merge: apply the worktree rule when a session exits on its own

Closes #82

crates/maestro-daemon/src/session.rs

@@ -441,21 +441,8 @@ impl SessionManager {
                 ),
             }
         };
-        // The probe runs before anything is torn down: both refusing (#79)
-        // and recording the retention (#81) must see the tree as it stands,
-        // and a refused kill leaves the session running as the operator left
-        // it.
         let probe = match &worktree {
-            Some((_, path)) => {
-                let path = path.clone();
-                Some(
-                    tmux_blocking(move || crate::worktree_probe::in_the_way(&path))
-                        .await
-                        .map_err(|e| {
-                            SessionError::Worktree(crate::worktree::WorktreeError::from(e))
-                        })?,
-                )
-            }
+            Some(wt) => Some(probe_worktree(wt).await?),
             None => None,
         };
         let guarded = probe.as_ref().is_some_and(|p| !p.is_clear());
@@ -463,29 +450,15 @@ impl SessionManager {
             return Err(SessionError::KillGuarded(probe.expect("guarded ⇒ probed")));
         }
 
-        // Record the retention BEFORE tearing down: a failed store write then
-        // leaves the session running and every artifact untouched, instead of
-        // ending a session whose work outlives it unrecorded.
         let mut retained = None;
         if guarded {
-            let store =
-                self.inner.retained.clone().ok_or_else(|| {
-                    SessionError::RetainFailed("no retained store is wired".into())
-                })?;
-            let (base_repo, path) = worktree.as_ref().expect("guarded ⇒ worktree");
-            let branch = known_branch
-                .or_else(|| crate::worktree_probe::current_branch(path))
-                .unwrap_or_default();
-            let entry = {
-                let store = store.clone();
-                let base_repo = base_repo.clone();
-                let path = path.clone();
-                tmux_blocking(move || {
-                    store.retain(&path, &base_repo, &branch, RetainedReason::ForceKilled)
-                })
-                .await
-                .map_err(|e| SessionError::RetainFailed(e.to_string()))?
-            };
+            let entry = record_retention(
+                &self.inner,
+                worktree.as_ref().expect("guarded ⇒ worktree"),
+                known_branch,
+                RetainedReason::ForceKilled,
+            )
+            .await?;
             retained = Some((entry, probe.expect("guarded ⇒ probed")));
         }
 
@@ -671,6 +644,49 @@ where
         .expect("tmux blocking task panicked")
 }
 
+/// What would be lost if this session's worktree were removed right now.
+///
+/// The single [`crate::worktree_probe::in_the_way`] call site behind both
+/// endings of a session — the kill guard (#79) and the natural-exit
+/// classifier (#82) — so neither can grow its own answer. Runs on the
+/// blocking pool; callers invoke it before anything is torn down, because
+/// refusing (#79), recording a retention (#81) and classifying an exit (#82)
+/// must all see the tree as it stands.
+async fn probe_worktree(
+    (_, path): &(PathBuf, PathBuf),
+) -> Result<maestro_protocol::InTheWay, SessionError> {
+    let path = path.clone();
+    tmux_blocking(move || crate::worktree_probe::in_the_way(&path))
+        .await
+        .map_err(|e| SessionError::Worktree(crate::worktree::WorktreeError::from(e)))
+}
+
+/// Record a guarded worktree into the retained store with `reason`, BEFORE
+/// the caller tears anything down: a failed write then leaves every artifact
+/// untouched instead of destroying work nothing records anymore. Shared by
+/// the forced kill (`ForceKilled`, #81) and the natural exit
+/// (`ExitedWithUnsavedWork`, #82) so the two paths cannot drift apart.
+async fn record_retention(
+    inner: &Arc<Inner>,
+    (base_repo, path): &(PathBuf, PathBuf),
+    known_branch: Option<String>,
+    reason: RetainedReason,
+) -> Result<crate::retained_store::RetainedWorktreeRecord, SessionError> {
+    let store = inner
+        .retained
+        .clone()
+        .ok_or_else(|| SessionError::RetainFailed("no retained store is wired".into()))?;
+    // Sessions adopted from a sidecar carry no branch; ask the tree itself.
+    let branch = known_branch
+        .or_else(|| crate::worktree_probe::current_branch(path))
+        .unwrap_or_default();
+    let base_repo = base_repo.clone();
+    let path = path.clone();
+    tmux_blocking(move || store.retain(&path, &base_repo, &branch, reason))
+        .await
+        .map_err(|e| SessionError::RetainFailed(e.to_string()))
+}
+
 /// One pass of the liveness watcher: diff the in-memory session set against
 /// the tmux-reported one, and reap anything we still track but tmux has lost.
 async fn run_liveness_pass(inner: &Arc<Inner>) {
@@ -794,17 +810,23 @@ async fn run_activity_pass(inner: &Arc<Inner>) {
 }
 
 /// Mark a session whose tmux session has disappeared as [`SessionStatus::Dead`]
-/// and announce it, keeping everything else intact.
+/// and settle its worktree per the natural-exit rule (#82).
 ///
 /// The record, its [`PtyBridge`] and its sidecar all survive, so a client can
 /// still attach and read the replay buffer — the last thing a crashed agent
-/// printed. Artifacts are only released when the operator dismisses the session
-/// via [`SessionManager::kill`].
+/// printed. The worktree, though, is settled right away: a pristine tree is
+/// removed, anything else is retained into the store with reason
+/// `exited-with-unsaved-work` (#82) — nobody is waiting for an answer here,
+/// so there is nothing to refuse. Once settled, the session drops its
+/// worktree reference so a later dismissal neither re-probes nor retains
+/// twice. When settling is impossible (probe or store failure) nothing is
+/// destroyed: the tree stays attached to the dead record for a later forced
+/// dismissal (#81).
 ///
 /// Dead sessions do not survive a daemon restart: [`SessionManager::recover`]
 /// adopts only what tmux still holds.
 async fn mark_session_dead(inner: &Arc<Inner>, id: Uuid) {
-    let updated = {
+    let flipped = {
         let mut sessions = inner.sessions.lock().await;
         match sessions.get_mut(&id) {
             Some(record) if record.session.status == SessionStatus::Running => {
@@ -812,19 +834,111 @@ async fn mark_session_dead(inner: &Arc<Inner>, id: Uuid) {
                 // Release anyone attached; the scrollback survives for a later
                 // attach.
                 record.bridge.seal();
-                Some(record.session.clone())
+                let session = record.session.clone();
+                let worktree = record
+                    .worktree_base_repo
+                    .clone()
+                    .zip(record.worktree_path.clone());
+                let branch = record.worktree_branch.clone();
+                Some((session, worktree, branch))
             }
             _ => None,
         }
     };
-    let Some(session) = updated else {
+    let Some((mut session, worktree, branch)) = flipped else {
         return;
     };
     tracing::info!(%id, "session vanished from tmux — marking dead");
+
+    if let Some(wt) = &worktree {
+        if settle_worktree_on_exit(inner, id, wt, branch).await {
+            session.worktree = None;
+            let mut sessions = inner.sessions.lock().await;
+            if let Some(record) = sessions.get_mut(&id) {
+                record.session.worktree = None;
+                record.worktree_path = None;
+                record.worktree_base_repo = None;
+                record.worktree_branch = None;
+            }
+        }
+    }
+
     let _ = inner.sidecar.write(&session);
     let _ = inner.events.send(CatalogEvent::SessionUpdated { session });
 }
 
+/// Apply the exit rule (#82) to a vanished session's worktree: probe what
+/// would be lost through the kill's own predicate, then remove a pristine
+/// tree or retain anything else under `exited-with-unsaved-work` — recorded
+/// before anything is torn down, exactly as the forced kill does (#81). A
+/// removal that fails falls back to retaining, since whatever blocked it is
+/// by definition something worth keeping.
+///
+/// Returns whether the worktree was fully accounted for. When it wasn't,
+/// nothing was destroyed and the caller keeps the reference on the record.
+async fn settle_worktree_on_exit(
+    inner: &Arc<Inner>,
+    id: Uuid,
+    (base_repo, path): &(PathBuf, PathBuf),
+    known_branch: Option<String>,
+) -> bool {
+    let probe = match probe_worktree(&(base_repo.clone(), path.clone())).await {
+        Ok(probe) => probe,
+        Err(e) => {
+            tracing::error!(
+                %id,
+                path = %path.display(),
+                error = ?e,
+                "natural exit: could not probe the worktree; leaving it untouched"
+            );
+            return false;
+        }
+    };
+    if probe.is_clear() {
+        match inner.worktree_mgr.remove(base_repo, path) {
+            Ok(()) => {
+                tracing::info!(%id, path = %path.display(), "natural exit: pristine worktree removed");
+                return true;
+            }
+            Err(e) => {
+                tracing::warn!(
+                    %id,
+                    path = %path.display(),
+                    error = ?e,
+                    "natural exit: removal failed; falling back to retention"
+                );
+            }
+        }
+    }
+    match record_retention(
+        inner,
+        &(base_repo.clone(), path.clone()),
+        known_branch,
+        RetainedReason::ExitedWithUnsavedWork,
+    )
+    .await
+    {
+        Ok(entry) => {
+            tracing::info!(
+                %id,
+                path = %path.display(),
+                entry = %entry.id,
+                "natural exit: worktree retained with unsaved work"
+            );
+            true
+        }
+        Err(e) => {
+            tracing::error!(
+                %id,
+                path = %path.display(),
+                error = ?e,
+                "natural exit: could not record the retained worktree; leaving it untouched"
+            );
+            false
+        }
+    }
+}
+
 /// Tear down a session's artifacts after it has already been removed from the
 /// live map. Shared by [`SessionManager::kill`] and [`reap_dead_session`],
 /// which previously hand-rolled the same five-step choreography and only

crates/maestro-daemon/tests/session_manager.rs

@@ -8,7 +8,9 @@ use std::process::Command;
 use std::sync::Arc;
 use std::time::Duration;
 
-use common::{init_bare_repo, init_repo, push_all_to_origin, wait_for_async, DaemonFixture};
+use common::{
+    init_bare_repo, init_repo, push_all_to_origin, wait_for_async, DaemonFixture, TmuxFixture,
+};
 use maestro_daemon::SessionError;
 use maestro_protocol::CreateSessionRequest;
 use maestro_protocol::{CatalogEvent, SessionStatus, WorktreeSpec};
@@ -668,6 +670,191 @@ async fn killing_an_ignored_only_worktree_succeeds() {
     assert!(!fx.manager.has(s.id).await);
 }
 
+/// Natural exit (#82): a session that ends on its own never reaches the kill
+/// path, so the watcher applies the kill's rule itself. A worktree holding
+/// unsaved work is RETAINED into the store with reason
+/// `exited-with-unsaved-work`; the session stays in the catalog marked dead
+/// until dismissed — and dismissing it afterwards neither refuses nor
+/// retains a second time.
+#[tokio::test]
+async fn natural_exit_of_a_guarded_worktree_retains_it_in_the_store() {
+    let fx = DaemonFixture::new();
+    let repo = TempDir::new().unwrap();
+    init_repo(repo.path());
+    let wt_path = repo.path().join("worktrees").join("feat").join("exited");
+
+    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/exited".into(),
+                cleanup_on_kill: true,
+                create_branch: true,
+            }),
+        })
+        .await
+        .expect("create");
+    std::fs::write(wt_path.join("README"), b"unsaved edits\n").unwrap();
+
+    // The command finishes / the operator types exit: tmux loses the session.
+    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;
+
+    // The tree would have blocked a kill, so the exit kept it...
+    assert!(
+        wt_path.exists(),
+        "a dirty worktree must be retained on natural exit"
+    );
+    // ...in the store, under the exit reason.
+    let all = fx.retained_store().load_all().expect("load_all");
+    assert_eq!(all.len(), 1);
+    assert_eq!(all[0].path, wt_path);
+    assert_eq!(all[0].branch, "feat/exited");
+    assert_eq!(
+        all[0].reason,
+        maestro_protocol::RetainedReason::ExitedWithUnsavedWork
+    );
+
+    // The session itself stays until dismissed; its worktree reference is
+    // settled, so dismissal is neither refused nor retained twice.
+    // (`Dead` is observable a moment before the settle step finishes.)
+    wait_for_async(Duration::from_secs(3), || async {
+        fx.manager.snapshot().await[0].worktree.is_none()
+    })
+    .await;
+    let snap = fx.manager.snapshot().await;
+    assert_eq!(snap.len(), 1);
+    assert_eq!(snap[0].worktree, None);
+
+    fx.manager.kill(s.id, false).await.expect("dismiss");
+    assert!(!fx.manager.has(s.id).await);
+    assert!(
+        wt_path.exists(),
+        "dismissal must not remove what was retained"
+    );
+    assert_eq!(
+        fx.retained_store().load_all().unwrap().len(),
+        1,
+        "dismissal must not record a second entry for the same tree"
+    );
+}
+
+/// Natural exit (#82), pristine side of the same rule: nothing in the tree,
+/// nothing to keep — the worktree is removed and no store entry appears.
+#[tokio::test]
+async fn natural_exit_of_a_pristine_worktree_removes_it() {
+    let fx = DaemonFixture::new();
+    let repo = TempDir::new().unwrap();
+    init_repo(repo.path());
+    let wt_path = repo.path().join("worktrees").join("feat").join("clean");
+
+    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/clean".into(),
+                cleanup_on_kill: true,
+                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;
+
+    assert!(
+        !wt_path.exists(),
+        "a pristine worktree leaves nothing behind"
+    );
+    assert!(
+        fx.retained_store().load_all().unwrap().is_empty(),
+        "nothing was retained"
+    );
+    assert!(
+        fx.manager.has(s.id).await,
+        "the session stays until dismissed"
+    );
+}
+
+/// When nothing can be recorded — here: no retained store wired — the exit
+/// destroys nothing. The tree stays on disk AND stays attached to the dead
+/// record, where dismissing it later still goes through #81's forced-kill
+/// retention. Losing the store must not lose the work.
+#[tokio::test]
+async fn natural_exit_without_a_retained_store_destroys_nothing() {
+    let tmux = TmuxFixture::new();
+    let state_dir = TempDir::new().unwrap();
+    let manager = maestro_daemon::SessionManager::new(
+        Arc::new(tmux.tmux.clone()),
+        maestro_daemon::sidecar::SidecarStore::new(state_dir.path().join("sessions")),
+        maestro_daemon::worktree::WorktreeManager::new(None),
+        state_dir.path().join("fifos"),
+    );
+    // Deliberately NO with_retained_store.
+
+    let repo = TempDir::new().unwrap();
+    init_repo(repo.path());
+    let wt_path = repo.path().join("worktrees").join("feat").join("nostore");
+
+    let s = 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/nostore".into(),
+                cleanup_on_kill: true,
+                create_branch: true,
+            }),
+        })
+        .await
+        .expect("create");
+    std::fs::write(wt_path.join("README"), b"unsaved edits\n").unwrap();
+
+    tmux.tmux.kill_session(s.id).expect("kill tmux directly");
+    manager.start_liveness_watcher(Duration::from_millis(50));
+    wait_for_async(Duration::from_secs(3), || async {
+        manager.status(s.id).await == Some(SessionStatus::Dead)
+    })
+    .await;
+
+    assert!(
+        wt_path.exists(),
+        "nothing may be destroyed when it cannot be recorded"
+    );
+    let snap = manager.snapshot().await;
+    assert!(
+        snap[0].worktree.is_some(),
+        "the tree must stay attached to the record so a later forced kill can retain it"
+    );
+}
+
 fn run_git_in(dir: &std::path::Path, args: &[&str]) {
     let out = Command::new("git")
         .arg("-C")

docs/WORKTREES.md

@@ -97,6 +97,17 @@ Nobody is waiting for an answer here, so there is nothing to refuse; the choice
 only between removing and retaining. It uses the same predicate as the kill, from
 the same place, so the two paths cannot drift apart.
 
+The session itself stays in the catalog marked dead until it is dismissed — the
+replay buffer of a crashed agent outlives it — but its worktree is settled at
+once. Once settled, the session drops its worktree reference, so dismissing it
+afterwards neither refuses (there is no guard left to trip) nor records a second
+store entry.
+
+If settling is impossible — the probe fails, or the store cannot take the entry —
+nothing is destroyed. The tree stays on disk *and* stays attached to the dead
+record, where dismissing it later still goes through `--force`'s
+retain-before-teardown path. Losing the store must never mean losing the work.
+
 ## The retained store
 
 A `state_dir`-backed record of worktrees the daemon created that no longer have a