swarm: a soft context limit per agent, as a percent of the window, applied at turn end

hive-agent/src/events.rs

@@ -367,6 +367,11 @@ pub struct Bus {
     /// limit the model enforces, which may differ from the default
     /// (e.g. 200 k active window on a 1 M cache-enabled model).
     api_context_window: Arc<Mutex<Option<u64>>>,
+    /// The swarm's soft context limit, as a percent of the context window
+    /// (`soft_context_percent` of the agent's `agent-inference` key): the
+    /// compaction policy compacts at it instead of the harness's own
+    /// watermark. `None` until the swarm sets one.
+    soft_context_percent: Arc<Mutex<Option<u8>>>,
     /// Resolved model id from the most recent turn's `assistant` events
     /// (the API-echoed `message.model`, e.g. `claude-opus-4-8`), as
     /// opposed to the requested `--model` name which may be a short
@@ -419,6 +424,7 @@ impl Bus {
             tool_calls: Arc::new(Mutex::new(std::collections::HashMap::new())),
             last_turn_ended_unix: Arc::new(AtomicI64::new(0)),
             api_context_window: Arc::new(Mutex::new(None)),
+            soft_context_percent: Arc::new(Mutex::new(None)),
             last_resolved_model: Arc::new(Mutex::new(None)),
         }
     }
@@ -700,6 +706,17 @@ impl Bus {
         *self.api_context_window.lock().unwrap()
     }
 
+    /// Set (or clear, with `None`) the swarm's soft context limit.
+    pub fn set_soft_context_percent(&self, percent: Option<u8>) {
+        *self.soft_context_percent.lock().unwrap() = percent;
+    }
+
+    /// The swarm's soft context limit, as a percent of the window.
+    #[must_use]
+    pub fn soft_context_percent(&self) -> Option<u8> {
+        *self.soft_context_percent.lock().unwrap()
+    }
+
     /// The effective context window for `model`: the API-reported window if a
     /// turn has completed (`api_context_window`), else the per-model default
     /// ([`context_window_tokens`]). Single accessor so the state + dashboard