fix(maestro): replace agent_session_id when a report names a new one

A resume issues a new conversation id, so write-once left the stored id
pointing at the pre-resume conversation and every later resume reattached
it. Rewrite the sidecar when the reported id differs from the stored one;
a repeated report of the same id still writes nothing.

Closes #176

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,
@@ -86,6 +87,11 @@ pub struct SessionRecord {
     /// (`POST /.../focus`), `None` while unfocused. Daemon-local; never rides
     /// the wire.
     pub focused_since: Option<std::time::Instant>,
+    /// Set for as long as a [`SessionManager::resume`] is between its two
+    /// takes of the map lock (#175). The spawn happens with the lock released,
+    /// so the `Running` check alone lets a second request through; this is the
+    /// state the second one is refused on. Daemon-local; never rides the wire.
+    pub resuming: bool,
     /// Sticky acknowledgement applied by [`crate::activity::apply_focus_suppression`]:
     /// once the pane has been focused long enough to clear an `AwaitingInput`
     /// glow, this holds through focus loss until the session does new work.
@@ -195,6 +201,11 @@ 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 +264,8 @@ 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 +310,26 @@ 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
@@ -567,6 +600,7 @@ impl SessionManager {
                     naming: false,
                     focused_since: None,
                     awaiting_suppressed: false,
+                    resuming: false,
                 },
             );
         }
@@ -618,15 +652,23 @@ impl SessionManager {
         id: Uuid,
         presets: &[maestro_protocol::SpawnPreset],
     ) -> Result<Session, SessionError> {
+        // The spawn below runs with the map lock released, so the `Running`
+        // check alone is not enough to keep two resumes apart (#175): both
+        // would pass it, both would open a `PtyBridge` on the same FIFO, and
+        // the loser would report a tmux failure instead of the conflict it
+        // is. The record is marked in-flight under this first lock, and every
+        // path out of here clears it again.
         let mut session = {
-            let sessions = self.inner.sessions.lock().await;
-            let rec = sessions.get(&id).ok_or(SessionError::NotFound(id))?;
-            if rec.session.status == SessionStatus::Running {
+            let mut sessions = self.inner.sessions.lock().await;
+            let rec = sessions.get_mut(&id).ok_or(SessionError::NotFound(id))?;
+            if rec.session.status == SessionStatus::Running || rec.resuming {
                 return Err(SessionError::AlreadyRunning(id));
             }
+            rec.resuming = true;
             rec.session.clone()
         };
         if !session.cwd.exists() {
+            self.clear_resuming(id).await;
             return Err(SessionError::CwdMissing(session.cwd.clone()));
         }
         let command = crate::resume::resume_command(&session, presets);
@@ -658,6 +700,7 @@ impl SessionManager {
         if let Err(e) = spawned {
             // `bridge` drops here, closing the FIFO reader. Nothing else was
             // touched, so the session stays exactly as dormant as it was.
+            self.clear_resuming(id).await;
             return Err(SessionError::Tmux(e));
         }
 
@@ -677,6 +720,7 @@ impl SessionManager {
             // sidecar does not describe.
             let tmux = self.inner.tmux.clone();
             let _ = tmux_blocking(move || tmux.kill_session(id)).await;
+            self.clear_resuming(id).await;
             return Err(SessionError::Sidecar(e));
         }
 
@@ -684,9 +728,17 @@ impl SessionManager {
             let mut sessions = self.inner.sessions.lock().await;
             let Some(rec) = sessions.get_mut(&id) else {
                 // Killed while we were spawning. Undo the pane instead of
-                // leaving one behind with no record of it.
+                // leaving one behind with no record of it — and delete the
+                // sidecar the write above just put back (#175). The kill
+                // deleted it before that write landed, so leaving it would
+                // have the next recovery register a dormant ghost for a
+                // session that is gone and whose worktree is already removed.
+                drop(sessions);
                 let tmux = self.inner.tmux.clone();
                 let _ = tmux_blocking(move || tmux.kill_session(id)).await;
+                if let Err(e) = self.inner.sidecar.delete(id) {
+                    tracing::warn!(error = ?e, %id, "resume: failed to delete the sidecar of a session killed mid-resume");
+                }
                 return Err(SessionError::NotFound(id));
             };
             rec.session = session.clone();
@@ -696,6 +748,7 @@ impl SessionManager {
             rec.settled = false;
             rec.focused_since = None;
             rec.awaiting_suppressed = false;
+            rec.resuming = false;
         }
         let _ = self.inner.events.send(CatalogEvent::SessionUpdated {
             session: session.clone(),
@@ -703,6 +756,16 @@ impl SessionManager {
         Ok(session)
     }
 
+    /// Drop the in-flight marker [`Self::resume`] set under its first lock
+    /// (#175), so a refused or failed resume can be retried. A no-op when the
+    /// record is already gone: a kill that landed mid-resume took the marker
+    /// with it.
+    async fn clear_resuming(&self, id: Uuid) {
+        if let Some(rec) = self.inner.sessions.lock().await.get_mut(&id) {
+            rec.resuming = false;
+        }
+    }
+
     /// Best-effort removal of a worktree created earlier in `create` when a
     /// later step fails. No-op when the request had no worktree.
     fn rollback_worktree(&self, base: &Option<PathBuf>, path: &Option<PathBuf>) {
@@ -819,20 +882,20 @@ 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?
         };
@@ -894,6 +957,7 @@ impl SessionManager {
                     naming: false,
                     focused_since: None,
                     awaiting_suppressed: false,
+                    resuming: false,
                 },
             );
             let _ = self
@@ -912,7 +976,9 @@ 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 +1025,8 @@ 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 +1037,7 @@ 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 +1052,16 @@ 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;
@@ -1006,6 +1084,7 @@ impl SessionManager {
                         naming: false,
                         focused_since: None,
                         awaiting_suppressed: false,
+                        resuming: false,
                     },
                 );
                 registered.push(session);
@@ -1025,12 +1104,45 @@ 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
@@ -1193,10 +1305,12 @@ impl SessionManager {
     /// and stays silent on the event stream at steady state.
     ///
     /// `agent_session_id` (#161) is the agent's own conversation id, parsed
-    /// by the caller from the hook payload's `session_id` field. It is
-    /// written once — the first report that carries one wins — and the
-    /// sidecar is only rewritten on that transition, never on every report,
-    /// since an agent's session id never changes mid-session.
+    /// by the caller from the hook payload's `session_id` field. The
+    /// sidecar is rewritten only when the reported id differs from the
+    /// stored one — a repeated report of the same id is pure churn from the
+    /// hook's `PreToolUse` cadence and writes nothing, but a resume (#176)
+    /// issues a new conversation id and must replace the stale one, or
+    /// every later resume reattaches the pre-resume conversation.
     pub async fn report_activity(
         &self,
         id: Uuid,
@@ -1218,16 +1332,16 @@ impl SessionManager {
                 state,
                 self.inner.report_ttl,
             ));
-            let newly_identified =
-                rec.session.agent_session_id.is_none() && agent_session_id.is_some();
-            if newly_identified {
+            let id_changed =
+                agent_session_id.is_some() && rec.session.agent_session_id != agent_session_id;
+            if id_changed {
                 rec.session.agent_session_id = agent_session_id;
                 self.inner
                     .sidecar
                     .write(&rec.session)
                     .map_err(SessionError::Sidecar)?;
             }
-            (changed || newly_identified).then(|| rec.session.clone())
+            (changed || id_changed).then(|| rec.session.clone())
         };
         if let Some(session) = updated {
             let _ = self

crates/maestro-daemon/tests/activity_report.rs

@@ -187,10 +187,30 @@ async fn a_reported_session_id_is_recorded_on_the_session() {
     assert_eq!(s.agent_session_id.as_deref(), Some("conv-abc123"));
 }
 
-/// #161: a session id does not change mid-session, so once set it is never
-/// overwritten by a later report — even one that names a different id.
+/// #161: repeated reports of the same id are pure churn from the hook's
+/// `PreToolUse` cadence — the sidecar must not be rewritten for them.
 #[tokio::test]
-async fn a_reported_session_id_is_written_once_and_never_replaced() {
+async fn a_repeated_report_of_the_same_session_id_writes_nothing() {
+    let fx = fixture(Duration::from_secs(300)).await;
+    let id = spawn_sleeping(&fx.manager).await;
+
+    fx.manager
+        .report_activity(id, ActivityState::Active, None, Some("conv-first".into()))
+        .await
+        .unwrap();
+    fx.manager
+        .report_activity(id, ActivityState::Active, None, Some("conv-first".into()))
+        .await
+        .unwrap();
+
+    let s = observed(&fx.manager, id).await;
+    assert_eq!(s.agent_session_id.as_deref(), Some("conv-first"));
+}
+
+/// #176: a resume issues a new conversation id. The stored id must move to
+/// it, or every later resume reattaches the stale pre-resume conversation.
+#[tokio::test]
+async fn a_reported_session_id_is_replaced_when_it_differs() {
     let fx = fixture(Duration::from_secs(300)).await;
     let id = spawn_sleeping(&fx.manager).await;
 
@@ -204,7 +224,14 @@ async fn a_reported_session_id_is_written_once_and_never_replaced() {
         .unwrap();
 
     let s = observed(&fx.manager, id).await;
-    assert_eq!(s.agent_session_id.as_deref(), Some("conv-first"));
+    assert_eq!(s.agent_session_id.as_deref(), Some("conv-second"));
+
+    let stored = fx
+        .sidecar
+        .read(id)
+        .expect("sidecar read")
+        .expect("sidecar present");
+    assert_eq!(stored.agent_session_id.as_deref(), Some("conv-second"));
 }
 
 #[tokio::test]

crates/maestro-daemon/tests/resume.rs

@@ -357,3 +357,237 @@ async fn post_resume_on_an_unknown_session_is_404() {
         .unwrap();
     assert_eq!(resp.status(), reqwest::StatusCode::NOT_FOUND);
 }
+
+// ---------------------------------------------------------------------------
+// Races (#175)
+// ---------------------------------------------------------------------------
+
+/// Real tmux, with the *first* `new_session_piped` held inside the call until
+/// the test releases it. Later calls pass straight through, so a second resume
+/// racing the first never blocks on a gate the first one owns.
+///
+/// This is what makes the two races below deterministic rather than timing
+/// dependent: the resume under test is parked in exactly the window the bug
+/// lives in, and the racing operation runs to completion before it moves.
+#[derive(Debug)]
+struct GatedSpawn {
+    inner: maestro_daemon::tmux::Tmux,
+    entered: tokio::sync::mpsc::UnboundedSender<()>,
+    release: std::sync::Mutex<std::sync::mpsc::Receiver<()>>,
+    gated: std::sync::atomic::AtomicBool,
+}
+
+/// The test's end of a [`GatedSpawn`].
+struct Gate {
+    entered: tokio::sync::mpsc::UnboundedReceiver<()>,
+    release: std::sync::mpsc::SyncSender<()>,
+}
+
+impl Gate {
+    /// Wait until the gated spawn is parked mid-resume.
+    async fn wait_entered(&mut self) {
+        tokio::time::timeout(Duration::from_secs(10), self.entered.recv())
+            .await
+            .expect("resume reached the tmux spawn")
+            .expect("gate alive");
+    }
+
+    fn release(&self) {
+        self.release.send(()).expect("gate receiver alive");
+    }
+}
+
+fn gated_panes(inner: maestro_daemon::tmux::Tmux) -> (Arc<GatedSpawn>, Gate) {
+    let (entered_tx, entered_rx) = tokio::sync::mpsc::unbounded_channel();
+    let (release_tx, release_rx) = std::sync::mpsc::sync_channel(1);
+    (
+        Arc::new(GatedSpawn {
+            inner,
+            entered: entered_tx,
+            release: std::sync::Mutex::new(release_rx),
+            gated: std::sync::atomic::AtomicBool::new(true),
+        }),
+        Gate {
+            entered: entered_rx,
+            release: release_tx,
+        },
+    )
+}
+
+impl maestro_daemon::panes::Panes for GatedSpawn {
+    fn new_session_piped(
+        &self,
+        id: Uuid,
+        cwd: &std::path::Path,
+        command: &str,
+        session_env: &std::collections::BTreeMap<String, String>,
+        sink_command: &str,
+    ) -> Result<(), maestro_daemon::tmux::TmuxError> {
+        if self.gated.swap(false, std::sync::atomic::Ordering::SeqCst) {
+            let _ = self.entered.send(());
+            let _ = self.release.lock().expect("gate mutex").recv();
+        }
+        self.inner
+            .new_session_piped(id, cwd, command, session_env, sink_command)
+    }
+
+    fn kill_session(&self, id: Uuid) -> Result<(), maestro_daemon::tmux::TmuxError> {
+        self.inner.kill_session(id)
+    }
+
+    fn list_sessions(&self) -> Result<Vec<Uuid>, maestro_daemon::tmux::TmuxError> {
+        self.inner.list_sessions()
+    }
+
+    fn pane_info(
+        &self,
+        id: Uuid,
+    ) -> Result<Option<maestro_daemon::tmux::PaneInfo>, maestro_daemon::tmux::TmuxError> {
+        self.inner.pane_info(id)
+    }
+
+    fn send_keys(&self, id: Uuid, bytes: &[u8]) -> Result<(), maestro_daemon::tmux::TmuxError> {
+        self.inner.send_keys(id, bytes)
+    }
+
+    fn pipe_pane(&self, id: Uuid, sink: &str) -> Result<(), maestro_daemon::tmux::TmuxError> {
+        self.inner.pipe_pane(id, sink)
+    }
+
+    fn resize_window(
+        &self,
+        id: Uuid,
+        cols: u16,
+        rows: u16,
+    ) -> Result<(), maestro_daemon::tmux::TmuxError> {
+        self.inner.resize_window(id, cols, rows)
+    }
+
+    fn capture_pane(&self, id: Uuid) -> Result<Option<Vec<u8>>, maestro_daemon::tmux::TmuxError> {
+        self.inner.capture_pane(id)
+    }
+}
+
+/// A dormant session whose manager's tmux spawn can be parked by the test.
+async fn dormant_gated(fx: &DaemonFixture, cwd: &TempDir) -> (SessionManager, Session, Gate) {
+    let session = 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");
+    fx.tmux.tmux.kill_server().expect("kill tmux server");
+
+    let (panes, gate) = gated_panes(fx.tmux.tmux.clone());
+    let manager = SessionManager::new(
+        panes,
+        maestro_daemon::sidecar::SidecarStore::new(fx.sidecar_dir()),
+        maestro_daemon::worktree::WorktreeManager::new(None),
+        fx.fifo_dir(),
+    );
+    manager.recover().await.expect("recover");
+    assert_eq!(
+        manager.status(session.id).await,
+        Some(SessionStatus::Dormant)
+    );
+    (manager, session, gate)
+}
+
+/// A kill that lands while a resume is inside the tmux spawn must not leave
+/// the sidecar behind. The kill deletes it; the resume writes it back a moment
+/// later and then discovers its own record is gone. The sidecar it resurrected
+/// would otherwise make the next recovery register a ghost dormant session for
+/// a session that was killed.
+#[tokio::test]
+async fn a_kill_during_resume_leaves_no_sidecar_behind() {
+    let fx = DaemonFixture::new();
+    let cwd = TempDir::new().unwrap();
+    let (manager, session, mut gate) = dormant_gated(&fx, &cwd).await;
+    let id = session.id;
+
+    let resuming = tokio::spawn({
+        let manager = manager.clone();
+        async move { manager.resume(id, &[]).await }
+    });
+    gate.wait_entered().await;
+
+    manager.kill(id, false).await.expect("kill mid-resume");
+    gate.release();
+
+    let err = resuming.await.unwrap().expect_err("record is gone");
+    assert!(matches!(err, SessionError::NotFound(got) if got == id));
+
+    assert!(
+        maestro_daemon::sidecar::SidecarStore::new(fx.sidecar_dir())
+            .read(id)
+            .expect("read sidecar")
+            .is_none(),
+        "the killed session's sidecar must not be resurrected by the losing resume"
+    );
+
+    // And so the next recovery registers no ghost.
+    let after = revive(&fx);
+    after.recover().await.expect("recover");
+    assert!(
+        after.snapshot().await.is_empty(),
+        "a killed session must not come back dormant"
+    );
+}
+
+/// Two resumes of the same session must not both proceed. The second is
+/// refused on the state — `already_running` — not on its tmux spawn colliding
+/// with the first one's.
+#[tokio::test]
+async fn a_second_resume_is_refused_while_the_first_is_in_flight() {
+    let fx = DaemonFixture::new();
+    let cwd = TempDir::new().unwrap();
+    let (manager, session, mut gate) = dormant_gated(&fx, &cwd).await;
+    let id = session.id;
+
+    let resuming = tokio::spawn({
+        let manager = manager.clone();
+        async move { manager.resume(id, &[]).await }
+    });
+    gate.wait_entered().await;
+
+    let err = manager
+        .resume(id, &[])
+        .await
+        .expect_err("a resume is already in flight");
+    assert!(matches!(err, SessionError::AlreadyRunning(got) if got == id));
+    assert_eq!(err.to_error_info().code, "already_running");
+
+    gate.release();
+    let first = resuming.await.unwrap().expect("the first resume wins");
+    assert_eq!(first.status, SessionStatus::Running);
+    assert_eq!(
+        fx.tmux.tmux.list_sessions().expect("list"),
+        vec![id],
+        "exactly one pane for the session"
+    );
+}
+
+/// A refused resume must not leave the session marked in-flight: once the
+/// reason for the refusal is gone, resuming works.
+#[tokio::test]
+async fn a_refused_resume_can_be_retried() {
+    let fx = DaemonFixture::new();
+    let cwd = TempDir::new().unwrap();
+    let (manager, session) = dormant_session(&fx, &cwd, "sleep 30", "retried").await;
+
+    std::fs::remove_dir_all(cwd.path()).unwrap();
+    let err = manager
+        .resume(session.id, &[])
+        .await
+        .expect_err("cwd is gone");
+    assert_eq!(err.to_error_info().code, "cwd_missing");
+
+    std::fs::create_dir_all(cwd.path()).unwrap();
+    let resumed = manager.resume(session.id, &[]).await.expect("resume");
+    assert_eq!(resumed.status, SessionStatus::Running);
+}

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

@@ -326,12 +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
@@ -349,15 +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!(
@@ -366,6 +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]

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/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
@@ -92,10 +98,48 @@ conversation id is respawned on the command it was created with. `Session::comma
 always keeps that original command, so a second resume resolves the same preset.
 Resume is refused with `409` for a session that is already running
 (`already_running`) and for one whose `cwd` has disappeared (`cwd_missing`) —
-neither is something a respawn could fix. The other thing to do with a dormant
+neither is something a respawn could fix. A session with a resume already in
+flight is refused as `already_running` too (#175): the respawn happens with
+the session map unlocked, so the record is marked in-flight before it starts
+and the second request is answered on that state rather than on its tmux spawn
+colliding with the first one's. A resume that loses a race with a kill takes
+its own sidecar back off disk, so the killed session does not return as a
+dormant ghost on the next recovery. 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.