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

swarm-controller/src/inference.rs

@@ -1,5 +1,5 @@
-//! `/api/agents/{name}/inference` — the model, effort, subagent models and
-//! subagent cap the swarm sets for one agent, and what the agent reports
+//! `/api/agents/{name}/inference` — the model, effort, subagent models,
+//! subagent cap and soft context limit the swarm sets for one agent, and what the agent reports
 //! running on.
 //!
 //! Each agent's settings are one value under its own key of `agent-inference`
@@ -28,7 +28,8 @@ use axum::http::StatusCode;
 use futures_util::StreamExt as _;
 use problem_details::ProblemDetails;
 use swarm_controller_api::inference::{
-    AgentInferenceView, EffectiveInference, InferenceSettings, MAX_SUBAGENTS,
+    AgentInferenceView, EffectiveInference, InferenceSettings, MAX_SOFT_CONTEXT_PERCENT,
+    MAX_SUBAGENTS, MIN_SOFT_CONTEXT_PERCENT,
 };
 use swarm_queue_client::agent_inference;
 use swarm_wire::agent_inference::{AgentInference, Effective};
@@ -47,6 +48,7 @@ fn settings_view(v: AgentInference) -> InferenceSettings {
         effort: v.effort,
         subagent_models: v.subagent_models,
         max_subagents: v.max_subagents,
+        soft_context_percent: v.soft_context_percent,
     }
 }
 
@@ -91,11 +93,19 @@ pub(crate) fn into_stored(settings: InferenceSettings) -> Result<AgentInference,
             "max_subagents is {max}; it is from 0 (no subagents) to {MAX_SUBAGENTS}, or left out for no cap"
         ));
     }
+    if let Some(percent) = settings.soft_context_percent
+        && !(MIN_SOFT_CONTEXT_PERCENT..=MAX_SOFT_CONTEXT_PERCENT).contains(&percent)
+    {
+        return Err(format!(
+            "soft_context_percent is {percent}; it is from {MIN_SOFT_CONTEXT_PERCENT} to {MAX_SOFT_CONTEXT_PERCENT}, or left out for the harness's own watermark"
+        ));
+    }
     Ok(AgentInference {
         model: settings.model,
         effort: settings.effort,
         subagent_models: settings.subagent_models,
         max_subagents: settings.max_subagents,
+        soft_context_percent: settings.soft_context_percent,
     })
 }
 
@@ -251,7 +261,8 @@ pub(crate) async fn get_agent_inference(
             ones whole", body = InferenceSettings),
         (status = 400, description = "not an identifier, not declared on any hive, or a \
             model name is empty, has whitespace, starts with `-`, or is listed \
-            twice, or `max_subagents` is above 32 (problem+json)",
+            twice, or `max_subagents` is above 32, or `soft_context_percent` is outside \
+            its range (problem+json)",
             body = String),
         (status = 422, description = "an unknown field, or an effort that is not one of \
             the five levels"),
@@ -394,6 +405,7 @@ mod tests {
                 effort: Some(Effort::High),
                 subagent_models: Some(vec!["haiku".to_owned()]),
                 max_subagents: None,
+                soft_context_percent: None,
             }
         );
         assert_eq!(
@@ -555,6 +567,25 @@ mod tests {
         assert!(settings(r#"{"max_subagents":-1}"#).is_err());
     }
 
+    #[test]
+    fn soft_context_percent_outside_its_range_is_refused() {
+        for percent in [0, MIN_SOFT_CONTEXT_PERCENT - 1, MAX_SOFT_CONTEXT_PERCENT + 1] {
+            let json = format!(r#"{{"soft_context_percent":{percent}}}"#);
+            assert!(into_stored(settings(&json).unwrap()).is_err(), "{json}");
+        }
+        assert!(settings(r#"{"soft_context_percent":-1}"#).is_err());
+        assert!(settings(r#"{"soft_context_percent":256}"#).is_err());
+    }
+
+    #[test]
+    fn soft_context_percent_in_range_is_stored() {
+        for percent in [MIN_SOFT_CONTEXT_PERCENT, 20, MAX_SOFT_CONTEXT_PERCENT] {
+            let json = format!(r#"{{"soft_context_percent":{percent}}}"#);
+            let stored = into_stored(settings(&json).unwrap()).unwrap();
+            assert_eq!(stored.soft_context_percent, Some(percent));
+        }
+    }
+
     #[test]
     fn max_subagents_in_range_is_stored() {
         for max in [0, 1, 3, MAX_SUBAGENTS] {