     // Left undefined rather than false when nothing resolved: the form
     // defaults the toggle on, and `false` would stick, so the fallback form
     // would disagree with both a normally-opened form and the TUI's fast path
     // (#67 review).
     worktreeEnabled: res.project ? true : undefined,
     worktreeBranch:
-      res.project && res.name ? res.name : undefined,
+      res.project && res.handle ? res.handle : undefined,
   };
 }

web/src/main.ts

@@ -356,14 +356,14 @@ async function spawnPresets(): Promise<SpawnPreset[]> {
 }
 
 async function requestFastForward(): Promise<void> {
-  const [discovered, name] = await Promise.all([
+  const [discovered, handle] = await Promise.all([
     fetchProjects().catch(() => [] as Project[]),
     fetchNames(1)
       .then((batch) => batch.names[0])
       .catch(() => undefined),
   ]);
   const presets = await spawnPresets();
-  const resolved = resolveFastForward(discovered, presets, name, focusedProjectCwd());
+  const resolved = resolveFastForward(discovered, presets, handle, focusedProjectCwd());
   const req = buildFastForwardRequest(resolved);
   if (req) {
     try {
@@ -390,7 +390,7 @@ async function requestFastForward(): Promise<void> {
 // one outside any repo spawns without a worktree, since there is no repo to cut
 // a branch from. Anything still unresolved opens the pre-filled form.
 async function requestSpawnInDirectory(path: string): Promise<void> {
-  const [discovered, name] = await Promise.all([
+  const [discovered, handle] = await Promise.all([
     fetchProjects().catch(() => [] as Project[]),
     fetchNames(1)
       .then((batch) => batch.names[0])
@@ -399,7 +399,7 @@ async function requestSpawnInDirectory(path: string): Promise<void> {
   const presets = await spawnPresets();
   const known = discovered.find((p) => p.path === path);
   const project: Project = known ?? { path, name: path.split("/").filter(Boolean).pop() ?? path };
-  const resolved = resolveFastForward([project], presets, name, path);
+  const resolved = resolveFastForward([project], presets, handle, path);
   const req = buildFastForwardRequest(resolved);
   if (req) {
     const inRepo =

web/src/multiview.ts

@@ -215,6 +215,20 @@ export function createMultiView(opts: MultiViewOptions): MultiView {
     return fl?.sessionId ?? null;
   }
 
+  /** The session the operator actually picked — what `focusedLeafSession()`
+   *  would return with the preview undone. A preview moves the active tab and
+   *  its focus, but it is a view: the accent stays on the row the operator
+   *  chose until they choose another (docs/PREVIEW.md). */
+  function realFocusedSession(): string | null {
+    const p = preview;
+    if (!p) return focusedLeafSession();
+    const tab = layout.tabs.find((t) => t.id === p.prevActiveTabId) ?? activeTab(layout);
+    const leafId =
+      p.prevFocus && p.prevFocus.tabId === tab.id ? p.prevFocus.leafId : tab.focusedLeafId;
+    const fl = leafId ? findLeaf(tab.root, leafId) : null;
+    return fl?.sessionId ?? null;
+  }
+
   /** Update focus styling + pool focus + sidebar highlights without rebuilding
    *  the DOM (cheap path for click-to-focus). */
   function syncFocus(): void {
@@ -233,7 +247,7 @@ export function createMultiView(opts: MultiViewOptions): MultiView {
     if (!preview) pool.setFocus(focusedLeafSession());
     sidebar.setHighlights({
       open: realOpenSessions(),
-      focused: focusedLeafSession(),
+      focused: realFocusedSession(),
     });
     // The row the preview came from wears the same colour, so the sidebar and
     // the pane read as one thing rather than two unrelated highlights.
@@ -608,7 +622,7 @@ export function createMultiView(opts: MultiViewOptions): MultiView {
       { focus: !preview && !quietRender },
     );
     if (!preview) pool.setFocus(focused.sessionId ?? null);
-    sidebar.setHighlights({ open: realOpenSessions(), focused: focused.sessionId ?? null });
+    sidebar.setHighlights({ open: realOpenSessions(), focused: realFocusedSession() });
     sidebar.setPreview(preview?.sessionId ?? null);
   }
 
@@ -817,7 +831,7 @@ export function createMultiView(opts: MultiViewOptions): MultiView {
     openSessions: realOpenSessions,
     beginSessionDrag,
     render,
-    focusedSessionId: focusedLeafSession,
+    focusedSessionId: realFocusedSession,
     previewSession,
     previewedSessionId: () => preview?.sessionId ?? null,
   };

web/src/preview.test.ts

@@ -47,12 +47,20 @@ function fakePool(): Spy {
 
 /** Last value the controller pushed to `SidebarHandle.setPreview`. */
 const previewRow: { id: string | null } = { id: null };
+/** Last highlights the controller pushed to `SidebarHandle.setHighlights`. */
+const rowHighlights: { open: Set<string>; focused: string | null } = {
+  open: new Set(),
+  focused: null,
+};
 
 function fakeSidebar(): SidebarHandle {
   return {
     el: document.createElement("aside"),
     setActive() {},
-    setHighlights() {},
+    setHighlights(h) {
+      rowHighlights.open = h.open;
+      rowHighlights.focused = h.focused;
+    },
     setPreview(id: string | null) {
       previewRow.id = id;
     },
@@ -95,6 +103,8 @@ describe("sidebar preview", () => {
     stubFetch();
     document.body.replaceChildren();
     previewRow.id = null;
+    rowHighlights.open = new Set();
+    rowHighlights.focused = null;
   });
 
   afterEach(() => {
@@ -134,6 +144,28 @@ describe("sidebar preview", () => {
     expect(mv.el.querySelectorAll(".mv-pane.is-preview")).toHaveLength(0);
   });
 
+  it("leaves the accent on the session the pane actually holds", () => {
+    const layout = twoTabs();
+    const spy = fakePool();
+    const mv = makeMv(layout, spy.pool);
+    expect(rowHighlights.focused).toBe("s2");
+
+    // Walking past other rows never moves the accent off what the operator
+    // picked: only a real open does (docs/PREVIEW.md).
+    mv.previewSession("s1");
+    expect(rowHighlights.focused).toBe("s2");
+    expect(mv.focusedSessionId()).toBe("s2");
+
+    mv.previewSession("s9");
+    expect(rowHighlights.focused).toBe("s2");
+
+    mv.previewSession(null);
+    expect(rowHighlights.focused).toBe("s2");
+
+    mv.openSession("s1");
+    expect(rowHighlights.focused).toBe("s1");
+  });
+
   it("shows a session no pane holds in a throwaway tab that leaves no trace", () => {
     const layout = twoTabs();
     const before = serializeLayout(layout);