Index messages by (session_id, created_timestamp, id) to stop on-disk sort storms (#10874)

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Lifei Zhou <lifei@squareup.com>

crates/goose/src/session/session_manager.rs

@@ -24,7 +24,7 @@ use std::path::{Path, PathBuf};
 use std::sync::{Arc, LazyLock};
 use tracing::{info, warn};
 
-pub const CURRENT_SCHEMA_VERSION: i32 = 15;
+pub const CURRENT_SCHEMA_VERSION: i32 = 16;
 pub const SESSIONS_FOLDER: &str = "sessions";
 pub const DB_NAME: &str = "sessions.db";
 const MILLISECOND_TIMESTAMP_THRESHOLD: i64 = 10_000_000_000;
@@ -1079,6 +1079,11 @@ impl SessionStorage {
         sqlx::query("CREATE INDEX IF NOT EXISTS idx_messages_message_id ON messages(message_id)")
             .execute(&mut *tx)
             .await?;
+        sqlx::query(
+            "CREATE INDEX IF NOT EXISTS idx_messages_session_created ON messages(session_id, created_timestamp, id)",
+        )
+        .execute(&mut *tx)
+        .await?;
         sqlx::query("CREATE INDEX IF NOT EXISTS idx_sessions_updated ON sessions(updated_at DESC)")
             .execute(&mut *tx)
             .await?;
@@ -1558,6 +1563,13 @@ impl SessionStorage {
                 .execute(&mut **tx)
                 .await?;
             }
+            16 => {
+                sqlx::query(
+                    "CREATE INDEX IF NOT EXISTS idx_messages_session_created ON messages(session_id, created_timestamp, id)",
+                )
+                .execute(&mut **tx)
+                .await?;
+            }
             _ => {
                 anyhow::bail!("Unknown migration version: {}", version);
             }
@@ -2963,6 +2975,49 @@ mod tests {
         assert_eq!(texts, ["appended first", "built first"]);
     }
 
+    #[tokio::test]
+    async fn test_messages_session_created_index_avoids_disk_sort() {
+        use sqlx::Row;
+
+        let temp_dir = TempDir::new().unwrap();
+        let sm = SessionManager::new(temp_dir.path().to_path_buf());
+        let pool = sm.storage.pool().await.unwrap();
+
+        let index_exists: bool = sqlx::query_scalar(
+            "SELECT EXISTS (SELECT 1 FROM sqlite_master WHERE type='index' AND name='idx_messages_session_created')",
+        )
+        .fetch_one(pool)
+        .await
+        .unwrap();
+        assert!(
+            index_exists,
+            "idx_messages_session_created should exist after schema init"
+        );
+
+        let plan_rows = sqlx::query(
+            "EXPLAIN QUERY PLAN \
+             SELECT content_json FROM messages WHERE session_id = ? ORDER BY created_timestamp, id",
+        )
+        .bind("nonexistent_session")
+        .fetch_all(pool)
+        .await
+        .unwrap();
+        let plan_text: String = plan_rows
+            .iter()
+            .map(|r| r.try_get::<String, _>("detail").unwrap_or_default())
+            .collect::<Vec<_>>()
+            .join("\n");
+
+        assert!(
+            plan_text.contains("idx_messages_session_created"),
+            "loading a session's messages should use idx_messages_session_created, got: {plan_text}"
+        );
+        assert!(
+            !plan_text.contains("TEMP B-TREE"),
+            "loading a session's messages must not require an on-disk sort, got: {plan_text}"
+        );
+    }
+
     #[tokio::test]
     async fn test_last_message_at_is_derived_from_messages() {
         let temp_dir = TempDir::new().unwrap();