Long chats stay fast; search in a chat; media overview

Performance (measured with 5,900 messages: open 9 s -> 0.7 s, typing 440 ms -> 25 ms)
- GET /sessions/{id}?limit=N loads the end of a chat (from the last summary
  on, at most N); /sessions/{id}/messages?before|after|around loads more
  (scrolling up stops at a summary unless asked). Without parameters the
  full history as before (terminal client).
- Chat view: memoised message list (typing, streaming and status changes no
  longer re-render the history), finished turns fold into "N steps · M files"
  with the answer visible, tool card bodies and summaries are built only when
  opened, scroll-to-bottom only when content changes.

Search: /sessions/{id}/search over the whole chat; a hit loads its part
(around) and marks the message, "back to the latest messages" returns.

Media: /sessions/{id}/media lists images, videos and audio of a chat and its
subagents (generated images, tool output, files written, media in answers,
attachments); ⋯ -> Media shows them with filters, a large view and a jump to
the message.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

server/src/api.rs

@@ -81,6 +81,9 @@ pub fn router(app: AppState) -> Router {
         .route("/sessions/{id}/tabs", get(session_tabs).put(put_file_tabs))
         .route("/sessions/{id}/export", get(export_session))
         .route("/blobs/{hash}", get(get_blob))
+        .route("/sessions/{id}/messages", get(session_messages))
+        .route("/sessions/{id}/search", get(search_in_session))
+        .route("/sessions/{id}/media", get(session_media))
         .route("/sessions/{id}", get(get_session).patch(update_session).delete(delete_session))
         .route("/sessions/{id}/prompt", post(prompt))
         .route("/sessions/{id}/abort", post(abort))
@@ -813,14 +816,81 @@ async fn export_session(Extension(user): Extension<User>, State(app): State<AppS
         .into_response())
 }
 
-async fn get_session(Extension(user): Extension<User>, State(app): State<AppState>, Path(id): Path<String>) -> ApiResult {
+#[derive(Deserialize)]
+struct WindowQ {
+    /// Only the end of the chat (from the last summary on, at most this many messages);
+    /// without it, all messages (terminal client).
+    limit: Option<i64>,
+    before: Option<String>,
+    after: Option<String>,
+    around: Option<String>,
+    /// Loading older messages stops at a summary (the history before it on request).
+    #[serde(default)]
+    stop_at_summary: bool,
+}
+
+impl WindowQ {
+    fn window(&self) -> Option<crate::store::MessageWindow> {
+        use crate::store::MessageWindow as W;
+        let limit = self.limit.unwrap_or(200).clamp(1, 1000);
+        Some(match (&self.before, &self.after, &self.around) {
+            (Some(id), _, _) => W::Before { id: id.clone(), limit, stop_at_summary: self.stop_at_summary },
+            (_, Some(id), _) => W::After { id: id.clone(), limit },
+            (_, _, Some(id)) => W::Around { id: id.clone(), limit },
+            _ if self.limit.is_some() => W::Tail { limit },
+            _ => return None,
+        })
+    }
+}
+
+async fn get_session(Extension(user): Extension<User>, State(app): State<AppState>, Path(id): Path<String>, Query(q): Query<WindowQ>) -> ApiResult {
     let s = readable(&app, &user, &id)?;
-    let messages = app.store.messages(&id)?;
     let busy = app.is_busy(&id);
     let can_write = app.access(&user, &id) == Access::Full;
     let queue = app.store.queue_list(&id)?;
     let step = app.with_runtime(&id, |r| r.step.clone());
-    Ok(Json(json!({"session": s, "messages": messages, "busy": busy, "can_write": can_write, "queue": queue, "step": step})))
+    let mut out = json!({"session": s, "busy": busy, "can_write": can_write, "queue": queue, "step": step});
+    match q.window() {
+        Some(w) => {
+            let (messages, older, newer) = app.store.messages_window(&id, &w)?;
+            out["messages"] = json!(messages);
+            out["has_older"] = json!(older);
+            out["has_newer"] = json!(newer);
+        }
+        None => out["messages"] = json!(app.store.messages(&id)?),
+    }
+    Ok(Json(out))
+}
+
+/// More messages of a chat: before / after / around a message.
+async fn session_messages(Extension(user): Extension<User>, State(app): State<AppState>, Path(id): Path<String>, Query(q): Query<WindowQ>) -> ApiResult {
+    readable(&app, &user, &id)?;
+    let w = q.window().ok_or_else(|| ApiError(StatusCode::BAD_REQUEST, "before, after, around or limit is required".into()))?;
+    let (messages, older, newer) = app.store.messages_window(&id, &w).map_err(|e| ApiError(StatusCode::NOT_FOUND, format!("{e:#}")))?;
+    Ok(Json(json!({"messages": messages, "has_older": older, "has_newer": newer})))
+}
+
+/// Images, videos and audio files shown in a chat (all of it, with subagents).
+async fn session_media(Extension(user): Extension<User>, State(app): State<AppState>, Path(id): Path<String>) -> ApiResult {
+    readable(&app, &user, &id)?;
+    let a = app.clone();
+    let items = tokio::task::spawn_blocking(move || crate::media::collect(&a, &id)).await.map_err(|e| ApiError(StatusCode::INTERNAL_SERVER_ERROR, e.to_string()))??;
+    Ok(Json(json!(items)))
+}
+
+/// Search within one chat (all of it, not only the loaded part).
+async fn search_in_session(Extension(user): Extension<User>, State(app): State<AppState>, Path(id): Path<String>, Query(q): Query<SearchQ>) -> ApiResult {
+    readable(&app, &user, &id)?;
+    if q.q.trim().chars().count() < 2 {
+        return Ok(Json(json!([])));
+    }
+    let hits: Vec<Value> = app
+        .store
+        .search_messages(&id, q.q.trim(), 100)?
+        .into_iter()
+        .map(|(mid, role, at, snippet)| json!({"id": mid, "role": role, "created_at": at, "snippet": snippet}))
+        .collect();
+    Ok(Json(json!(hits)))
 }
 
 #[derive(Deserialize)]