swarm: show each agent's effective model and effort, and where they came from

Each agent now reports the model and effort it runs on, and where each
comes from (`swarm`, `agent_nix`, `local_file` or `default`), in its
turn-state header on `$SWARM.agent-state.<agent>`: `effort`,
`model_source` and `effort_source` join `model`. The shared
`swarm_queue_client::agent_inference::{Effective, Source}` types spell
those fields for both ends.

The Bus keeps a source next to the model and effort. `Bus::new` takes it
from the local fallback chain (`harness_state::local_model` /
`local_effort`, which now return the source with the value), a `/model`
or `/effort` pick sets `local_file`, and the swarm poller sets `swarm`
or, on a clear, the local chain's source. A swarm value equal to the one
the agent already runs is now applied once, so the source moves to
`swarm` and the header is republished; before, `next()` skipped it as
unchanged.

swarm-controller subscribes to every agent's header with the reader
grant it already holds for the state relay, and keeps the latest
inference fields per agent in memory (`inference::Reported`).
`GET /api/agents/{name}/inference` now answers
`{configured, effective}`, `effective` being `null` until the agent's
first header with these fields since the controller started.
`swarmctl agent inference get` prints both; `set` reads `configured`.

Refs #5034

swarm-controller/src/inference.rs

@@ -1,19 +1,27 @@
 //! `/api/agents/{name}/inference` — the model, effort and subagent models the
-//! swarm sets for one agent.
+//! 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`
 //! (`swarm_queue_client::agent_inference`), which this daemon alone writes.
 //! The agent reads its key and applies each set field over its local value;
 //! an unset field leaves the local value in force.
+//!
+//! What the agent runs on comes from its turn-state header
+//! (`$SWARM.agent-state.<agent>`), which [`Reported`] keeps the latest of.
+//! Agents publish a header only when it changes and the queue keeps none, so
+//! an agent that has not changed since this daemon started has no entry.
 
-use std::collections::BTreeSet;
+use std::collections::{BTreeSet, HashMap};
+use std::sync::{Arc, Mutex, PoisonError};
+use std::time::Duration;
 
 use axum::Json;
 use axum::extract::{Path, State};
 use axum::http::StatusCode;
+use futures_util::StreamExt as _;
 use problem_details::ProblemDetails;
 use serde::{Deserialize, Serialize};
-use swarm_queue_client::agent_inference::{self, AgentInference, Effort};
+use swarm_queue_client::agent_inference::{self, AgentInference, Effective, Effort, Source};
 use utoipa::ToSchema;
 
 use crate::schedules::{live, queue, read, refused, write};
@@ -90,6 +98,103 @@ impl InferenceSettings {
     }
 }
 
+/// What `GET` answers for one agent.
+#[derive(Debug, Serialize, ToSchema)]
+pub struct AgentInferenceView {
+    /// The settings the swarm sets; `{}` when none is set.
+    configured: InferenceSettings,
+    /// What the agent reported running on in its latest turn-state header;
+    /// `null` when this daemon has received none with these fields since it
+    /// started.
+    effective: Option<EffectiveInference>,
+}
+
+/// The model and effort an agent runs on, and where each comes from.
+#[derive(Debug, PartialEq, Eq, Serialize, ToSchema)]
+pub struct EffectiveInference {
+    model: String,
+    effort: String,
+    /// `swarm`, `agent_nix`, `local_file` or `default`.
+    #[schema(value_type = String)]
+    model_source: Source,
+    /// As `model_source`.
+    #[schema(value_type = String)]
+    effort_source: Source,
+}
+
+impl From<Effective> for EffectiveInference {
+    fn from(v: Effective) -> Self {
+        Self {
+            model: v.model,
+            effort: v.effort,
+            model_source: v.model_source,
+            effort_source: v.effort_source,
+        }
+    }
+}
+
+/// The latest [`Effective`] each agent reported, by agent.
+#[derive(Debug, Default)]
+pub(crate) struct Reported {
+    latest: Mutex<HashMap<String, Effective>>,
+}
+
+impl Reported {
+    /// Start recording every agent's turn-state headers from `client`.
+    pub(crate) fn spawn(client: async_nats::Client) -> Arc<Self> {
+        let reported = Arc::new(Self::default());
+        let recording = Arc::clone(&reported);
+        tokio::spawn(async move { recording.follow(&client).await });
+        reported
+    }
+
+    /// Subscribe to every agent's header, and subscribe again if the
+    /// subscription ends.
+    async fn follow(&self, client: &async_nats::Client) {
+        const RETRY: Duration = Duration::from_secs(5);
+        let subject = swarm_queue_client::agent_state_subject_wildcard();
+        loop {
+            match client.subscribe(subject.clone()).await {
+                Ok(mut headers) => {
+                    tracing::info!(%subject, "inference: following agent turn-state headers");
+                    while let Some(msg) = headers.next().await {
+                        self.record(&msg.subject, &msg.payload);
+                    }
+                    tracing::warn!(%subject, "inference: header subscription ended");
+                }
+                Err(e) => tracing::warn!(%subject, error = %e, "inference: subscribe failed"),
+            }
+            tokio::time::sleep(RETRY).await;
+        }
+    }
+
+    /// Keep one header's inference fields. A header without them, from an
+    /// agent that does not report them, removes what was kept.
+    fn record(&self, subject: &str, payload: &[u8]) {
+        let Some(agent) = swarm_queue_client::agent_from_state_subject(subject) else {
+            return;
+        };
+        let mut latest = self.latest.lock().unwrap_or_else(PoisonError::into_inner);
+        match serde_json::from_slice::<Effective>(payload) {
+            Ok(effective) => {
+                latest.insert(agent.to_owned(), effective);
+            }
+            Err(e) => {
+                tracing::debug!(%agent, error = %e, "inference: header has no inference fields");
+                latest.remove(agent);
+            }
+        }
+    }
+
+    fn get(&self, agent: &str) -> Option<Effective> {
+        self.latest
+            .lock()
+            .unwrap_or_else(PoisonError::into_inner)
+            .get(agent)
+            .cloned()
+    }
+}
+
 fn agent_name(name: &str) -> Result<String, (StatusCode, String)> {
     hive_types::Ident::parse(name)
         .map(hive_types::Ident::into_string)
@@ -114,8 +219,8 @@ async fn open(
     path = "/api/agents/{name}/inference",
     params(("name" = String, Path, description = "agent name")),
     responses(
-        (status = 200, description = "the agent's settings; `{}` when none is set",
-            body = InferenceSettings),
+        (status = 200, description = "the settings the swarm sets for the agent, and what \
+            it reported running on", body = AgentInferenceView),
         (status = 400, description = "not an identifier (problem+json)", body = String),
         (status = 503, description = "no swarm queue is configured on this host, or it is \
             not connected (problem+json)", body = String),
@@ -127,14 +232,21 @@ async fn open(
 pub(crate) async fn get_agent_inference(
     State(state): State<AppState>,
     Path(name): Path<String>,
-) -> Result<Json<InferenceSettings>, ProblemDetails> {
+) -> Result<Json<AgentInferenceView>, ProblemDetails> {
     let agent = agent_name(&name).map_err(refused)?;
     let client = queue(&state).map_err(refused)?;
     let store = open(&client).await?;
     let (current, _) = read::<AgentInference>(&store, &agent)
         .await
         .map_err(|e| queue_problem(&e))?;
-    Ok(Json(current.into()))
+    Ok(Json(AgentInferenceView {
+        configured: current.into(),
+        effective: state
+            .reported_inference
+            .as_ref()
+            .and_then(|r| r.get(&agent))
+            .map(Into::into),
+    }))
 }
 
 #[utoipa::path(
@@ -280,6 +392,70 @@ mod tests {
         assert!(settings(r#"{"model":"opus","effort":"xhigh"}"#).is_ok());
     }
 
+    const NEW_HEADER: &[u8] = br#"{"turn_state":"idle","model":"opus","effort":"high",
+        "model_source":"swarm","effort_source":"local_file"}"#;
+
+    /// A header from an agent that does not report effort or sources.
+    const OLD_HEADER: &[u8] = br#"{"turn_state":"idle","model":"sonnet"}"#;
+
+    fn iris() -> String {
+        swarm_queue_client::agent_state_subject("iris")
+    }
+
+    #[test]
+    fn a_header_is_kept_under_its_agent() {
+        let reported = Reported::default();
+        reported.record(&iris(), NEW_HEADER);
+        assert_eq!(
+            reported.get("iris"),
+            Some(Effective {
+                model: "opus".to_owned(),
+                effort: "high".to_owned(),
+                model_source: Source::Swarm,
+                effort_source: Source::LocalFile,
+            })
+        );
+        assert_eq!(reported.get("atlas"), None);
+    }
+
+    #[test]
+    fn a_header_without_the_inference_fields_leaves_no_entry() {
+        let reported = Reported::default();
+        reported.record(&iris(), NEW_HEADER);
+        reported.record(&iris(), OLD_HEADER);
+        assert_eq!(reported.get("iris"), None);
+    }
+
+    #[test]
+    fn a_subject_naming_no_agent_is_skipped() {
+        let reported = Reported::default();
+        reported.record("$SWARM.agent-state.iris.sub.scout", NEW_HEADER);
+        reported.record("$SWARM.term.iris", NEW_HEADER);
+        assert!(reported.latest.lock().unwrap().is_empty());
+    }
+
+    #[test]
+    fn the_view_answers_both_halves() {
+        let view = |effective: Option<Effective>| {
+            serde_json::to_value(AgentInferenceView {
+                configured: InferenceSettings::default(),
+                effective: effective.map(Into::into),
+            })
+            .unwrap()
+        };
+        assert_eq!(
+            view(None),
+            serde_json::json!({"configured": {}, "effective": null})
+        );
+        let reported = Reported::default();
+        reported.record(&iris(), NEW_HEADER);
+        assert_eq!(
+            view(reported.get("iris"))["effective"],
+            serde_json::json!({"model": "opus", "effort": "high",
+                "model_source": "swarm", "effort_source": "local_file"})
+        );
+    }
+
     #[test]
     fn bad_model_names_are_refused() {
         for json in [