address mara: drop CompactionMode, always checkpoint-then-compact

docs/coordinator.md

@@ -40,7 +40,7 @@ somewhere."
 | `Destroy` | For future use (`destroy --purge` does real I/O). Variant exists so the wire shape doesn't change later; not currently routed through the queue. |
 | `Restart` | Stop + start a container without touching config (~5-10s). Routed through the queue so it serialises against in-flight rebuilds for the same agent — prevents a restart racing a rebuild mid-flight. Sources: dashboard ↺ button, the `restart` MCP tool. |
 | `PermChange` | Write a tool-group or capability change to the shared JSON file (`tool-groups.json` / `capabilities.json`), then rebuild the agent so the updated `HIVE_TOOL_GROUPS` / `HIVE_CAPABILITIES` env var takes effect. Serialising the file write through the queue prevents concurrent dashboard batch-apply actions from racing on the shared file. After a successful file write, emits `CapabilitiesChanged` or `ToolGroupsChanged` SSE snapshot so the P3RM1SS10NS tab updates live. |
-| `GracefulStop` | Quiesce then stop a container (the `?graceful=true` path on `/api/kill/<agent>`). Signals the harness (its next `Recv` returns `GracefulStop` — the inbound fence — so it runs **one** stop-checkpoint turn that flushes durable `/state` and compacts the session if it crossed the watermark, then exits) and **immediately releases the build lane**, spawning a detached watcher that holds the `Stopping` transient across the drain (bounded by a 3-min timeout → hard-stop fallback) and then enqueues a fast-lane `Stop` (`parent_id` = this entry) for the actual `nixos-container stop`. Net: a whole-hive graceful stop signals every agent up front, drains overlap, and only the container teardowns serialise (on the fast lane). Queued so the signal can't race an in-flight rebuild for the same agent. |
+| `GracefulStop` | Quiesce then stop a container (the `?graceful=true` path on `/api/kill/<agent>`). Signals the harness (its next `Recv` returns `GracefulStop` — the inbound fence — so it runs a stop-checkpoint turn that flushes durable `/state`, then takes the normal post-turn compaction path if it crossed the watermark, then exits) and **immediately releases the build lane**, spawning a detached watcher that holds the `Stopping` transient across the drain (bounded by a 3-min timeout → hard-stop fallback) and then enqueues a fast-lane `Stop` (`parent_id` = this entry) for the actual `nixos-container stop`. Net: a whole-hive graceful stop signals every agent up front, drains overlap, and only the container teardowns serialise (on the fast lane). Queued so the signal can't race an in-flight rebuild for the same agent. |
 
 **Intentionally not queued** (sub-second ops): the *hard* `start`, `stop`, `kill`. (A *graceful* stop is the `GracefulStop` kind above — it takes a checkpoint turn, so it rides the queue.)
 

docs/turn-loop.md

@@ -517,12 +517,10 @@ ttl_seconds?, to?)`, `answer(id, answer)`.
   explicit `from: "graceful-stop"` message instead of an empty inbox.
   This unmissably directs the agent to flush durable state (`/state`
   files) and end the turn — the container exits when the turn completes.
-  This is a **single** wake: the graceful-stop turn *is* the checkpoint
-  (its prompt carries the full notes/CLAUDE.md/TODO.md flush guidance),
-  so the harness compacts directly afterwards if the context crossed the
-  watermark (`CompactionMode::CompactOnly`) rather than waking a second
-  dedicated checkpoint turn. Compacting before shutdown keeps a later
-  cold start cheap instead of re-uploading a huge transcript.
+  The graceful-stop turn takes the same post-turn compaction path as any
+  other turn: if the context crossed the watermark the harness runs a
+  notes-checkpoint turn and then `/compact`. Compacting before shutdown
+  keeps a later cold start cheap instead of re-uploading a huge transcript.
 - `ask` — surface a structured question to the operator (default) or
   a peer agent (`to: "<agent>"`). Non-blocking — returns a question
   id; the answer arrives as a `question_answered` system event in the

hive-ag3nt/src/bin/hive.rs

@@ -546,9 +546,6 @@ async fn serve_loop<S: Surface>(
                         stats.as_ref(),
                         files,
                         &turn_lock,
-                        // The graceful prompt IS the checkpoint — compact
-                        // directly afterwards if needed, no second wake.
-                        turn::CompactionMode::CompactOnly,
                         graceful_stop_message(),
                     )
                     .await;
@@ -557,16 +554,7 @@ async fn serve_loop<S: Surface>(
                 }
             },
         };
-        let ctrl = handle_turn::<S>(
-            socket,
-            &bus,
-            stats.as_ref(),
-            files,
-            &turn_lock,
-            turn::CompactionMode::CheckpointThenCompact,
-            next,
-        )
-        .await;
+        let ctrl = handle_turn::<S>(socket, &bus, stats.as_ref(), files, &turn_lock, next).await;
         if ctrl.auth_failed {
             *login_state.lock().unwrap() = LoginState::NeedsLogin;
             turn::wait_for_login(
@@ -595,7 +583,6 @@ async fn handle_turn<S: Surface>(
     stats: Option<&TurnStats>,
     files: &turn::TurnFiles,
     turn_lock: &TurnLock,
-    compaction: turn::CompactionMode,
     first: hive_sh4re::DeliveredMessage,
 ) -> TurnControl {
     let from = first.from;
@@ -616,7 +603,7 @@ async fn handle_turn<S: Surface>(
     let prompt = serve_common::format_wake_prompt(&from, &body, unread, redelivered);
     let outcome = {
         let _guard = turn_lock.lock().await;
-        turn::drive_turn_with(&prompt, files, bus, compaction).await
+        turn::drive_turn(&prompt, files, bus).await
     };
     turn::emit_turn_end(bus, &outcome);
     bus.set_state(TurnState::Idle);

hive-ag3nt/src/turn.rs

@@ -263,20 +263,6 @@ fn compact_watermark_tokens(bus: &Bus) -> u64 {
     effective_context_window(bus) * 3 / 4
 }
 
-/// Post-turn compaction behaviour for [`drive_turn`].
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub enum CompactionMode {
-    /// Normal turns: if the context crossed the watermark, run a dedicated
-    /// notes-checkpoint turn so the agent can flush durable state, THEN
-    /// `/compact`. The checkpoint turn is a separate wake.
-    CheckpointThenCompact,
-    /// Graceful-stop turn: the turn that just ran WAS the checkpoint (its
-    /// prompt already told the agent to flush state), so compact directly
-    /// if the watermark was crossed — no second wake. Keeps a cold-start
-    /// resume cheap without waking the agent twice.
-    CompactOnly,
-}
-
 /// Drive one turn end-to-end. Three paths layer on top of the raw `run_turn`:
 ///
 /// - **Auto-reset (pre-turn)** — context is large AND the prompt cache has
@@ -292,24 +278,12 @@ pub enum CompactionMode {
 ///   size has crept past the watermark: while the session is still healthy we
 ///   give the agent one dedicated turn to checkpoint its `/state` notes, then
 ///   compact. This keeps a later turn from hitting the reactive path (where
-///   there is no chance to save anything first). The graceful-stop path uses
-///   [`CompactionMode::CompactOnly`] to skip the dedicated checkpoint turn.
+///   there is no chance to save anything first). The graceful-stop path takes
+///   the same proactive route — a checkpoint turn before `/compact` is cheap
+///   insurance and keeps a later cold-start resume small.
 ///
 /// Called once per turn by the `hive` serve loop (every agent role).
 pub async fn drive_turn(prompt: &str, files: &TurnFiles, bus: &Bus) -> TurnOutcome {
-    drive_turn_with(prompt, files, bus, CompactionMode::CheckpointThenCompact).await
-}
-
-/// As [`drive_turn`] but with explicit control over the post-turn
-/// compaction behaviour — see [`CompactionMode`]. The graceful-stop path
-/// passes [`CompactionMode::CompactOnly`] so the agent isn't woken a
-/// second time for a checkpoint it already did.
-pub async fn drive_turn_with(
-    prompt: &str,
-    files: &TurnFiles,
-    bus: &Bus,
-    compaction: CompactionMode,
-) -> TurnOutcome {
     maybe_auto_reset(bus);
     let outcome = match run_turn(prompt, files, bus).await {
         TurnOutcome::PromptTooLong => {
@@ -340,22 +314,13 @@ pub async fn drive_turn_with(
         other => other,
     };
     // Proactive: a turn just completed on a still-healthy session. If its
-    // context crossed the watermark, compact before a later turn overflows
-    // into the reactive path. In the normal mode this first runs a separate
-    // notes-checkpoint turn so the agent can flush durable state; in
-    // `CompactOnly` mode (graceful stop) the turn that just ran was itself
-    // the checkpoint, so we compact directly without a second wake.
-    // Best-effort — never changes the outcome of the turn that already
-    // succeeded, but records it as `Compacted` so turn stats can distinguish
-    // it from a plain `Ok`.
-    if matches!(outcome, TurnOutcome::Ok) {
-        let compacted = match compaction {
-            CompactionMode::CheckpointThenCompact => maybe_checkpoint_and_compact(files, bus).await,
-            CompactionMode::CompactOnly => maybe_compact(files, bus).await,
-        };
-        if compacted {
-            return TurnOutcome::Compacted;
-        }
+    // context crossed the watermark, run a separate notes-checkpoint turn so
+    // the agent can flush durable state, then compact before a later turn
+    // overflows into the reactive path. Best-effort — never changes the
+    // outcome of the turn that already succeeded, but records it as
+    // `Compacted` so turn stats can distinguish it from a plain `Ok`.
+    if matches!(outcome, TurnOutcome::Ok) && maybe_checkpoint_and_compact(files, bus).await {
+        return TurnOutcome::Compacted;
     }
     outcome
 }
@@ -399,28 +364,6 @@ async fn maybe_checkpoint_and_compact(files: &TurnFiles, bus: &Bus) -> bool {
     true
 }
 
-/// Compact-only proactive path: if the context crossed the watermark,
-/// `/compact` directly — NO preceding checkpoint turn. Used by the
-/// graceful-stop path, where the turn that just ran already flushed
-/// durable state (its prompt said so), so a second checkpoint wake would
-/// be redundant. Compacting before the container stops keeps a later
-/// cold-start resume cheap rather than re-uploading a huge transcript.
-/// Returns `true` if compaction was attempted.
-async fn maybe_compact(files: &TurnFiles, bus: &Bus) -> bool {
-    let Some(used) = watermark_crossed(bus) else {
-        return false;
-    };
-    let watermark = compact_watermark_tokens(bus);
-    bus.emit(LiveEvent::Note {
-        text: format!(
-            "context at {used} tokens (watermark {watermark}) — compacting before \
-             graceful stop so a later cold start resumes cheap"
-        ),
-    });
-    do_compact(files, bus).await;
-    true
-}
-
 /// Returns `Some(used_tokens)` when proactive compaction is enabled AND the
 /// last inference's context size has reached the watermark; `None` when
 /// compaction is disabled (watermark 0), there's no usage reading yet, or