{"messages":[{"content":"You are a constitutional council ranking individual git commits for ownership allocation.\n\nCompare these two commits. Decide which contributed more lasting value to the project.\n\nJudge substance, not spectacle:\n- Prefer correct, lasting design and real bugfixes over churn, formatting, renames, or generated noise.\n- Prefer clarity and necessity over sheer line count. A small precise change can beat a large diffuse one.\n- Do not favor a side merely because its patch is longer or noisier.\n- Weight what the change does for the project, not the contributor's name.\n\nReturn ONLY a JSON object: {\"winner\": \"A\" or \"B\", \"ratio\": \"N:M\", \"explanation\": \"...\"}\nThe explanation must cite concrete differences in the patches (1-3 sentences).\n\nSide A — contributor: tommy-mor\nSide A — commit message:\n[5ca518f6] url refactor\n\nSide A — unified diff (full patch):\ndiff --git a/Cargo.lock b/Cargo.lock\nindex 67a09a3b54f778fa7e857fdd589c3ed9c92e1322..ad7e4fe6d4ba2f2b033916194c1ef1ed873f1d46 100644\n--- a/Cargo.lock\n+++ b/Cargo.lock\n@@ -1757,6 +1757,7 @@ name = \"slug-types\"\n version = \"0.1.0\"\n dependencies = [\n  \"serde\",\n+ \"url\",\n ]\n \n [[package]]\n@@ -2272,6 +2273,7 @@ dependencies = [\n  \"idna\",\n  \"percent-encoding\",\n  \"serde\",\n+ \"serde_derive\",\n ]\n \n [[package]]\ndiff --git a/server/src/api/ui_html.rs b/server/src/api/ui_html.rs\nindex 606f7d6f97a4428efb90d1e0d544934c861fc4c5..cd3e0f0afd972d9ad9e7e4b92c5fa4c22bb8f620 100644\n--- a/server/src/api/ui_html.rs\n+++ b/server/src/api/ui_html.rs\n@@ -270,10 +270,10 @@ fn post_redirect_location(room: &str, thread_tag: &str) -> String {\n         format!(\"/t/{tag}\")\n     } else {\n         let room = room.trim();\n-        let Some((a, b)) = room.split_once('/') else {\n+        let Some(seg) = slug_types::room_route_segment(room) else {\n             return \"/\".to_string();\n         };\n-        format!(\"/r/{a}/{b}/t/{tag}\")\n+        format!(\"/r/{seg}/t/{tag}\")\n     }\n }\n \ndiff --git a/server/src/api/write_actor.rs b/server/src/api/write_actor.rs\nindex cb78d2f3f95b1bc163c1fb064d1d5f657e18000f..f9c3b8bd3fbf8fcb9c035e1a1572fef0b08fa8a9 100644\n--- a/server/src/api/write_actor.rs\n+++ b/server/src/api/write_actor.rs\n@@ -19,13 +19,15 @@ use crate::{\n use super::auth::{issue_token_for_user, verify_token};\n use super::helpers::{now_ms, resolve_item};\n use super::validate::{normalize_room_and_thread, validate_ingest_document};\n-use slug_types::RpcResult;\n+use slug_types::{room_route_segment, RpcResult, ROOM_SHORT_ID_LEN};\n \n fn gen_short_id() -> String {\n     use rand::Rng;\n     const ALPHABET: &[u8] = b\"0123456789abcdefghijklmnopqrstuvwxyz\";\n     let mut rng = rand::thread_rng();\n-    (0..7).map(|_| ALPHABET[rng.gen_range(0..ALPHABET.len())] as char).collect()\n+    (0..ROOM_SHORT_ID_LEN)\n+        .map(|_| ALPHABET[rng.gen_range(0..ALPHABET.len())] as char)\n+        .collect()\n }\n \n fn parse_capability(s: &str) -> Result<crate::events::ThreadCapability, String> {\n@@ -55,8 +57,8 @@ async fn broadcast_web_refresh(state: &AppState, room_key: &str, thread_id: &str\n     let feed_id = if room_key == \"public\" { \"thread-feed\" } else { \"room-thread-feed\" };\n     let thread_url = if room_key == \"public\" {\n         format!(\"/t/{thread_id}\")\n-    } else if let Some((short, slug)) = room_key.split_once('/') {\n-        format!(\"/r/{short}/{slug}/t/{thread_id}\")\n+    } else if let Some(seg) = room_route_segment(room_key) {\n+        format!(\"/r/{seg}/t/{thread_id}\")\n     } else {\n         format!(\"/t/{thread_id}\")\n     };\n@@ -78,8 +80,8 @@ async fn broadcast_web_refresh(state: &AppState, room_key: &str, thread_id: &str\n     let js = builder.build();\n     let mut path_prefixes = vec![if room_key == \"public\" {\n         \"/\".to_string()\n-    } else if let Some((short, slug)) = room_key.split_once('/') {\n-        format!(\"/r/{short}/{slug}\")\n+    } else if let Some(seg) = room_route_segment(room_key) {\n+        format!(\"/r/{seg}\")\n     } else {\n         \"/\".to_string()\n     }];\ndiff --git a/server/src/html/forum/nav.rs b/server/src/html/forum/nav.rs\nindex 0ee33d91160fc5542817b5e3e9ab4fee1d0e600f..48fe11e46731670874ff8b6b05baa6f09ae0b7e4 100644\n--- a/server/src/html/forum/nav.rs\n+++ b/server/src/html/forum/nav.rs\n@@ -1,7 +1,8 @@\n use crate::canonical_path::canonicalize_item;\n use crate::reducer::ScopeId;\n+use slug_types::room_route_segment;\n \n-/// URL helpers for public `/t/…` and private room threads `/r/{short}/{slug}/t/…`.\n+/// URL helpers for public `/t/…` and private room threads `/r/{short}{slug}/t/…`.\n #[derive(Clone)]\n pub struct ThreadNav {\n     pub room_wire: String,\n@@ -22,18 +23,15 @@ impl ThreadNav {\n         }\n     }\n \n-    /// `room_id` wire form `shortid/slug`.\n+    /// `room_id` wire form `shortid/slug` (HTTP uses [`slug_types::room_route_segment`]).\n     pub(crate) fn from_room_id(room_id: &str) -> Option<Self> {\n-        let (short, slug) = room_id.split_once('/')?;\n-        if short.is_empty() || slug.is_empty() {\n-            return None;\n-        }\n+        let room_seg = room_route_segment(room_id)?;\n         Some(Self {\n             room_wire: room_id.to_string(),\n             scope: ScopeId::Room(room_id.to_string()),\n-            room_path: format!(\"/r/{short}/{slug}\"),\n-            thread_path_prefix: format!(\"/r/{short}/{slug}/t\"),\n-            garden_path_prefix: format!(\"/r/{short}/{slug}/~\"),\n+            room_path: format!(\"/r/{room_seg}\"),\n+            thread_path_prefix: format!(\"/r/{room_seg}/t\"),\n+            garden_path_prefix: format!(\"/r/{room_seg}/~\"),\n         })\n     }\n \ndiff --git a/server/src/html/forum/post_single.rs b/server/src/html/forum/post_single.rs\nindex c316f8f836df9d4ef9c05ebd9e54f699540e6d72..473747b3da3d4d7a54b5e0c63165d2533df643e1 100644\n--- a/server/src/html/forum/post_single.rs\n+++ b/server/src/html/forum/post_single.rs\n@@ -93,12 +93,14 @@ pub async fn thread_post_view(\n \n pub async fn room_thread_post_view(\n     State(state): State<AppState>,\n-    Path((room_short, room_slug, tag, index_str)): Path<(String, String, String, String)>,\n+    Path((room_key, tag, index_str)): Path<(String, String, String)>,\n     headers: HeaderMap,\n     jar: CookieJar,\n     uri: Uri,\n ) -> impl IntoResponse {\n-    let room_id = format!(\"{room_short}/{room_slug}\");\n+    let Some(room_id) = slug_types::room_id_from_route_segment(&room_key) else {\n+        return (StatusCode::NOT_FOUND, \"bad room path\").into_response();\n+    };\n     let reduced = state.reduced.read().await;\n     let user = optional_principal(&headers, &jar, &reduced);\n     if !user_can_view_room(&reduced, &room_id, user.as_deref()) {\ndiff --git a/server/src/html/forum/views.rs b/server/src/html/forum/views.rs\nindex be5df1745ef580891a167c23c3dd6c06f804f295..1ec421f84335cbfe7f9db775b73a8ed24b197174 100644\n--- a/server/src/html/forum/views.rs\n+++ b/server/src/html/forum/views.rs\n@@ -183,16 +183,18 @@ pub async fn thread_view(\n     thread_view_inner(state, tag, q, ThreadNav::public(), headers, jar, uri).await\n }\n \n-/// Room thread — `/r/:short/:slug/t/:tag`\n+/// Room thread — `/r/:room_key/t/:tag` (`room_key` = `{short}{slug}`).\n pub async fn room_thread_view(\n     State(state): State<AppState>,\n-    Path((room_short, room_slug, tag)): Path<(String, String, String)>,\n+    Path((room_key, tag)): Path<(String, String)>,\n     Query(q): Query<ThreadViewQuery>,\n     headers: HeaderMap,\n     jar: CookieJar,\n     uri: Uri,\n ) -> impl IntoResponse {\n-    let room_id = format!(\"{room_short}/{room_slug}\");\n+    let Some(room_id) = slug_types::room_id_from_route_segment(&room_key) else {\n+        return (StatusCode::NOT_FOUND, \"bad room path\").into_response();\n+    };\n     let reduced = state.reduced.read().await;\n     let user = optional_principal(&headers, &jar, &reduced);\n     if !user_can_view_room(&reduced, &room_id, user.as_deref()) {\n@@ -226,15 +228,17 @@ pub(super) fn room_not_found_page(jar: &CookieJar, uri: &Uri) -> impl IntoRespon\n     (StatusCode::NOT_FOUND, Html(page.into_string()))\n }\n \n-/// Private room index — `/r/:short/:slug`\n+/// Private room index — `/r/:room_key`\n pub async fn room_page(\n     State(state): State<AppState>,\n-    Path((room_short, room_slug)): Path<(String, String)>,\n+    Path(room_key): Path<String>,\n     headers: HeaderMap,\n     jar: CookieJar,\n     uri: Uri,\n ) -> impl IntoResponse {\n-    let room_id = format!(\"{room_short}/{room_slug}\");\n+    let Some(room_id) = slug_types::room_id_from_route_segment(&room_key) else {\n+        return (StatusCode::NOT_FOUND, \"room not found\").into_response();\n+    };\n     let now = now_ms();\n     let reduced = state.reduced.read().await;\n     if !reduced.rooms.contains(&room_id) {\n@@ -266,7 +270,10 @@ pub async fn room_page(\n     let audit_cli = format!(\"npx slugsocial private {room_id} audit\");\n     drop(reduced);\n \n-    let slug_display = room_slug.as_str();\n+    let slug_display = room_id\n+        .split_once('/')\n+        .map(|(_, slug)| slug)\n+        .unwrap_or(room_id.as_str());\n     let page = layout(\n         &format!(\"room {slug_display} — slug.social\"),\n         \"view-thread\",\ndiff --git a/server/src/html/garden.rs b/server/src/html/garden.rs\nindex 423f23fd8c9ad7b7f454d6ea7a9a7607a4c9c5b9..e615dd356bcf634232d85610c0a26235ead125fd 100644\n--- a/server/src/html/garden.rs\n+++ b/server/src/html/garden.rs\n@@ -309,12 +309,14 @@ pub async fn external_ontology_path(\n \n pub async fn room_garden_index(\n     State(state): State<AppState>,\n-    Path((room_short, room_slug)): Path<(String, String)>,\n+    Path(room_key): Path<String>,\n     headers: HeaderMap,\n     jar: CookieJar,\n     uri: Uri,\n ) -> impl IntoResponse {\n-    let room_id = format!(\"{room_short}/{room_slug}\");\n+    let Some(room_id) = slug_types::room_id_from_route_segment(&room_key) else {\n+        return (StatusCode::NOT_FOUND, \"bad room path\").into_response();\n+    };\n     let Some(nav) = ThreadNav::from_room_id(&room_id) else {\n         return (StatusCode::NOT_FOUND, \"bad room path\").into_response();\n     };\n@@ -341,12 +343,14 @@ pub async fn room_garden_index(\n \n pub async fn room_external_garden_index(\n     State(state): State<AppState>,\n-    Path((room_short, room_slug)): Path<(String, String)>,\n+    Path(room_key): Path<String>,\n     headers: HeaderMap,\n     jar: CookieJar,\n     uri: Uri,\n ) -> impl IntoResponse {\n-    let room_id = format!(\"{room_short}/{room_slug}\");\n+    let Some(room_id) = slug_types::room_id_from_route_segment(&room_key) else {\n+        return (StatusCode::NOT_FOUND, \"bad room path\").into_response();\n+    };\n     let Some(nav) = ThreadNav::from_room_id(&room_id) else {\n         return (StatusCode::NOT_FOUND, \"bad room path\").into_response();\n     };\n@@ -416,12 +420,14 @@ pub async fn room_external_garden_index(\n \n pub async fn room_external_ontology_path(\n     State(state): State<AppState>,\n-    Path((room_short, room_slug, path)): Path<(String, String, String)>,\n+    Path((room_key, path)): Path<(String, String)>,\n     headers: HeaderMap,\n     jar: CookieJar,\n     uri: Uri,\n ) -> impl IntoResponse {\n-    let room_id = format!(\"{room_short}/{room_slug}\");\n+    let Some(room_id) = slug_types::room_id_from_route_segment(&room_key) else {\n+        return (StatusCode::NOT_FOUND, \"bad room path\").into_response();\n+    };\n     let Some(nav) = ThreadNav::from_room_id(&room_id) else {\n         return (StatusCode::NOT_FOUND, \"bad room path\").into_response();\n     };\n@@ -442,12 +448,14 @@ pub async fn room_external_ontology_path(\n \n pub async fn room_ontology_path(\n     State(state): State<AppState>,\n-    Path((room_short, room_slug, path)): Path<(String, String, String)>,\n+    Path((room_key, path)): Path<(String, String)>,\n     headers: HeaderMap,\n     jar: CookieJar,\n     uri: Uri,\n ) -> impl IntoResponse {\n-    let room_id = format!(\"{room_short}/{room_slug}\");\n+    let Some(room_id) = slug_types::room_id_from_route_segment(&room_key) else {\n+        return (StatusCode::NOT_FOUND, \"bad room path\").into_response();\n+    };\n     let Some(nav) = ThreadNav::from_room_id(&room_id) else {\n         return (StatusCode::NOT_FOUND, \"bad room path\").into_response();\n     };\ndiff --git a/server/src/html/search.rs b/server/src/html/search.rs\nindex 43e6ebf36cf0fe72c96f0f9d850bea51ac094c43..f01732f7edb32c68fcc10c39545c8f56476adb27 100644\n--- a/server/src/html/search.rs\n+++ b/server/src/html/search.rs\n@@ -351,8 +351,8 @@ fn render_search_results(results: &SearchResults, query: &str) -> Markup {\n                     ul class=\"search-posts\" {\n                         @for r in &results.posts {\n                             @let (post_href, post_label) = if let Some((room, tag)) = r.thread.split_once(\"/#\") {\n-                                if let Some((short, slug)) = room.split_once('/') {\n-                                    (format!(\"/r/{short}/{slug}/t/{tag}\"), format!(\"{room}/#{tag}\"))\n+                                if let Some(seg) = slug_types::room_route_segment(room) {\n+                                    (format!(\"/r/{seg}/t/{tag}\"), format!(\"{room}/#{tag}\"))\n                                 } else {\n                                     (\"/\".to_string(), r.thread.clone())\n                                 }\ndiff --git a/server/src/lib.rs b/server/src/lib.rs\nindex 9e69c3f4a153527caa77b00ad101aca94b425995..71032f9a0b556097d90f3b403c677e0c86429ee4 100644\n--- a/server/src/lib.rs\n+++ b/server/src/lib.rs\n@@ -79,30 +79,30 @@ pub fn create_app(state: AppState) -> Router {\n         .route(\"/~/*path\", get(crate::html::ontology_path))\n         .route(\"/-\", get(crate::html::external_garden_index))\n         .route(\"/-/*path\", get(crate::html::external_ontology_path))\n-        .route(\"/r/:room_short/:room_slug/~\", get(crate::html::room_garden_index))\n+        .route(\"/r/:room_key/~\", get(crate::html::room_garden_index))\n         .route(\n-            \"/r/:room_short/:room_slug/~/*path\",\n+            \"/r/:room_key/~/*path\",\n             get(crate::html::room_ontology_path),\n         )\n         .route(\n-            \"/r/:room_short/:room_slug/-\",\n+            \"/r/:room_key/-\",\n             get(crate::html::room_external_garden_index),\n         )\n         .route(\n-            \"/r/:room_short/:room_slug/-/*path\",\n+            \"/r/:room_key/-/*path\",\n             get(crate::html::room_external_ontology_path),\n         )\n         .route(\"/t/:tag/:index\", get(crate::html::thread_post_view))\n         .route(\"/t/:tag\", get(crate::html::thread_view))\n         .route(\n-            \"/r/:room_short/:room_slug/t/:thread_tag/:index\",\n+            \"/r/:room_key/t/:thread_tag/:index\",\n             get(crate::html::room_thread_post_view),\n         )\n         .route(\n-            \"/r/:room_short/:room_slug/t/:thread_tag\",\n+            \"/r/:room_key/t/:thread_tag\",\n             get(crate::html::room_thread_view),\n         )\n-        .route(\"/r/:room_short/:room_slug\", get(crate::html::room_page))\n+        .route(\"/r/:room_key\", get(crate::html::room_page))\n         .route(\"/join/:token\", get(api::get_join_invite))\n         .route(\"/auth/login\", get(api::get_auth_login))\n         .route(\"/auth/callback\", get(api::get_auth_callback))\ndiff --git a/server/tests/integration.rs b/server/tests/integration.rs\nindex 515c691d04ef3f1f4bdfa8ee911360a43fd2b26e..feb73d475b3fc635d7f16c329d4600718c7472ba 100644\n--- a/server/tests/integration.rs\n+++ b/server/tests/integration.rs\n@@ -1,4 +1,5 @@\n use sha2::{Digest, Sha256};\n+use slug_types::room_route_segment;\n use slugsocial_server::{\n     event_log::EventLog,\n     events::{Event, TokenIssued, UserRegistered},\n@@ -607,7 +608,7 @@ async fn test_private_room_thread_urls_use_t_segment() {\n         .as_str()\n         .unwrap()\n         .to_string();\n-    let (room_short, room_slug) = room_id.split_once('/').unwrap();\n+    let room_seg = room_route_segment(&room_id).unwrap();\n \n     let rpc = ui_post_ingest_rpc(&room_id, \"main-thread\", \"private post via web\");\n     let post = client\n@@ -626,7 +627,7 @@ async fn test_private_room_thread_urls_use_t_segment() {\n         Some(\"text/javascript; charset=utf-8\")\n     );\n     let post_js = post.text().await.unwrap();\n-    let location = format!(\"/r/{room_short}/{room_slug}/t/main-thread\");\n+    let location = format!(\"/r/{room_seg}/t/main-thread\");\n     assert!(post_js.contains(&format!(\"window.location = {:?};\", location)));\n     assert!(post_js.contains(\"#room-thread-feed\"));\n     assert!(post_js.contains(\"#thread-feed-region\"));\n@@ -665,7 +666,7 @@ async fn test_private_room_post_links_use_private_garden_routes() {\n         .as_str()\n         .unwrap()\n         .to_string();\n-    let (room_short, room_slug) = room_id.split_once('/').unwrap();\n+    let room_seg = room_route_segment(&room_id).unwrap();\n \n     let rpc = ui_post_ingest_rpc(\n         &room_id,\n@@ -682,18 +683,18 @@ async fn test_private_room_post_links_use_private_garden_routes() {\n     assert_eq!(post.status(), reqwest::StatusCode::OK);\n \n     let thread_page = client\n-        .get(format!(\"http://{addr}/r/{room_short}/{room_slug}/t/garden-thread\"))\n+        .get(format!(\"http://{addr}/r/{room_seg}/t/garden-thread\"))\n         .header(\"Authorization\", format!(\"Bearer {bearer}\"))\n         .send()\n         .await\n         .unwrap();\n     assert!(thread_page.status().is_success());\n     let body = thread_page.text().await.unwrap();\n-    assert!(body.contains(&format!(\"/r/{room_short}/{room_slug}/~/secret/item\")));\n+    assert!(body.contains(&format!(\"/r/{room_seg}/~/secret/item\")));\n     assert!(!body.contains(\"href=\\\"/~/secret/item\\\"\"));\n \n     let garden_page = client\n-        .get(format!(\"http://{addr}/r/{room_short}/{room_slug}/~/secret/item\"))\n+        .get(format!(\"http://{addr}/r/{room_seg}/~/secret/item\"))\n         .header(\"Authorization\", format!(\"Bearer {bearer}\"))\n         .send()\n         .await\n@@ -701,7 +702,7 @@ async fn test_private_room_post_links_use_private_garden_routes() {\n     assert!(garden_page.status().is_success());\n     let garden_body = garden_page.text().await.unwrap();\n     assert!(garden_body.contains(\"classified\"));\n-    assert!(garden_body.contains(&format!(\"/r/{room_short}/{room_slug}/t/garden-thread\")));\n+    assert!(garden_body.contains(&format!(\"/r/{room_seg}/t/garden-thread\")));\n }\n \n #[tokio::test]\n@@ -726,7 +727,7 @@ async fn test_private_room_garden_root_lists_top_level_tilde_children() {\n         .as_str()\n         .unwrap()\n         .to_string();\n-    let (room_short, room_slug) = room_id.split_once('/').unwrap();\n+    let room_seg = room_route_segment(&room_id).unwrap();\n \n     let rpc = ui_post_ingest_rpc(\n         &room_id,\n@@ -743,7 +744,7 @@ async fn test_private_room_garden_root_lists_top_level_tilde_children() {\n     assert_eq!(post.status(), reqwest::StatusCode::OK);\n \n     let root_page = client\n-        .get(format!(\"http://{addr}/r/{room_short}/{room_slug}/~\"))\n+        .get(format!(\"http://{addr}/r/{room_seg}/~\"))\n         .header(\"Authorization\", format!(\"Bearer {bearer}\"))\n         .send()\n         .await\n@@ -782,10 +783,10 @@ async fn test_empty_private_room_garden_returns_404() {\n         .as_str()\n         .unwrap()\n         .to_string();\n-    let (room_short, room_slug) = room_id.split_once('/').unwrap();\n+    let room_seg = room_route_segment(&room_id).unwrap();\n \n     let root = client\n-        .get(format!(\"http://{addr}/r/{room_short}/{room_slug}/~\"))\n+        .get(format!(\"http://{addr}/r/{room_seg}/~\"))\n         .header(\"Authorization\", format!(\"Bearer {bearer}\"))\n         .send()\n         .await\n@@ -896,8 +897,8 @@ async fn test_sse_stream_emits_evalable_js_after_post() {\n         .as_str()\n         .unwrap()\n         .to_string();\n-    let (room_short, room_slug) = room_id.split_once('/').unwrap();\n-    let room_path = format!(\"/r/{room_short}/{room_slug}\");\n+    let room_seg = room_route_segment(&room_id).unwrap();\n+    let room_path = format!(\"/r/{room_seg}\");\n \n     let sse_resp = client\n         .get(format!(\"http://{addr}/sse?path={}\", urlencoding::encode(&room_path)))\ndiff --git a/test/browser_room_delete.clj b/test/browser_room_delete.clj\nindex 833e3f8aa7f850b60ee59742736143cbf101a07d..764ecaa674798a61c1ffca3859f2a56a91a0e97e 100644\n--- a/test/browser_room_delete.clj\n+++ b/test/browser_room_delete.clj\n@@ -54,7 +54,7 @@\n            room-id (get-in create-json [\"results\" 0 \"result\" \"RoomCreated\" \"room_id\"])\n            _ (is (string? room-id) \"room id present\")\n            [room-short room-slug] (str/split room-id #\"/\" 2)\n-           room-path (str \"/r/\" room-short \"/\" room-slug)]\n+           room-path (str \"/r/\" room-short room-slug)]\n        (core/with-playwright [pw]\n          (core/with-browser [browser (core/launch-chromium pw {:headless true :channel \"chrome\"})]\n            (core/with-context [ctx (core/new-context browser)]\ndiff --git a/test/browser_sse.clj b/test/browser_sse.clj\nindex 8bb064dbc2dc0feb6caaa67f520a461645958277..678399b79f78ff48b5e77342fa21e69992393834 100644\n--- a/test/browser_sse.clj\n+++ b/test/browser_sse.clj\n@@ -77,7 +77,7 @@\n                   (login-user! bob-pg base-url \"bob\")\n \n                    (let [[room-short room-slug] (str/split room-id #\"/\" 2)\n-                         room-url (str base-url \"/r/\" room-short \"/\" room-slug)\n+                         room-url (str base-url \"/r/\" room-short room-slug)\n                          thread-url (str room-url \"/t/sse-thread\")]\n                     ;; Object under test: slug_ui.js intercepts POST /ui, evals JS, morphs\n                     ;; #new-thread-ui-slot (expand compose), then post_ingest redirects to thread.\ndiff --git a/test/walkthrough_fixture.clj b/test/walkthrough_fixture.clj\nindex a487ff1ef8548580577914fb33f321586859c9af..f7eb1cacca0317129e9baf68fa4f4e33356ad70f 100644\n--- a/test/walkthrough_fixture.clj\n+++ b/test/walkthrough_fixture.clj\n@@ -88,9 +88,9 @@\n      :room {:id room-id\n             :short room-short\n             :slug room-slug\n-            :url (str base-url \"/r/\" room-short \"/\" room-slug)\n-            :thread_url (str base-url \"/r/\" room-short \"/\" room-slug \"/t/walkthrough-thread\")\n-            :garden_url (str base-url \"/r/\" room-short \"/\" room-slug \"/~/secret/item\")}}))\n+            :url (str base-url \"/r/\" room-short room-slug)\n+            :thread_url (str base-url \"/r/\" room-short room-slug \"/t/walkthrough-thread\")\n+            :garden_url (str base-url \"/r/\" room-short room-slug \"/~/secret/item\")}}))\n \n (defn- rebase-fixture-summary [saved current-base-url current-google-url current-data-dir]\n   (let [inner (:summary saved)\n@@ -103,9 +103,9 @@\n            :data_dir (str current-data-dir)\n            :summary (assoc inner\n                            :room (assoc room\n-                                         :url (str current-base-url \"/r/\" rs \"/\" lg)\n-                                         :thread_url (str current-base-url \"/r/\" rs \"/\" lg \"/t/walkthrough-thread\")\n-                                         :garden_url (str current-base-url \"/r/\" rs \"/\" lg \"/~/secret/item\"))))))\n+                                         :url (str current-base-url \"/r/\" rs lg)\n+                                         :thread_url (str current-base-url \"/r/\" rs lg \"/t/walkthrough-thread\")\n+                                         :garden_url (str current-base-url \"/r/\" rs lg \"/~/secret/item\"))))))\n \n (defn- fixture-log-present? [data-dir]\n   (let [p (fs/path data-dir \"events.jsonl\")]\ndiff --git a/types/Cargo.toml b/types/Cargo.toml\nindex 1ed06d483ac7c126516bce27f90e7639c2dfe370..5dc3becf238f23243313dff0484c682a7b225737 100644\n--- a/types/Cargo.toml\n+++ b/types/Cargo.toml\n@@ -5,3 +5,4 @@ edition = \"2021\"\n \n [dependencies]\n serde = { version = \"1.0\", features = [\"derive\"] }\n+url = { version = \"2.5\", features = [\"serde\"] }\ndiff --git a/types/src/lib.rs b/types/src/lib.rs\nindex fce1b5fa5e259a4b86a11cb4d4f7cc9bec3a0aa1..516cf935f15fca97081b39b988da5be894c67725 100644\n--- a/types/src/lib.rs\n+++ b/types/src/lib.rs\n@@ -1,5 +1,7 @@\n use serde::{Deserialize, Serialize};\n \n+pub mod room_route;\n+pub mod url_normalize;\n pub mod paths;\n pub mod timeago;\n \n@@ -8,6 +10,8 @@ pub use paths::{\n     CanonicalItemUrl, ForumThreadUrl, GardenItemUrl, RelativePath, SLUG_TILDE_ONTOLOGY_ROOT,\n     TildeHttpPathTail, TildeOntologyPath, TildePath, tilde_http_path_to_canonical,\n };\n+pub use room_route::{room_id_from_route_segment, room_route_segment, ROOM_SHORT_ID_LEN};\n+pub use url_normalize::normalize_http_identity_url;\n \n /// Max characters returned for a garden item body unless `full=true` / `--full` (API + CLI).\n pub const MAX_ITEM_BODY_PREVIEW_CHARS: usize = 100_000;\n@@ -657,3 +661,6 @@ pub struct VoteResponse {\n     pub ranking: Vec<RankRow>,\n     pub next: NextMoves,\n }\n+\n+#[cfg(test)]\n+mod url_identity_tests;\ndiff --git a/types/src/paths.rs b/types/src/paths.rs\nindex 8971f599a7ebcf399f60c306d35ee28d0f581194..98787a5fb481a1599556564bbbbd1d54dc693fc3 100644\n--- a/types/src/paths.rs\n+++ b/types/src/paths.rs\n@@ -5,7 +5,7 @@\n //!\n //! - **[`canonicalize_item`] / [`CanonicalItemUrl`]** — graph storage key and DSL form; tilde\n //!   ontology root is always [`SLUG_TILDE_ONTOLOGY_ROOT`] (no `…/~/` trailing slash only).\n-//! - **[`TildeHttpPathTail`]** — capture from `GET /~/*path` or `…/r/…/~/…` (the `*path` segment).\n+//! - **[`TildeHttpPathTail`]** — capture from `GET /~/*path` or `…/r/{short}{slug}/~/…` (the `*path` segment).\n //! - **`-/…` wire form** — external items; see [`canonicalize_item`] dash branch.\n //! - **[`GardenItemUrl`], [`ForumThreadUrl`]** — JSON / browser href surfaces.\n \n@@ -15,6 +15,9 @@ use std::ops::Deref;\n \n use serde::{Deserialize, Serialize};\n \n+use crate::room_route::room_route_segment;\n+use crate::url_normalize::{host_preserves_dash_path_case, normalize_http_identity_url};\n+\n // ---------------------------------------------------------------------------\n // Slug tilde ontology (single storage form for `~/`)\n // ---------------------------------------------------------------------------\n@@ -41,6 +44,29 @@ pub fn canonicalize_tag(input: &str) -> String {\n     input.trim().trim_start_matches('#').to_lowercase()\n }\n \n+fn finalize_external_identity_url(s: String) -> String {\n+    if s.starts_with(\"https://slug.social/\") {\n+        return s;\n+    }\n+    let normalized = normalize_http_identity_url(&s).unwrap_or_else(|| s.clone());\n+    strip_redundant_root_slash(&normalized).unwrap_or(normalized)\n+}\n+\n+/// `url::Url` serializes bare hosts with a `/` path; we keep host-only items slash-free for stable\n+/// keys matching the pre-normalizer spellings.\n+fn strip_redundant_root_slash(s: &str) -> Option<String> {\n+    let u = url::Url::parse(s).ok()?;\n+    if u.path() == \"/\" && u.query().is_none() && u.fragment().is_none() {\n+        let scheme = u.scheme();\n+        let host = u.host_str()?;\n+        return Some(match u.port() {\n+            Some(p) => format!(\"{scheme}://{host}:{p}\"),\n+            None => format!(\"{scheme}://{host}\"),\n+        });\n+    }\n+    None\n+}\n+\n /// Ontology item reference → canonical absolute URL on the slug host.\n pub fn canonicalize_item(input: &str) -> String {\n     let s = input.trim();\n@@ -57,8 +83,9 @@ pub fn canonicalize_item(input: &str) -> String {\n         if host.is_empty() {\n             return String::new();\n         }\n+        let preserve_case = host_preserves_dash_path_case(&host);\n         return if tail.is_empty() {\n-            format!(\"https://{}\", host)\n+            finalize_external_identity_url(format!(\"https://{}\", host))\n         } else {\n             let path = tail\n                 .trim_start_matches('/')\n@@ -68,33 +95,35 @@ pub fn canonicalize_item(input: &str) -> String {\n                     let t = seg.trim();\n                     if t.is_empty() {\n                         None\n+                    } else if preserve_case {\n+                        Some(t.to_string())\n                     } else {\n                         Some(t.to_lowercase())\n                     }\n                 })\n                 .collect::<Vec<_>>()\n                 .join(\"/\");\n-            format!(\"https://{}/{}\", host, path)\n+            finalize_external_identity_url(format!(\"https://{}/{}\", host, path))\n         };\n     }\n \n     if let Some(rest) = s.strip_prefix(\"https://\") {\n         let (host, tail) = rest.split_once('/').map_or((rest, \"\"), |(h, t)| (h, t));\n         let host = host.trim().to_lowercase();\n-        if tail.is_empty() {\n-            return format!(\"https://{}\", host);\n+        return finalize_external_identity_url(if tail.is_empty() {\n+            format!(\"https://{}\", host)\n         } else {\n-            return format!(\"https://{}/{}\", host, tail);\n-        }\n+            format!(\"https://{}/{}\", host, tail)\n+        });\n     }\n     if let Some(rest) = s.strip_prefix(\"http://\") {\n         let (host, tail) = rest.split_once('/').map_or((rest, \"\"), |(h, t)| (h, t));\n         let host = host.trim().to_lowercase();\n-        if tail.is_empty() {\n-            return format!(\"http://{}\", host);\n+        return finalize_external_identity_url(if tail.is_empty() {\n+            format!(\"http://{}\", host)\n         } else {\n-            return format!(\"http://{}/{}\", host, tail);\n-        }\n+            format!(\"http://{}/{}\", host, tail)\n+        });\n     }\n \n     let is_tilde = s.starts_with(\"~/\");\n@@ -319,7 +348,7 @@ impl CanonicalItemUrl {\n     }\n }\n \n-/// HTTP route capture: path segment after `~/` in `GET /~/*path` or `…/r/…/~/…` (empty = ontology root).\n+/// HTTP route capture: path segment after `~/` in `GET /~/*path` or `…/r/{short}{slug}/~/…` (empty = ontology root).\n #[derive(Debug, Clone, PartialEq, Eq, Hash)]\n pub struct TildeHttpPathTail(pub String);\n \n@@ -506,12 +535,9 @@ fn garden_href_string(item: &str, room_wire: &str) -> String {\n     if room.is_empty() || room == \"public\" {\n         return api_path_or_url(item);\n     }\n-    let Some((short, slug)) = room.split_once('/') else {\n+    let Some(room_seg) = room_route_segment(room) else {\n         return api_path_or_url(item);\n     };\n-    if short.is_empty() || slug.is_empty() {\n-        return api_path_or_url(item);\n-    }\n     let Some(c) = CanonicalItemUrl::parse(item) else {\n         return api_path_or_url(item);\n     };\n@@ -520,19 +546,19 @@ fn garden_href_string(item: &str, room_wire: &str) -> String {\n     let root_norm = root.as_str().trim_end_matches('/');\n     if let Some(tail) = c.tilde_tail() {\n         return if tail.is_empty() {\n-            format!(\"https://slug.social/r/{short}/{slug}/~\")\n+            format!(\"https://slug.social/r/{room_seg}/~\")\n         } else {\n-            format!(\"https://slug.social/r/{short}/{slug}/~/{}\", tail)\n+            format!(\"https://slug.social/r/{room_seg}/~/{}\", tail)\n         };\n     }\n     if item_norm == root_norm {\n-        return format!(\"https://slug.social/r/{short}/{slug}/~\");\n+        return format!(\"https://slug.social/r/{room_seg}/~\");\n     }\n     // External http(s) items use the same `/-/…` namespace under the room garden.\n     if c.as_str().starts_with(\"https://\") || c.as_str().starts_with(\"http://\") {\n         let tail = c.display_path();\n         let tail = tail.strip_prefix(\"-/\").unwrap_or(tail.as_str());\n-        return format!(\"https://slug.social/r/{short}/{slug}/-/{tail}\");\n+        return format!(\"https://slug.social/r/{room_seg}/-/{tail}\");\n     }\n     api_path_or_url(item)\n }\n@@ -556,12 +582,8 @@ impl ForumThreadUrl {\n         let tag = thread_tag.trim().trim_start_matches('#');\n         Self(if room.is_empty() || room == \"public\" {\n             format!(\"https://slug.social/t/{tag}\")\n-        } else if let Some((short, slug)) = room.split_once('/') {\n-            if short.is_empty() || slug.is_empty() {\n-                format!(\"https://slug.social/t/{tag}\")\n-            } else {\n-                format!(\"https://slug.social/r/{short}/{slug}/t/{tag}\")\n-            }\n+        } else if let Some(room_seg) = room_route_segment(room) {\n+            format!(\"https://slug.social/r/{room_seg}/t/{tag}\")\n         } else {\n             format!(\"https://slug.social/t/{tag}\")\n         })\n@@ -706,7 +728,7 @@ mod tests {\n     fn garden_private_room_prefixes_ontology() {\n         assert_eq!(\n             GardenItemUrl::from_storage_str(\"https://slug.social/~/topic/x\", \"9ab12cd/my-room\").as_str(),\n-            \"https://slug.social/r/9ab12cd/my-room/~/topic/x\"\n+            \"https://slug.social/r/9ab12cdmy-room/~/topic/x\"\n         );\n     }\n \n@@ -714,11 +736,11 @@ mod tests {\n     fn garden_private_room_ontology_root() {\n         assert_eq!(\n             GardenItemUrl::from_storage_str(\"https://slug.social/~\", \"9ab12cd/my-room\").as_str(),\n-            \"https://slug.social/r/9ab12cd/my-room/~\"\n+            \"https://slug.social/r/9ab12cdmy-room/~\"\n         );\n         assert_eq!(\n             GardenItemUrl::from_storage_str(\"https://slug.social/~/\", \"9ab12cd/my-room\").as_str(),\n-            \"https://slug.social/r/9ab12cd/my-room/~\"\n+            \"https://slug.social/r/9ab12cdmy-room/~\"\n         );\n     }\n \n@@ -727,7 +749,7 @@ mod tests {\n         let u = \"https://example.com/z\";\n         assert_eq!(\n             GardenItemUrl::from_storage_str(u, \"9ab12cd/my-room\").as_str(),\n-            \"https://slug.social/r/9ab12cd/my-room/-/example.com/z\"\n+            \"https://slug.social/r/9ab12cdmy-room/-/example.com/z\"\n         );\n     }\n \n@@ -739,7 +761,19 @@ mod tests {\n         );\n         assert_eq!(\n             ForumThreadUrl::from_room_tag(\"9ab12cd/my-room\", \"#debate\").as_str(),\n-            \"https://slug.social/r/9ab12cd/my-room/t/debate\"\n+            \"https://slug.social/r/9ab12cdmy-room/t/debate\"\n+        );\n+    }\n+\n+    #[test]\n+    fn canonicalize_youtube_short_links() {\n+        assert_eq!(\n+            canonicalize_item(\"https://youtu.be/dQw4w9WgXcQ\"),\n+            \"https://www.youtube.com/watch?v=dQw4w9WgXcQ\"\n+        );\n+        assert_eq!(\n+            canonicalize_item(\"-/youtu.be/dQw4w9WgXcQ\"),\n+            \"https://www.youtube.com/watch?v=dQw4w9WgXcQ\"\n         );\n     }\n \ndiff --git a/types/src/room_route.rs b/types/src/room_route.rs\nnew file mode 100644\nindex 0000000000000000000000000000000000000000..4f4780c88e30f2b28e2cfcd7aee713d39dbd1c66\n--- /dev/null\n+++ b/types/src/room_route.rs\n@@ -0,0 +1,56 @@\n+//! HTTP path encoding for private rooms: `/r/{short}{slug}` (short is fixed width).\n+\n+/// Byte length of the random `short` segment in `short/slug` room ids.\n+/// Must match room creation (`gen_short_id`) and [`super::paths`][] URL builders.\n+pub const ROOM_SHORT_ID_LEN: usize = 7;\n+\n+/// `ab12cde/my-room` → `ab12cdemy-room` for a single `/r/…` path segment.\n+pub fn room_route_segment(room_id: &str) -> Option<String> {\n+    let (short, slug) = room_id.split_once('/')?;\n+    if short.len() != ROOM_SHORT_ID_LEN || short.is_empty() || slug.is_empty() {\n+        return None;\n+    }\n+    if !short\n+        .bytes()\n+        .all(|b| matches!(b, b'0'..=b'9' | b'a'..=b'z'))\n+    {\n+        return None;\n+    }\n+    Some(format!(\"{short}{slug}\"))\n+}\n+\n+/// `/r/{short}{slug}` path segment → `short/slug` wire id (inverse of [`room_route_segment`]).\n+pub fn room_id_from_route_segment(seg: &str) -> Option<String> {\n+    if seg.len() <= ROOM_SHORT_ID_LEN {\n+        return None;\n+    }\n+    let (short, slug) = seg.split_at(ROOM_SHORT_ID_LEN);\n+    if short.is_empty() || slug.is_empty() {\n+        return None;\n+    }\n+    if !short\n+        .bytes()\n+        .all(|b| matches!(b, b'0'..=b'9' | b'a'..=b'z'))\n+    {\n+        return None;\n+    }\n+    Some(format!(\"{short}/{slug}\"))\n+}\n+\n+#[cfg(test)]\n+mod tests {\n+    use super::*;\n+\n+    #[test]\n+    fn round_trip_room_segment() {\n+        let id = \"9ab12cd/my-room\";\n+        let seg = room_route_segment(id).unwrap();\n+        assert_eq!(seg, \"9ab12cdmy-room\");\n+        assert_eq!(room_id_from_route_segment(&seg).as_deref(), Some(id));\n+    }\n+\n+    #[test]\n+    fn too_short_segment_rejected() {\n+        assert!(room_id_from_route_segment(\"9ab12cd\").is_none());\n+    }\n+}\ndiff --git a/types/src/url_identity_tests.rs b/types/src/url_identity_tests.rs\nnew file mode 100644\nindex 0000000000000000000000000000000000000000..e2ff0a9a64a88049e31f20979c703777df6a9b65\n--- /dev/null\n+++ b/types/src/url_identity_tests.rs\n@@ -0,0 +1,126 @@\n+//! How `url::Url` behaves as `HashMap` keys (`Eq` + `Hash`).\n+//!\n+//! If `ItemId::External` stores `Url`, these tests are the contract you are buying into\n+//! (or the baseline before you add a custom normalization layer).\n+\n+use std::collections::HashMap;\n+use std::hash::{Hash, Hasher};\n+use url::Url;\n+\n+fn hash_one(url: &Url) -> u64 {\n+    let mut h = std::collections::hash_map::DefaultHasher::new();\n+    url.hash(&mut h);\n+    h.finish()\n+}\n+\n+#[test]\n+fn identical_parse_strings_are_eq_and_share_hash_bucket() {\n+    let a = Url::parse(\"https://example.com/path\").unwrap();\n+    let b = Url::parse(\"https://example.com/path\").unwrap();\n+    assert_eq!(a, b);\n+    assert_eq!(hash_one(&a), hash_one(&b));\n+\n+    let mut m: HashMap<Url, u32> = HashMap::new();\n+    m.insert(a, 1);\n+    *m.entry(b).or_default() += 10;\n+    assert_eq!(m.len(), 1);\n+    assert_eq!(m[&Url::parse(\"https://example.com/path\").unwrap()], 11);\n+}\n+\n+#[test]\n+fn host_is_ascii_lowercase_in_eq() {\n+    let lower = Url::parse(\"https://examplE.com/\").unwrap();\n+    let upper = Url::parse(\"https://EXAMPLE.com/\").unwrap();\n+    assert_eq!(lower, upper);\n+    assert_eq!(hash_one(&lower), hash_one(&upper));\n+}\n+\n+#[test]\n+fn path_space_normalizes_to_percent_encoding_so_forms_merge() {\n+    let encoded = Url::parse(\"https://example.com/a%20b\").unwrap();\n+    let decoded = Url::parse(\"https://example.com/a b\").unwrap();\n+    // Parser normalizes both to the same internal path (`/a%20b`).\n+    assert_eq!(encoded, decoded);\n+    assert_eq!(hash_one(&encoded), hash_one(&decoded));\n+\n+    let mut m: HashMap<Url, &str> = HashMap::new();\n+    m.insert(encoded, \"first\");\n+    assert_eq!(m.insert(decoded, \"second\"), Some(\"first\"));\n+    assert_eq!(m.len(), 1);\n+    assert_eq!(m.values().next().copied(), Some(\"second\"));\n+}\n+\n+#[test]\n+fn encoded_slash_in_segment_stays_distinct_from_real_path_separator() {\n+    let encoded = Url::parse(\"https://example.com/a%2Fb\").unwrap();\n+    let real_slash = Url::parse(\"https://example.com/a/b\").unwrap();\n+    assert_ne!(encoded, real_slash);\n+    assert_ne!(hash_one(&encoded), hash_one(&real_slash));\n+}\n+\n+#[test]\n+fn trailing_slash_on_path_is_significant_for_eq() {\n+    let with_slash = Url::parse(\"https://example.com/foo/\").unwrap();\n+    let no_slash = Url::parse(\"https://example.com/foo\").unwrap();\n+    assert_ne!(with_slash, no_slash);\n+    assert_ne!(hash_one(&with_slash), hash_one(&no_slash));\n+}\n+\n+#[test]\n+fn default_http_port_80_is_normalized_in_representation() {\n+    let explicit = Url::parse(\"http://example.com:80/\").unwrap();\n+    let implicit = Url::parse(\"http://example.com/\").unwrap();\n+    assert_eq!(explicit, implicit);\n+    assert_eq!(hash_one(&explicit), hash_one(&implicit));\n+}\n+\n+#[test]\n+fn default_https_port_443_is_normalized() {\n+    let explicit = Url::parse(\"https://example.com:443/foo\").unwrap();\n+    let implicit = Url::parse(\"https://example.com/foo\").unwrap();\n+    assert_eq!(explicit, implicit);\n+}\n+\n+#[test]\n+fn non_default_port_is_part_of_identity() {\n+    let a = Url::parse(\"https://example.com:444/\").unwrap();\n+    let b = Url::parse(\"https://example.com:445/\").unwrap();\n+    assert_ne!(a, b);\n+}\n+\n+#[test]\n+fn empty_path_vs_slash_only_path_may_differ() {\n+    let root = Url::parse(\"https://example.com\").unwrap();\n+    let slash = Url::parse(\"https://example.com/\").unwrap();\n+    // Both serialize to `https://example.com/` in practice for this crate — verify.\n+    assert_eq!(root, slash, \"document: root and trailing-slash-only merge for this parser\");\n+}\n+\n+#[test]\n+fn scheme_case_is_normalized_to_lowercase() {\n+    let lower = Url::parse(\"https://example.com/\").unwrap();\n+    let upper = Url::parse(\"HTTPS://example.com/\").unwrap();\n+    assert_eq!(lower, upper);\n+}\n+\n+#[test]\n+fn fragment_is_part_of_eq_and_hash() {\n+    let no_frag = Url::parse(\"https://example.com/a\").unwrap();\n+    let frag = Url::parse(\"https://example.com/a#section\").unwrap();\n+    assert_ne!(\n+        no_frag, frag,\n+        \"#fragment is included in PartialEq — anchors are different HashMap keys\"\n+    );\n+    assert_ne!(hash_one(&no_frag), hash_one(&frag));\n+}\n+\n+#[test]\n+fn query_order_and_encoding_can_split_identity() {\n+    let a = Url::parse(\"https://example.com/?b=2&a=1\").unwrap();\n+    let b = Url::parse(\"https://example.com/?a=1&b=2\").unwrap();\n+    assert_ne!(a, b, \"query pairs order is preserved in serialization\");\n+\n+    let plus = Url::parse(\"https://example.com/?q=a+b\").unwrap();\n+    let encoded = Url::parse(\"https://example.com/?q=a%20b\").unwrap();\n+    assert_ne!(plus, encoded, \"space as + vs %20 — different keys unless normalized\");\n+}\ndiff --git a/types/src/url_normalize.rs b/types/src/url_normalize.rs\nnew file mode 100644\nindex 0000000000000000000000000000000000000000..d5bc913f33ad29cd0cd1c7158e28e4fefdbf5f5d\n--- /dev/null\n+++ b/types/src/url_normalize.rs\n@@ -0,0 +1,234 @@\n+//! Normalization for external `http(s)://` item identity (not slug tilde ontology).\n+//!\n+//! Policy (intentional, extend here as new domains need treatment):\n+//! - Query pairs sorted lexicographically by **lowercased** key, then value.\n+//! - YouTube family → stable `www.youtube.com` shapes where possible.\n+\n+use url::Url;\n+\n+/// Whether `-/` → `https://…` path segments should keep original casing (YouTube video IDs are\n+/// case-sensitive).\n+pub(crate) fn host_preserves_dash_path_case(host: &str) -> bool {\n+    let h = host.trim().to_ascii_lowercase();\n+    let h = h.strip_prefix(\"www.\").unwrap_or(h.as_str());\n+    matches!(\n+        h,\n+        \"youtu.be\" | \"youtube.com\" | \"m.youtube.com\" | \"music.youtube.com\"\n+    )\n+}\n+\n+/// Normalize external http(s) URLs for stable [`super::paths::canonicalize_item`] output.\n+pub fn normalize_http_identity_url(s: &str) -> Option<String> {\n+    let mut u = Url::parse(s).ok()?;\n+    if !matches!(u.scheme(), \"http\" | \"https\") {\n+        return None;\n+    }\n+    rewrite_youtube(&mut u);\n+    sort_query_pairs(&mut u);\n+    Some(u.to_string())\n+}\n+\n+fn base_host(host: &str) -> String {\n+    let lower = host.to_ascii_lowercase();\n+    lower\n+        .strip_prefix(\"www.\")\n+        .unwrap_or(lower.as_str())\n+        .to_string()\n+}\n+\n+fn rewrite_youtube(u: &mut Url) {\n+    let Some(host_raw) = u.host_str() else {\n+        return;\n+    };\n+    let base = base_host(host_raw);\n+    let path = u.path().to_string();\n+\n+    match base.as_str() {\n+        \"youtu.be\" => {\n+            let id = path.trim_start_matches('/').split('/').next().unwrap_or(\"\").to_string();\n+            if id.is_empty() {\n+                return;\n+            }\n+            let saved: Vec<(String, String)> = u.query_pairs().into_owned().collect();\n+            let Ok(mut out) = Url::parse(&format!(\"https://www.youtube.com/watch?v={id}\")) else {\n+                return;\n+            };\n+            {\n+                let mut q = out.query_pairs_mut();\n+                for (k, v) in saved {\n+                    if k.eq_ignore_ascii_case(\"v\") {\n+                        continue;\n+                    }\n+                    q.append_pair(&k, &v);\n+                }\n+            }\n+            *u = out;\n+        }\n+        \"youtube.com\" | \"m.youtube.com\" => {\n+            if base == \"m.youtube.com\" {\n+                let _ = u.set_host(Some(\"www.youtube.com\"));\n+            }\n+            if path.starts_with(\"/embed/\") {\n+                let id = path\n+                    .strip_prefix(\"/embed/\")\n+                    .unwrap_or(\"\")\n+                    .trim_matches('/')\n+                    .split('/')\n+                    .next()\n+                    .unwrap_or(\"\")\n+                    .to_string();\n+                if id.is_empty() {\n+                    return;\n+                }\n+                let saved: Vec<(String, String)> = u.query_pairs().into_owned().collect();\n+                let Ok(mut out) = Url::parse(&format!(\"https://www.youtube.com/watch?v={id}\"))\n+                else {\n+                    return;\n+                };\n+                {\n+                    let mut q = out.query_pairs_mut();\n+                    for (k, v) in saved {\n+                        if k.eq_ignore_ascii_case(\"v\") {\n+                            continue;\n+                        }\n+                        q.append_pair(&k, &v);\n+                    }\n+                }\n+                *u = out;\n+                return;\n+            }\n+            if path.starts_with(\"/v/\") {\n+                let id = path\n+                    .strip_prefix(\"/v/\")\n+                    .unwrap_or(\"\")\n+                    .trim_matches('/')\n+                    .split('/')\n+                    .next()\n+                    .unwrap_or(\"\")\n+                    .to_string();\n+                if id.is_empty() {\n+                    return;\n+                }\n+                let saved: Vec<(String, String)> = u.query_pairs().into_owned().collect();\n+                let Ok(mut out) = Url::parse(&format!(\"https://www.youtube.com/watch?v={id}\"))\n+                else {\n+                    return;\n+                };\n+                {\n+                    let mut q = out.query_pairs_mut();\n+                    for (k, v) in saved {\n+                        if k.eq_ignore_ascii_case(\"v\") {\n+                            continue;\n+                        }\n+                        q.append_pair(&k, &v);\n+                    }\n+                }\n+                *u = out;\n+                return;\n+            }\n+            if path.starts_with(\"/watch\") {\n+                let _ = u.set_host(Some(\"www.youtube.com\"));\n+                return;\n+            }\n+            if path.starts_with(\"/shorts/\") {\n+                let id = path\n+                    .strip_prefix(\"/shorts/\")\n+                    .unwrap_or(\"\")\n+                    .trim_matches('/')\n+                    .split('/')\n+                    .next()\n+                    .unwrap_or(\"\")\n+                    .to_string();\n+                if id.is_empty() {\n+                    return;\n+                }\n+                let saved: Vec<(String, String)> = u.query_pairs().into_owned().collect();\n+                let Ok(mut out) = Url::parse(&format!(\"https://www.youtube.com/shorts/{id}\"))\n+                else {\n+                    return;\n+                };\n+                {\n+                    let mut q = out.query_pairs_mut();\n+                    for (k, v) in saved {\n+                        q.append_pair(&k, &v);\n+                    }\n+                }\n+                *u = out;\n+                return;\n+            }\n+            let _ = u.set_host(Some(\"www.youtube.com\"));\n+        }\n+        \"music.youtube.com\" => {}\n+        _ => {}\n+    }\n+}\n+\n+fn sort_query_pairs(u: &mut Url) {\n+    let pairs: Vec<(String, String)> = u.query_pairs().into_owned().collect();\n+    if pairs.is_empty() {\n+        u.set_query(None);\n+        return;\n+    }\n+    let mut pairs = pairs;\n+    pairs.sort_by(|a, b| {\n+        a.0.to_ascii_lowercase()\n+            .cmp(&b.0.to_ascii_lowercase())\n+            .then_with(|| a.1.cmp(&b.1))\n+    });\n+    u.set_query(None);\n+    {\n+        let mut q = u.query_pairs_mut();\n+        for (k, v) in pairs {\n+            q.append_pair(&k, &v);\n+        }\n+    }\n+}\n+\n+#[cfg(test)]\n+mod tests {\n+    use super::*;\n+\n+    #[test]\n+    fn youtube_youtu_be_to_watch() {\n+        assert_eq!(\n+            normalize_http_identity_url(\"https://youtu.be/dQw4w9WgXcQ\").as_deref(),\n+            Some(\"https://www.youtube.com/watch?v=dQw4w9WgXcQ\")\n+        );\n+    }\n+\n+    #[test]\n+    fn youtube_watch_query_sorted() {\n+        assert_eq!(\n+            normalize_http_identity_url(\"https://youtube.com/watch?v=Z&a=1&b=2\").as_deref(),\n+            Some(\"https://www.youtube.com/watch?a=1&b=2&v=Z\")\n+        );\n+        assert_eq!(\n+            normalize_http_identity_url(\"https://youtube.com/watch?b=2&a=1&v=Z\").as_deref(),\n+            Some(\"https://www.youtube.com/watch?a=1&b=2&v=Z\")\n+        );\n+    }\n+\n+    #[test]\n+    fn youtube_embed_to_watch() {\n+        assert_eq!(\n+            normalize_http_identity_url(\"https://www.youtube.com/embed/dQw4w9WgXcQ\").as_deref(),\n+            Some(\"https://www.youtube.com/watch?v=dQw4w9WgXcQ\")\n+        );\n+    }\n+\n+    #[test]\n+    fn youtube_shorts_host() {\n+        assert_eq!(\n+            normalize_http_identity_url(\"https://youtube.com/shorts/AbCdEfGhIjK\").as_deref(),\n+            Some(\"https://www.youtube.com/shorts/AbCdEfGhIjK\")\n+        );\n+    }\n+\n+    #[test]\n+    fn arbitrary_query_sorted() {\n+        assert_eq!(\n+            normalize_http_identity_url(\"https://example.com/x?z=1&a=2\").as_deref(),\n+            Some(\"https://example.com/x?a=2&z=1\")\n+        );\n+    }\n+}\n\n\nSide B — contributor: tommy-mor\nSide B — commit message:\n[9e20d06c] Add sorterc dev tool for offline DSL compile and JSONL lint.\n\nIntroduce a workspace-only binary that validates .sorter files into ranking JSON and scans events.jsonl for corrupt or unreplayable ingests.\n\nCo-authored-by: Cursor <cursoragent@cursor.com>\n\nSide B — unified diff (full patch):\ndiff --git a/Cargo.lock b/Cargo.lock\nindex bf8153d9c723af97122c9ffdd4a7cfe82e853bb6..a07734f089b466440c3ae6fc1087ce85fc24ce62 100644\n--- a/Cargo.lock\n+++ b/Cargo.lock\n@@ -1826,6 +1826,17 @@ dependencies = [\n  \"windows-sys 0.60.2\",\n ]\n \n+[[package]]\n+name = \"sorterc\"\n+version = \"0.0.1\"\n+dependencies = [\n+ \"anyhow\",\n+ \"clap\",\n+ \"serde\",\n+ \"serde_json\",\n+ \"slugsocial-server\",\n+]\n+\n [[package]]\n name = \"spin\"\n version = \"0.9.8\"\ndiff --git a/Cargo.toml b/Cargo.toml\nindex 149cbf07901eab57c593184ff8719a75d530f1da..25337acdd61e44b20f354c78fed4a88caf896280 100644\n--- a/Cargo.toml\n+++ b/Cargo.toml\n@@ -1,5 +1,5 @@\n [workspace]\n-members = [\"server\", \"cli\"]\n+members = [\"server\", \"cli\", \"sorterc\"]\n resolver = \"2\"\n \n \ndiff --git a/agents.md b/agents.md\nindex d8b801e454fdf37e7ac6038b91a69f83b0746d59..ce646ed3cd7123be4732dccec4a6800467e651e7 100644\n--- a/agents.md\n+++ b/agents.md\n@@ -93,6 +93,17 @@ SLUG_GOOGLE_CLIENT_SECRET=mock\n \n After OAuth completes, the pending-session poll returns a `slug_…` bearer token for API calls.\n \n+### Dev-only offline tooling\n+\n+**`sorterc`** — workspace binary, not published via npm. Compiles `.sorter` files and lints `events.jsonl` without a server:\n+\n+```\n+cargo run -p sorterc -- compile path/to/doc.sorter [--base events.jsonl] [--room public] [--pretty]\n+cargo run -p sorterc -- scan path/to/events.jsonl [--pretty]\n+```\n+\n+`compile` validates DSL, simulates ingest against empty (or `--base`) reducer state, and prints JSON rankings. `scan` reports corrupt JSONL lines and ingests that fail DSL replay.\n+\n ### Testing\n \n - **Rust tests:** `cargo nextest run --workspace` (163 tests; requires `cargo-nextest`)\ndiff --git a/server/src/lib.rs b/server/src/lib.rs\nindex c1d477d21aea03aff00e6f0689b0b4379d0d68d2..ad8e31099c807fb5844acb16cd5086a2f19327a7 100644\n--- a/server/src/lib.rs\n+++ b/server/src/lib.rs\n@@ -10,6 +10,7 @@ pub mod form_template;\n pub mod html;\n pub mod identity;\n pub mod middleware;\n+pub mod offline;\n pub mod path_types;\n pub mod ranking;\n pub mod reducer;\ndiff --git a/server/src/offline.rs b/server/src/offline.rs\nnew file mode 100644\nindex 0000000000000000000000000000000000000000..54ad0ded096a305ef8454ab2cdd1c3af71b14f5d\n--- /dev/null\n+++ b/server/src/offline.rs\n@@ -0,0 +1,333 @@\n+//! Offline `.sorter` compilation and JSONL diagnostics (no network, no auth).\n+\n+use std::collections::HashSet;\n+use std::path::Path;\n+\n+use serde::Serialize;\n+use slug_types::{CheckScopeRanking, RankComponent, RankRow, paths::GardenItemUrl};\n+\n+use crate::{\n+    api::{resolve_item, validate_ingest_document},\n+    dsl,\n+    events::{Event, Ingest},\n+    path_types::ItemId,\n+    reducer::{ReducerState, ScopeId, scope_from_room_wire},\n+    scope_rank::build_children_rankings,\n+};\n+\n+#[derive(Debug, Clone, Serialize)]\n+pub struct CompileStats {\n+    pub items: usize,\n+    pub votes: usize,\n+    pub prose_blocks: usize,\n+}\n+\n+#[derive(Debug, Serialize)]\n+pub struct CompileResult {\n+    pub ok: bool,\n+    pub threads: Vec<String>,\n+    pub rankings: Vec<CheckScopeRanking>,\n+    pub stats: CompileStats,\n+}\n+\n+#[derive(Debug, Clone, Serialize)]\n+pub struct CompileError {\n+    pub ok: bool,\n+    pub error: String,\n+    #[serde(skip_serializing_if = \"Option::is_none\")]\n+    pub hint: Option<String>,\n+}\n+\n+#[derive(Debug, Clone, Serialize)]\n+pub struct BadJsonLine {\n+    pub line: usize,\n+    pub message: String,\n+}\n+\n+#[derive(Debug, Clone, Serialize)]\n+pub struct MalformedIngest {\n+    pub line: usize,\n+    pub id: String,\n+    pub room_id: String,\n+    pub thread_tag: String,\n+    pub reason: String,\n+}\n+\n+#[derive(Debug, Clone, Serialize)]\n+pub struct ScanResult {\n+    pub ok: bool,\n+    pub path: String,\n+    pub total_lines: usize,\n+    pub parsed_events: usize,\n+    pub bad_json_lines: Vec<BadJsonLine>,\n+    pub malformed_ingests: Vec<MalformedIngest>,\n+    pub skipped_ingests: usize,\n+}\n+\n+fn document_stats(doc: &dsl::Document) -> CompileStats {\n+    let mut items = 0usize;\n+    let mut votes = 0usize;\n+    let mut prose_blocks = 0usize;\n+    for stmt in &doc.statements {\n+        match stmt {\n+            dsl::Stmt::Item { .. } => items += 1,\n+            dsl::Stmt::Vote { .. } => votes += 1,\n+            dsl::Stmt::Prose { .. } => prose_blocks += 1,\n+        }\n+    }\n+    CompileStats {\n+        items,\n+        votes,\n+        prose_blocks,\n+    }\n+}\n+\n+fn threads_in_document(text: &str) -> Vec<String> {\n+    let mut out = HashSet::new();\n+    for line in text.lines() {\n+        let trimmed = line.trim();\n+        if !trimmed.starts_with('#') {\n+            continue;\n+        }\n+        let rest = trimmed.trim_start_matches('#').trim();\n+        if rest.is_empty() {\n+            continue;\n+        }\n+        let tag = rest.split_whitespace().next().unwrap_or(rest);\n+        let tag = tag.split(':').next().unwrap_or(tag).trim();\n+        if tag.is_empty() {\n+            continue;\n+        }\n+        out.insert(format!(\"#{}\", crate::canonical_path::canonicalize_tag(tag)));\n+    }\n+    let mut tags: Vec<String> = out.into_iter().collect();\n+    tags.sort();\n+    tags\n+}\n+\n+fn voted_parent_scopes(doc: &dsl::Document) -> Vec<ItemId> {\n+    let mut parents = HashSet::new();\n+    for stmt in &doc.statements {\n+        if let dsl::Stmt::Vote { item1, item2, .. } = stmt {\n+            if let (Ok(a), Ok(b)) = (resolve_item(item1), resolve_item(item2)) {\n+                if let Some(p) = a.parent() {\n+                    parents.insert(p);\n+                }\n+                if let Some(p) = b.parent() {\n+                    parents.insert(p);\n+                }\n+            }\n+        }\n+    }\n+    let mut out: Vec<ItemId> = parents.into_iter().collect();\n+    out.sort();\n+    out\n+}\n+\n+fn rankings_for_simulated(\n+    simulated: &ReducerState,\n+    scope: &ScopeId,\n+    room_wire: &str,\n+    doc: &dsl::Document,\n+) -> Vec<CheckScopeRanking> {\n+    voted_parent_scopes(doc)\n+        .iter()\n+        .map(|parent| {\n+            let scoped_content = simulated\n+                .content_for_scope(&scope)\n+                .unwrap_or_else(|| simulated.public());\n+            let scoped = build_children_rankings(scoped_content, parent);\n+            let components: Vec<RankComponent> = scoped\n+                .component_rankings\n+                .into_iter()\n+                .map(|comp| RankComponent {\n+                    pairs: comp.pairs,\n+                    ranking: comp\n+                        .ranked\n+                        .into_iter()\n+                        .map(|r| RankRow {\n+                            item: GardenItemUrl::from_stored(&r.item, room_wire),\n+                            score: r.score,\n+                            percent: None,\n+                        })\n+                        .collect(),\n+                })\n+                .collect();\n+            CheckScopeRanking {\n+                parent: GardenItemUrl::from_stored(parent, room_wire).into_inner(),\n+                components,\n+                unranked_items: scoped\n+                    .unranked_items\n+                    .into_iter()\n+                    .map(|it| GardenItemUrl::from_stored(&it, room_wire))\n+                    .collect(),\n+            }\n+        })\n+        .collect()\n+}\n+\n+/// Validate and simulate one `.sorter` document against optional base reducer state.\n+pub fn compile_document(\n+    base: &ReducerState,\n+    room: &str,\n+    text: &str,\n+) -> Result<CompileResult, CompileError> {\n+    let room_key = room.trim();\n+    let scope = scope_from_room_wire(room_key);\n+    let validated = validate_ingest_document(base, text, &scope).map_err(|(_, message, hint)| {\n+        CompileError {\n+            ok: false,\n+            error: message,\n+            hint,\n+        }\n+    })?;\n+\n+    let event = Event::Ingest(Ingest {\n+        ts: validated.ts,\n+        id: uuid::Uuid::new_v4().to_string(),\n+        raw: validated.raw_text.clone(),\n+        principal: \"offline\".to_string(),\n+        delegate: None,\n+        room_id: room_key.to_string(),\n+        thread_tag: \"offline\".to_string(),\n+    });\n+\n+    let mut simulated = base.clone();\n+    simulated.apply_event(event);\n+\n+    Ok(CompileResult {\n+        ok: true,\n+        threads: threads_in_document(text),\n+        rankings: rankings_for_simulated(&simulated, &scope, room_key, &validated.doc),\n+        stats: document_stats(&validated.doc),\n+    })\n+}\n+\n+fn ingest_parse_error(raw: &str) -> Option<String> {\n+    dsl::parse_full(raw).err().map(|e| e.to_string())\n+}\n+\n+fn load_events_from_jsonl(path: &Path) -> Result<(Vec<(usize, Event)>, Vec<BadJsonLine>), std::io::Error> {\n+    let text = std::fs::read_to_string(path)?;\n+    let mut events = Vec::new();\n+    let mut bad_json_lines = Vec::new();\n+    for (idx, line) in text.lines().enumerate() {\n+        let line_no = idx + 1;\n+        let trimmed = line.trim();\n+        if trimmed.is_empty() {\n+            continue;\n+        }\n+        match serde_json::from_str::<Event>(trimmed) {\n+            Ok(ev) => events.push((line_no, ev)),\n+            Err(e) => bad_json_lines.push(BadJsonLine {\n+                line: line_no,\n+                message: e.to_string(),\n+            }),\n+        }\n+    }\n+    Ok((events, bad_json_lines))\n+}\n+\n+/// Replay a JSONL event log into reducer state (same rules as server boot).\n+pub fn load_reducer_from_jsonl(path: &Path) -> Result<(ReducerState, Vec<BadJsonLine>), std::io::Error> {\n+    let (events, bad_json_lines) = load_events_from_jsonl(path)?;\n+    let mut state = ReducerState::default();\n+    for (_line_no, ev) in events {\n+        state.apply_event(ev);\n+    }\n+    Ok((state, bad_json_lines))\n+}\n+\n+/// Scan an events.jsonl for corrupt JSON lines and ingests that fail DSL replay.\n+pub fn scan_jsonl(path: &Path) -> Result<ScanResult, std::io::Error> {\n+    let text = std::fs::read_to_string(path)?;\n+    let total_lines = text.lines().count();\n+    let (events, bad_json_lines) = load_events_from_jsonl(path)?;\n+\n+    let mut malformed_ingests = Vec::new();\n+    let mut skipped_ingests = 0usize;\n+    let mut state = ReducerState::default();\n+    let parsed_events = events.len();\n+\n+    for (line_no, ev) in events {\n+        if let Event::Ingest(ref ing) = ev {\n+            if let Some(reason) = ingest_parse_error(&ing.raw) {\n+                malformed_ingests.push(MalformedIngest {\n+                    line: line_no,\n+                    id: ing.id.clone(),\n+                    room_id: ing.room_id.clone(),\n+                    thread_tag: ing.thread_tag.clone(),\n+                    reason,\n+                });\n+            }\n+            let before = state.ingests_by_id.len();\n+            state.apply_event(ev);\n+            if state.ingests_by_id.len() == before {\n+                skipped_ingests += 1;\n+            }\n+        } else {\n+            state.apply_event(ev);\n+        }\n+    }\n+\n+    let ok = bad_json_lines.is_empty() && malformed_ingests.is_empty() && skipped_ingests == 0;\n+\n+    Ok(ScanResult {\n+        ok,\n+        path: path.display().to_string(),\n+        total_lines,\n+        parsed_events,\n+        bad_json_lines,\n+        malformed_ingests,\n+        skipped_ingests,\n+    })\n+}\n+\n+#[cfg(test)]\n+mod tests {\n+    use super::*;\n+\n+    const TUTORIAL: &str = include_str!(\"../tests/fixtures/tutorial.sorter\");\n+\n+    #[test]\n+    fn compile_tutorial_fixture_emits_rankings() {\n+        let result = compile_document(&ReducerState::default(), \"public\", TUTORIAL).unwrap();\n+        assert!(result.ok);\n+        assert!(!result.threads.is_empty());\n+        assert!(result.stats.items >= 6);\n+        assert!(result.stats.votes >= 6);\n+        assert!(!result.rankings.is_empty());\n+    }\n+\n+    #[test]\n+    fn compile_rejects_vote_on_missing_item() {\n+        let err = compile_document(\n+            &ReducerState::default(),\n+            \"public\",\n+            \"{ reason }\\n~/missing/a 2:1 ~/missing/b\",\n+        )\n+        .unwrap_err();\n+        assert!(!err.ok);\n+        assert!(err.error.contains(\"undefined\"));\n+    }\n+\n+    #[test]\n+    fn scan_empty_jsonl_is_ok() {\n+        let dir = tempfile::tempdir().unwrap();\n+        let path = dir.path().join(\"events.jsonl\");\n+        std::fs::write(&path, \"\").unwrap();\n+        let report = scan_jsonl(&path).unwrap();\n+        assert!(report.ok);\n+        assert!(report.bad_json_lines.is_empty());\n+    }\n+\n+    #[test]\n+    fn scan_reports_bad_json_line() {\n+        let dir = tempfile::tempdir().unwrap();\n+        let path = dir.path().join(\"events.jsonl\");\n+        std::fs::write(&path, \"{not json}\\n\").unwrap();\n+        let report = scan_jsonl(&path).unwrap();\n+        assert!(!report.ok);\n+        assert_eq!(report.bad_json_lines.len(), 1);\n+    }\n+}\ndiff --git a/sorterc/Cargo.toml b/sorterc/Cargo.toml\nnew file mode 100644\nindex 0000000000000000000000000000000000000000..92d477aff9b53291fb1a266db83065c1c800791d\n--- /dev/null\n+++ b/sorterc/Cargo.toml\n@@ -0,0 +1,18 @@\n+[package]\n+name = \"sorterc\"\n+version = \"0.0.1\"\n+edition = \"2021\"\n+license = \"MIT\"\n+publish = false\n+description = \"Offline .sorter compiler and events.jsonl linter (dev only)\"\n+\n+[[bin]]\n+name = \"sorterc\"\n+path = \"src/main.rs\"\n+\n+[dependencies]\n+anyhow = \"1\"\n+clap = { version = \"4\", features = [\"derive\"] }\n+serde = { version = \"1\", features = [\"derive\"] }\n+serde_json = \"1\"\n+slugsocial-server = { path = \"../server\" }\ndiff --git a/sorterc/readme.md b/sorterc/readme.md\nnew file mode 100644\nindex 0000000000000000000000000000000000000000..1ebcc3fc935541ea9e47e0458ec67a750fe19fff\n--- /dev/null\n+++ b/sorterc/readme.md\n@@ -0,0 +1,92 @@\n+# sorterc\n+\n+Dev-only offline tooling for the slug `.sorter` DSL and `events.jsonl` event log.\n+\n+`sorterc` is **not** published via npm and does not talk to slug.social. It reuses the same parser, validator, and ranking code as the server, but runs entirely on local files.\n+\n+## Build\n+\n+From the repo root:\n+\n+```bash\n+cargo build -p sorterc\n+cargo run -p sorterc -- --help\n+```\n+\n+## Commands\n+\n+### `compile` — evaluate a `.sorter` document\n+\n+Reads a `.sorter` file (or `-` for stdin), validates the DSL, simulates one ingest against reducer state, and prints JSON rankings to stdout.\n+\n+```bash\n+cargo run -p sorterc -- compile path/to/doc.sorter\n+cargo run -p sorterc -- compile path/to/doc.sorter --pretty\n+cargo run -p sorterc -- compile - --pretty                    # stdin\n+cargo run -p sorterc -- compile doc.sorter --base events.jsonl  # seed garden from log\n+cargo run -p sorterc -- compile doc.sorter --room public         # default room\n+```\n+\n+**Flags**\n+\n+| Flag | Description |\n+|------|-------------|\n+| `--base PATH` | Replay an `events.jsonl` first, then compile against that garden state |\n+| `--room ID` | Room wire id (`public` or private room id). Default: `public` |\n+| `--pretty` | Pretty-print JSON |\n+\n+**Success output** (shape):\n+\n+```json\n+{\n+  \"ok\": true,\n+  \"threads\": [\"#my-thread\"],\n+  \"rankings\": [ … ],\n+  \"stats\": { \"items\": 3, \"votes\": 2, \"prose_blocks\": 5 }\n+}\n+```\n+\n+Rankings use the same structure as the server's dry-run check: parent scope, connected components, scores, unranked items.\n+\n+**Error output** exits with code 1:\n+\n+```json\n+{\n+  \"ok\": false,\n+  \"error\": \"parse error\",\n+  \"hint\": \"…\"\n+}\n+```\n+\n+### `scan` — lint an `events.jsonl`\n+\n+Reads a JSONL event log and reports problems without starting a server.\n+\n+```bash\n+cargo run -p sorterc -- scan events.jsonl\n+cargo run -p sorterc -- scan events.jsonl --pretty\n+```\n+\n+Reports:\n+\n+- **bad JSON lines** — lines that are not valid JSON\n+- **malformed ingests** — ingest events whose `raw` DSL fails to parse\n+- **skipped ingests** — ingests dropped during replay (same behavior as server boot)\n+\n+Exits 0 when clean, 1 when any issue is found.\n+\n+## Typical uses\n+\n+- Iterate on `.sorter` files in an editor and pipe through `compile` to see rankings instantly\n+- Verify a downloaded or edited `events.jsonl` before uploading to Fly\n+- Debug \"malformed ingest\" warnings from production boot logs\n+- CI or pre-commit checks on fixture docs (no OAuth, no network)\n+\n+## What it does not do\n+\n+- Post to slug.social or append to a live log\n+- Authenticate users or bind agents\n+- Run browser/UI tests\n+- Replace `slugsocial public check` for operators who want the full RPC path against a running server\n+\n+For live server dry-run against current garden state, use `npx slugsocial public check` or `POST /try/check` in the browser.\ndiff --git a/sorterc/src/main.rs b/sorterc/src/main.rs\nnew file mode 100644\nindex 0000000000000000000000000000000000000000..71382c180085cb0ad71043c852f8db5d3a48a284\n--- /dev/null\n+++ b/sorterc/src/main.rs\n@@ -0,0 +1,117 @@\n+use std::path::{Path, PathBuf};\n+\n+use anyhow::{bail, Context, Result};\n+use clap::{Parser, Subcommand};\n+use slugsocial_server::{\n+    offline::{self, CompileError, CompileResult, ScanResult},\n+    reducer::ReducerState,\n+};\n+\n+#[derive(Parser)]\n+#[command(\n+    name = \"sorterc\",\n+    about = \"Offline .sorter compiler and events.jsonl linter (dev only)\",\n+    version\n+)]\n+struct Cli {\n+    #[command(subcommand)]\n+    cmd: Command,\n+}\n+\n+#[derive(Subcommand)]\n+enum Command {\n+    /// Parse and simulate a .sorter document; emit ranking JSON to stdout.\n+    Compile {\n+        /// `.sorter` file, or `-` for stdin.\n+        file: PathBuf,\n+        /// Room wire id (`public` or private room id).\n+        #[arg(long, default_value = \"public\")]\n+        room: String,\n+        /// Optional events.jsonl to replay before compiling (seed garden state).\n+        #[arg(long)]\n+        base: Option<PathBuf>,\n+        /// Pretty-print JSON.\n+        #[arg(long)]\n+        pretty: bool,\n+    },\n+    /// Scan an events.jsonl for corrupt JSON lines and malformed ingests.\n+    Scan {\n+        file: PathBuf,\n+        #[arg(long)]\n+        pretty: bool,\n+    },\n+}\n+\n+fn read_input(path: &Path) -> Result<String> {\n+    if path.as_os_str() == \"-\" {\n+        use std::io::Read;\n+        let mut buf = String::new();\n+        std::io::stdin().read_to_string(&mut buf)?;\n+        Ok(buf)\n+    } else {\n+        std::fs::read_to_string(path)\n+            .with_context(|| format!(\"read {}\", path.display()))\n+    }\n+}\n+\n+fn load_base_state(base: Option<&Path>) -> Result<ReducerState> {\n+    let Some(path) = base else {\n+        return Ok(ReducerState::default());\n+    };\n+    let (state, bad_lines) = offline::load_reducer_from_jsonl(path)\n+        .with_context(|| format!(\"load base jsonl {}\", path.display()))?;\n+    if !bad_lines.is_empty() {\n+        bail!(\n+            \"base jsonl has {} corrupt line(s); fix or omit --base\",\n+            bad_lines.len()\n+        );\n+    }\n+    Ok(state)\n+}\n+\n+fn print_json<T: serde::Serialize>(value: &T, pretty: bool) -> Result<()> {\n+    if pretty {\n+        println!(\"{}\", serde_json::to_string_pretty(value)?);\n+    } else {\n+        println!(\"{}\", serde_json::to_string(value)?);\n+    }\n+    Ok(())\n+}\n+\n+fn run_compile(file: PathBuf, room: String, base: Option<PathBuf>, pretty: bool) -> Result<()> {\n+    let text = read_input(&file)?;\n+    let base_state = load_base_state(base.as_deref())?;\n+    match offline::compile_document(&base_state, &room, &text) {\n+        Ok(result) => {\n+            print_json::<CompileResult>(&result, pretty)?;\n+            Ok(())\n+        }\n+        Err(err) => {\n+            print_json::<CompileError>(&err, pretty)?;\n+            std::process::exit(1);\n+        }\n+    }\n+}\n+\n+fn run_scan(file: PathBuf, pretty: bool) -> Result<()> {\n+    let report = offline::scan_jsonl(&file)\n+        .with_context(|| format!(\"scan {}\", file.display()))?;\n+    print_json::<ScanResult>(&report, pretty)?;\n+    if !report.ok {\n+        std::process::exit(1);\n+    }\n+    Ok(())\n+}\n+\n+fn main() -> Result<()> {\n+    let cli = Cli::parse();\n+    match cli.cmd {\n+        Command::Compile {\n+            file,\n+            room,\n+            base,\n+            pretty,\n+        } => run_compile(file, room, base, pretty),\n+        Command::Scan { file, pretty } => run_scan(file, pretty),\n+    }\n+}\n","role":"user"}],"model":"openai/gpt-chat-latest"}