{"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[a888d56c] refactor: centralize path identity in slug-types\n\nMove canonicalization and CanonicalItemUrl into types::paths with\nGardenItemUrl, ForumThreadUrl, and TildeOntologyPath for JSON hrefs.\nServer canonical_path and path_types re-export slug-types; RPC and\nvalidation build hrefs via those types instead of string helpers.\n\nMade-with: Cursor\n\nSide A — unified diff (full patch):\ndiff --git a/server/src/api/helpers.rs b/server/src/api/helpers.rs\nindex 9b71491e9f9efc44a2a4beba09be8f64bd2ff2ee..03b3e77911ccd662bec8635345dafe2593cf242e 100644\n--- a/server/src/api/helpers.rs\n+++ b/server/src/api/helpers.rs\n@@ -4,12 +4,12 @@ use axum::{\n Json,\n };\n use sha2::{Digest, Sha256};\n+use slug_types::paths::{CanonicalItemUrl, GardenItemUrl};\n use slug_types::*;\n use std::collections::HashMap;\n \n use crate::{\n canonical_path::canonicalize_item,\n- path_types::CanonicalItemUrl,\n ranking::connected_components_from_voted_pairs,\n };\n \n@@ -30,64 +30,6 @@ pub fn now_ms() -> i64 {\n t.as_millis() as i64\n }\n \n-/// Serialize a canonical item for JSON: absolute URLs stay as-is; bare paths get a `/` prefix.\n-pub fn item_path_for_api(item: &str) -> String {\n- if item.starts_with(\"http://\") || item.starts_with(\"https://\") {\n- item.to_string()\n- } else {\n- format!(\"/{}\", item)\n- }\n-}\n-\n-/// Same as [`item_path_for_api`], but for private rooms ontology items are prefixed with\n-/// `/r/{short}/{slug}` so the URL matches the web app (`/r/…/~/…` routes).\n-pub fn item_path_for_api_in_room(item: &str, room_wire: &str) -> String {\n- let room = room_wire.trim();\n- if room.is_empty() || room == \"public\" {\n- return item_path_for_api(item);\n- }\n- let Some((short, slug)) = room.split_once('/') else {\n- return item_path_for_api(item);\n- };\n- if short.is_empty() || slug.is_empty() {\n- return item_path_for_api(item);\n- }\n- let Some(c) = CanonicalItemUrl::parse(item) else {\n- return item_path_for_api(item);\n- };\n- let root = CanonicalItemUrl::ontology_root();\n- let item_norm = c.as_str().trim_end_matches('/');\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- } else {\n- format!(\"https://slug.social/r/{short}/{slug}/~/{}\", tail)\n- };\n- }\n- if item_norm == root_norm {\n- return format!(\"https://slug.social/r/{short}/{slug}/~\");\n- }\n- item_path_for_api(item)\n-}\n-\n-/// Absolute thread URL for forum JSON (`/t/…` vs `/r/…/t/…`).\n-pub fn forum_thread_web_url(room_wire: &str, thread_tag: &str) -> String {\n- let room = room_wire.trim();\n- let tag = thread_tag.trim().trim_start_matches('#');\n- 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 {\n- format!(\"https://slug.social/t/{tag}\")\n- }\n-}\n-\n /// Resolve an item path as a first-class canonical path.\n pub fn resolve_item(item: &str) -> Result {\n let canonical = canonicalize_item(item);\n@@ -109,14 +51,12 @@ pub fn parse_parent_specs(parent: Option<&String>) -> Vec {\n }\n \n /// Apply offset+limit pagination to the flattened component rankings.\n-/// Items are flattened in component order (largest component first), then unranked last.\n-/// Returns (components, unranked_items) after the window.\n pub fn paginate_rankings(\n components: Vec,\n- unranked_items: Vec,\n+ unranked_items: Vec,\n offset: usize,\n limit: Option,\n-) -> (Vec, Vec) {\n+) -> (Vec, Vec) {\n let mut remaining_skip = offset;\n let mut remaining_take = limit.unwrap_or(usize::MAX);\n let mut out_components: Vec = Vec::new();\n@@ -141,7 +81,7 @@ pub fn paginate_rankings(\n });\n }\n \n- let out_unranked: Vec = if remaining_take > 0 {\n+ let out_unranked: Vec = if remaining_take > 0 {\n unranked_items\n .into_iter()\n .skip(remaining_skip)\n@@ -183,11 +123,9 @@ pub fn is_pair_voted(group: &crate::reducer::GroupState, a: &str, b: &str) -> bo\n group.voted_pairs.contains(&(i, j))\n }\n \n-/// Compute graph connectivity stats for a set of items within the ranking group.\n pub fn compute_connectivity_stats(group: &crate::reducer::GroupState, pool: &[String]) -> ConnectivityStats {\n let n = pool.len();\n \n- // Map pool items to global indices (items not yet in the group get no index)\n let global_idxs: Vec> = pool\n .iter()\n .map(|it| {\n@@ -197,7 +135,6 @@ pub fn compute_connectivity_stats(group: &crate::reducer::GroupState, pool: &[St\n .collect();\n let present: Vec = global_idxs.iter().filter_map(|x| *x).collect();\n \n- // Build local index mapping for items that exist in the ranking group\n let global_to_local: HashMap = present\n .iter()\n .enumerate()\n@@ -213,7 +150,6 @@ pub fn compute_connectivity_stats(group: &crate::reducer::GroupState, pool: &[St\n }),\n );\n \n- // Items not in the ranking group at all are also isolates\n let items_not_in_group = global_idxs.iter().filter(|x| x.is_none()).count();\n \n let num_components = comps.len() + isolates.len() + items_not_in_group;\n@@ -237,52 +173,3 @@ pub fn vote_touches_path(a: &str, b: &str, parent_canon: &str) -> bool {\n let under = |item: &str| item == parent_canon || item.starts_with(&format!(\"{}/\", parent_canon));\n under(a) || under(b)\n }\n-\n-#[cfg(test)]\n-mod wire_url_tests {\n- use super::{forum_thread_web_url, item_path_for_api_in_room};\n-\n- #[test]\n- fn public_room_unchanged() {\n- let u = \"https://slug.social/~/a/b\";\n- assert_eq!(item_path_for_api_in_room(u, \"public\"), u);\n- }\n-\n- #[test]\n- fn private_room_prefixes_ontology() {\n- assert_eq!(\n- item_path_for_api_in_room(\"https://slug.social/~/topic/x\", \"9ab12cd/my-room\"),\n- \"https://slug.social/r/9ab12cd/my-room/~/topic/x\"\n- );\n- }\n-\n- #[test]\n- fn private_room_ontology_root() {\n- assert_eq!(\n- item_path_for_api_in_room(\"https://slug.social/~\", \"9ab12cd/my-room\"),\n- \"https://slug.social/r/9ab12cd/my-room/~\"\n- );\n- assert_eq!(\n- item_path_for_api_in_room(\"https://slug.social/~/\", \"9ab12cd/my-room\"),\n- \"https://slug.social/r/9ab12cd/my-room/~\"\n- );\n- }\n-\n- #[test]\n- fn external_url_untouched_in_private_room() {\n- let u = \"https://example.com/z\";\n- assert_eq!(item_path_for_api_in_room(u, \"9ab12cd/my-room\"), u);\n- }\n-\n- #[test]\n- fn forum_web_public_vs_room() {\n- assert_eq!(\n- forum_thread_web_url(\"public\", \"debate\"),\n- \"https://slug.social/t/debate\"\n- );\n- assert_eq!(\n- forum_thread_web_url(\"9ab12cd/my-room\", \"#debate\"),\n- \"https://slug.social/r/9ab12cd/my-room/t/debate\"\n- );\n- }\n-}\ndiff --git a/server/src/api/mod.rs b/server/src/api/mod.rs\nindex 042aa248305f9362a3be78f9eea2a5abf6ba707a..cf22cb0129366c3aed031bc86f3197a4321cb806 100644\n--- a/server/src/api/mod.rs\n+++ b/server/src/api/mod.rs\n@@ -24,8 +24,7 @@ pub use auth::{\n \n pub use helpers::{\n api_error, compute_connectivity_stats, is_pair_voted, now_ms, paginate_rankings,\n- parse_parent_specs, pick_random_distinct, sha256_hex, resolve_item, vote_touches_path,\n- item_path_for_api,\n+ parse_parent_specs, pick_random_distinct, resolve_item, sha256_hex, vote_touches_path,\n };\n \n pub use rpc::handle_rpc_batch;\ndiff --git a/server/src/api/rpc.rs b/server/src/api/rpc.rs\nindex 5b91f5836625eedbb1cd9423168046e3fb576c17..5f7d50188f1381267402f2e57e671234ef5db2fd 100644\n--- a/server/src/api/rpc.rs\n+++ b/server/src/api/rpc.rs\n@@ -8,6 +8,7 @@ use axum::{\n Json,\n };\n use rand::seq::SliceRandom;\n+use slug_types::paths::{ForumThreadUrl, GardenItemUrl, TildeOntologyPath};\n use slug_types::*;\n \n use crate::{\n@@ -27,9 +28,8 @@ use crate::{\n \n use super::auth::verify_bearer_principal;\n use super::helpers::{\n- compute_connectivity_stats, forum_thread_web_url, is_pair_voted, item_path_for_api,\n- item_path_for_api_in_room, now_ms, paginate_rankings, parse_parent_specs, pick_random_distinct,\n- resolve_item, vote_touches_path,\n+ compute_connectivity_stats, is_pair_voted, now_ms, paginate_rankings, parse_parent_specs,\n+ pick_random_distinct, resolve_item, vote_touches_path,\n };\n use super::validate::{normalize_room_and_thread, validate_ingest_document};\n \n@@ -184,7 +184,7 @@ fn compute_scope_rank_changes(\n };\n if changed {\n changes.push(RankChange {\n- item: item_path_for_api_in_room(&item, room_wire),\n+ item: GardenItemUrl::from_storage_str(&item, room_wire),\n before: b,\n after: a,\n });\n@@ -206,7 +206,7 @@ fn compute_scope_rank_changes(\n parent: if parent.is_empty() {\n \"/\".to_string()\n } else {\n- item_path_for_api_in_room(parent, room_wire)\n+ GardenItemUrl::from_storage_str(parent, room_wire).into_inner()\n },\n changes,\n })\n@@ -302,7 +302,7 @@ fn build_rank_response_for_content(\n .ranked\n .into_iter()\n .map(|r| RankRow {\n- item: item_path_for_api_in_room(r.item.as_str(), room_wire),\n+ item: GardenItemUrl::from_stored(&r.item, room_wire),\n percent: if want_percent {\n Some((r.score / max_score) * 100.0)\n } else {\n@@ -315,10 +315,10 @@ fn build_rank_response_for_content(\n })\n .collect();\n \n- let prefixed_unranked: Vec = rankings\n+ let prefixed_unranked: Vec = rankings\n .unranked_items\n .into_iter()\n- .map(|s| item_path_for_api_in_room(s.as_str(), room_wire))\n+ .map(|s| GardenItemUrl::from_stored(&s, room_wire))\n .collect();\n \n let (components, unranked_items) = if offset > 0 || limit.is_some() {\n@@ -537,13 +537,13 @@ async fn rpc_post(\n (\n \"npx slugsocial public garden pair\".to_string(),\n \"npx slugsocial public garden rank\".to_string(),\n- forum_thread_web_url(\"public\", &thread_id),\n+ ForumThreadUrl::from_room_tag(\"public\", &thread_id),\n )\n } else {\n (\n format!(\"npx slugsocial private {room_key} garden pair\"),\n format!(\"npx slugsocial private {room_key} garden rank\"),\n- forum_thread_web_url(&room_key, &thread_id),\n+ ForumThreadUrl::from_room_tag(&room_key, &thread_id),\n )\n };\n \n@@ -664,7 +664,7 @@ async fn rpc_check(\n .ranked\n .into_iter()\n .map(|r| RankRow {\n- item: item_path_for_api_in_room(r.item.as_str(), &room_key),\n+ item: GardenItemUrl::from_stored(&r.item, &room_key),\n score: r.score,\n percent: None,\n })\n@@ -672,12 +672,12 @@ async fn rpc_check(\n })\n .collect();\n CheckScopeRanking {\n- parent: item_path_for_api_in_room(parent.as_str(), &room_key),\n+ parent: GardenItemUrl::from_stored(parent, &room_key).into_inner(),\n components,\n unranked_items: scoped\n .unranked_items\n .into_iter()\n- .map(|it| item_path_for_api_in_room(it.as_str(), &room_key))\n+ .map(|it| GardenItemUrl::from_stored(&it, &room_key))\n .collect(),\n }\n })\n@@ -687,13 +687,13 @@ async fn rpc_check(\n vec![\n \"npx slugsocial public forum post --delegate \".to_string(),\n \"npx slugsocial public forum list\".to_string(),\n- forum_thread_web_url(\"public\", &thread_id),\n+ ForumThreadUrl::from_room_tag(\"public\", &thread_id).into_inner(),\n ]\n } else {\n vec![\n format!(\"npx slugsocial private {room_key} forum post --delegate \"),\n format!(\"npx slugsocial private {room_key} forum list\"),\n- forum_thread_web_url(&room_key, &thread_id),\n+ ForumThreadUrl::from_room_tag(&room_key, &thread_id).into_inner(),\n ]\n };\n \n@@ -717,7 +717,7 @@ fn rpc_list_forum_threads(reduced: &ReducerState, room: &str) -> ThreadsResponse\n .map(|((_, tag), ts)| ThreadSummary {\n thread: format!(\"#{tag}\"),\n last_activity_ts: ts.last_activity_ts,\n- web: forum_thread_web_url(room, tag),\n+ web: ForumThreadUrl::from_room_tag(room, tag),\n })\n .collect();\n out.sort_by(|a, b| b.last_activity_ts.cmp(&a.last_activity_ts));\n@@ -885,7 +885,7 @@ fn rpc_search(reduced: &ReducerState, q: &str, limit: usize, principal: Option<&\n }\n if score > 0 {\n scored_items.push((score, SearchItemHit {\n- path: item_path_for_api(item.as_str()),\n+ path: GardenItemUrl::from_storage_str(item.as_str(), \"public\"),\n body: content.item_bodies.get(item).map(|b| snippet_around(b, &words, 120)),\n }));\n }\n@@ -1058,8 +1058,8 @@ async fn rpc_get_pair(state: &AppState, room: String, parent_path: String) -> Re\n .collect();\n let cs = compute_connectivity_stats(&content.ranking_group, &pool);\n Ok(RpcResult::Pair(PairResponse {\n- left: item_path_for_api_in_room(&left, &room),\n- right: item_path_for_api_in_room(&right, &room),\n+ left: GardenItemUrl::from_storage_str(&left, &room),\n+ right: GardenItemUrl::from_storage_str(&right, &room),\n left_body: lb,\n right_body: rb,\n threads: th,\n@@ -1137,7 +1137,7 @@ pub async fn handle_rpc_batch(\n if !content.items.contains(&item) {\n line_err(\n \"item not found\",\n- Some(format!(\"{} does not exist\", item_path_for_api_in_room(&item_str, &room))),\n+ Some(format!(\"{} does not exist\", GardenItemUrl::from_storage_str(&item_str, &room))),\n )\n } else {\n const MAX_ITEM_BODY: usize = 10_000;\n@@ -1160,7 +1160,7 @@ pub async fn handle_rpc_batch(\n .map(|s| s.iter().cloned().collect())\n .unwrap_or_default();\n line_ok(RpcResult::GardenItem(ItemResponse {\n- item: item_path_for_api_in_room(&item_str, &room),\n+ item: GardenItemUrl::from_storage_str(&item_str, &room),\n body,\n truncated,\n body_len,\n@@ -1554,7 +1554,7 @@ pub async fn handle_rpc_batch(\n for r in items {\n let pct = want_percent.then(|| ((r.score - bot) / range * 100.0).clamp(0.0, 100.0));\n ranked.push(RankRow {\n- item: item_path_for_api_in_room(r.item.as_str(), &room),\n+ item: GardenItemUrl::from_storage_str(r.item.as_str(), &room),\n score: r.score,\n percent: pct,\n });\n@@ -1574,7 +1574,7 @@ pub async fn handle_rpc_batch(\n let page: Vec = ranked\n .into_iter()\n .chain(unranked.into_iter().map(|it| RankRow {\n- item: item_path_for_api_in_room(&it, &room),\n+ item: GardenItemUrl::from_storage_str(&it, &room),\n score: 0.0,\n percent: want_percent.then_some(0.0),\n }))\n@@ -1618,7 +1618,7 @@ pub async fn handle_rpc_batch(\n if !content.items.contains(&item) {\n line_err(\n \"item not found\",\n- Some(format!(\"{} does not exist\", item_path_for_api_in_room(&item_str, &room))),\n+ Some(format!(\"{} does not exist\", GardenItemUrl::from_storage_str(&item_str, &room))),\n )\n } else {\n let votes: Vec = content\n@@ -1629,8 +1629,8 @@ pub async fn handle_rpc_batch(\n .take(limit)\n .map(|v| VoteRow {\n ts: v.ts,\n- a: item_path_for_api_in_room(v.a.as_str(), &room),\n- b: item_path_for_api_in_room(v.b.as_str(), &room),\n+ a: GardenItemUrl::from_stored(&v.a, &room),\n+ b: GardenItemUrl::from_stored(&v.b, &room),\n ratio: format!(\"{}:{}\", v.ratio_left, v.ratio_right),\n actor: Some(v.principal.clone()),\n body: v.body.clone(),\n@@ -1640,7 +1640,7 @@ pub async fn handle_rpc_batch(\n })\n .unwrap_or_default();\n line_ok(RpcResult::Matchup(MatchupResponse {\n- item: item_path_for_api_in_room(&item_str, &room),\n+ item: GardenItemUrl::from_storage_str(&item_str, &room),\n votes,\n }))\n }\n@@ -1667,8 +1667,8 @@ pub async fn handle_rpc_batch(\n if a == item_str || b == item_str {\n Some(VoteRow {\n ts: e.ts,\n- a: item_path_for_api_in_room(&a, &room),\n- b: item_path_for_api_in_room(&b, &room),\n+ a: GardenItemUrl::from_storage_str(&a, &room),\n+ b: GardenItemUrl::from_storage_str(&b, &room),\n ratio: format!(\"{}:{}\", ratio_left, ratio_right),\n actor: reduced.ingests_by_id.get(&e.post_id).map(|ing| ing.principal.clone()),\n body: explanation,\n@@ -1704,7 +1704,7 @@ pub async fn handle_rpc_batch(\n }\n }).collect();\n line_ok(RpcResult::RankHistory(RankHistoryResponse {\n- item: item_path_for_api_in_room(&item_str, &room),\n+ item: GardenItemUrl::from_storage_str(&item_str, &room),\n history,\n }))\n }\n@@ -1716,17 +1716,13 @@ pub async fn handle_rpc_batch(\n } else {\n let content = content_for_room(&reduced, &room);\n let parents: HashSet<&str> = content.item_children.keys().map(|s| s.as_str()).collect();\n- let mut paths: Vec = content\n+ let mut paths: Vec = content\n .items\n .iter()\n .filter(|p| !parents.contains(p.as_str()))\n- .map(|p| p.as_str().to_string())\n- .collect();\n- paths.sort();\n- let paths: Vec = paths\n- .into_iter()\n- .map(|p| item_path_for_api_in_room(&p, &room))\n+ .map(|p| GardenItemUrl::from_stored(p, &room))\n .collect();\n+ paths.sort_by(|a, b| a.as_str().cmp(b.as_str()));\n line_ok(RpcResult::Leaves(LeavesResponse { paths }))\n }\n },\n@@ -1743,24 +1739,13 @@ pub async fn handle_rpc_batch(\n let mut v: Vec = roots.iter()\n .map(|path| {\n let children = content.item_children.get(path.as_str()).map(|s| s.len()).unwrap_or(0);\n- let path_label = CanonicalItemUrl::parse(path.as_str())\n- .and_then(|c| {\n- c.tilde_tail().map(|t| {\n- if t.is_empty() {\n- \"~/\".to_string()\n- } else {\n- format!(\"~/{}\", t)\n- }\n- })\n- })\n- .unwrap_or_else(|| path.to_string());\n PathSummary {\n- path: path_label,\n+ path: TildeOntologyPath::from_stored(path),\n children,\n- web: item_path_for_api_in_room(path.as_str(), &room),\n+ web: GardenItemUrl::from_stored(path, &room),\n }\n }).collect();\n- v.sort_by(|a, b| a.path.cmp(&b.path));\n+ v.sort_by(|a, b| a.path.as_str().cmp(b.path.as_str()));\n v\n })\n .unwrap_or_default();\n@@ -1790,8 +1775,8 @@ pub async fn handle_rpc_batch(\n .take(limit)\n .map(|v| VoteRow {\n ts: v.ts,\n- a: item_path_for_api_in_room(v.a.as_str(), &room),\n- b: item_path_for_api_in_room(v.b.as_str(), &room),\n+ a: GardenItemUrl::from_stored(&v.a, &room),\n+ b: GardenItemUrl::from_stored(&v.b, &room),\n ratio: format!(\"{}:{}\", v.ratio_left, v.ratio_right),\n actor: Some(v.principal.clone()),\n body: v.body.clone(),\ndiff --git a/server/src/api/validate.rs b/server/src/api/validate.rs\nindex 27150577982f52cbd6d11bb93654dc3d4cf75cc5..a51c783ee9785569b5a44c0b1572471fe00d174b 100644\n--- a/server/src/api/validate.rs\n+++ b/server/src/api/validate.rs\n@@ -7,8 +7,9 @@ use crate::{\n path_types::CanonicalItemUrl,\n reducer::{ReducerState, ScopeId},\n };\n+use slug_types::paths::GardenItemUrl;\n \n-use super::helpers::{item_path_for_api, resolve_item};\n+use super::helpers::resolve_item;\n \n #[derive(Debug)]\n pub struct ValidatedIngest {\n@@ -22,6 +23,10 @@ pub fn validate_ingest_document(\n text: &str,\n scope: &ScopeId,\n ) -> Result)> {\n+ let room_wire = match scope {\n+ ScopeId::Public => \"public\",\n+ ScopeId::Room(r) => r.as_str(),\n+ };\n let public_content = reduced.public();\n let scoped_content = match scope {\n ScopeId::Public => None,\n@@ -61,14 +66,14 @@ pub fn validate_ingest_document(\n let Some(body_text) = body else {\n return Err((\n StatusCode::BAD_REQUEST,\n- format!(\"item missing body: {}\", item_path_for_api(&item)),\n+ format!(\"item missing body: {}\", GardenItemUrl::from_storage_str(&item, room_wire)),\n Some(\"items must be declared with bodies, e.g. `~/path/item { ... }`\".to_string()),\n ));\n };\n if body_text.trim().is_empty() {\n return Err((\n StatusCode::BAD_REQUEST,\n- format!(\"item body is empty: {}\", item_path_for_api(&item)),\n+ format!(\"item body is empty: {}\", GardenItemUrl::from_storage_str(&item, room_wire)),\n Some(\"write at least one sentence inside `{ ... }`\".to_string()),\n ));\n }\n@@ -101,7 +106,7 @@ pub fn validate_ingest_document(\n let key = CanonicalItemUrl((*it).clone());\n !defined_in_doc.contains(*it) && !item_exists(&key)\n })\n- .map(|it| item_path_for_api(it))\n+ .map(|it| GardenItemUrl::from_storage_str(it, room_wire).into_inner())\n .collect();\n if !missing.is_empty() {\n return Err((\n@@ -119,7 +124,7 @@ pub fn validate_ingest_document(\n let key = CanonicalItemUrl((*it).clone());\n !defined_in_doc.contains(*it) && !body_exists(&key)\n })\n- .map(|it| item_path_for_api(it))\n+ .map(|it| GardenItemUrl::from_storage_str(it, room_wire).into_inner())\n .collect();\n if !missing_body.is_empty() {\n return Err((\ndiff --git a/server/src/canonical_path.rs b/server/src/canonical_path.rs\nindex 5c0febe883d8b3978a25896ed0d71df8509a8717..8a1998025121838b0867f8c5ddbd28aea41a23d2 100644\n--- a/server/src/canonical_path.rs\n+++ b/server/src/canonical_path.rs\n@@ -1,92 +1,3 @@\n-//! Normalization for thread tags and ontology item URLs (DSL ↔ stored canonical form).\n-//! Not event types — see `events` and `path_types`.\n+//! Re-exports — implementations live in `slug-types` (`paths` module).\n \n-/// Thread / public tag: stored without leading `#`, lowercase.\n-pub fn canonicalize_tag(input: &str) -> String {\n- input.trim().trim_start_matches('#').to_lowercase()\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- if s.is_empty() {\n- return String::new();\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- } else {\n- return 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- } else {\n- return format!(\"http://{}/{}\", host, tail);\n- }\n- }\n-\n- let is_tilde = s.starts_with(\"~/\");\n- let rest = s.strip_prefix(\"~/\").or_else(|| s.strip_prefix(\"/\")).unwrap_or(s);\n-\n- let tail = rest\n- .split('/')\n- .filter_map(|seg| {\n- let t = seg.trim();\n- if t.is_empty() {\n- None\n- } else {\n- Some(t.to_lowercase())\n- }\n- })\n- .collect::>()\n- .join(\"/\");\n-\n- if is_tilde {\n- format!(\"https://slug.social/~/{}\", tail)\n- } else if tail.is_empty() {\n- \"https://slug.social\".to_string()\n- } else {\n- format!(\"https://slug.social/{}\", tail)\n- }\n-}\n-\n-pub fn item_path_segments(input: &str) -> Vec {\n- let canonical = canonicalize_item(input);\n- if canonical.is_empty() {\n- return vec![];\n- }\n-\n- if let Some(rest) = canonical.strip_prefix(\"https://\") {\n- let (host, tail) = rest.split_once('/').map_or((rest, \"\"), |(h, t)| (h, t));\n- let mut out = vec![format!(\"https://{}\", host)];\n- out.extend(tail.split('/').filter(|s| !s.is_empty()).map(|s| s.to_string()));\n- return out;\n- }\n- if let Some(rest) = canonical.strip_prefix(\"http://\") {\n- let (host, tail) = rest.split_once('/').map_or((rest, \"\"), |(h, t)| (h, t));\n- let mut out = vec![format!(\"http://{}\", host)];\n- out.extend(tail.split('/').filter(|s| !s.is_empty()).map(|s| s.to_string()));\n- return out;\n- }\n-\n- canonical\n- .split('/')\n- .filter(|s| !s.is_empty())\n- .map(|s| s.to_string())\n- .collect()\n-}\n-\n-pub fn item_parent_path(input: &str) -> Option {\n- let segs = item_path_segments(input);\n- if segs.len() <= 1 {\n- return None;\n- }\n- Some(segs[..segs.len() - 1].join(\"/\"))\n-}\n+pub use slug_types::paths::{canonicalize_item, canonicalize_tag, item_parent_path, item_path_segments};\ndiff --git a/server/src/html/forum.rs b/server/src/html/forum.rs\nindex ab7970feca47a4431ddc19dab2c8186180b78413..f789e347dc136f8ffd356f4492f0bd76cea04bf0 100644\n--- a/server/src/html/forum.rs\n+++ b/server/src/html/forum.rs\n@@ -697,7 +697,7 @@ async fn thread_view_inner(\n let offset = q.offset.unwrap_or(0);\n let page_ids: Vec = all_ids.into_iter().skip(offset).take(PAGE_SIZE).collect();\n \n- let (display_ingests, subtitle) = {\n+ let (display_ingests, _subtitle) = {\n let reduced = state.reduced.read().await;\n let ingests = page_ids\n .iter()\ndiff --git a/server/src/path_types.rs b/server/src/path_types.rs\nindex cad58cac7da948f92d6ea2a5587d917ab21d57ea..4c8075bbd488f1b9a5eda9e03ced83f6238c6d5e 100644\n--- a/server/src/path_types.rs\n+++ b/server/src/path_types.rs\n@@ -1,260 +1,3 @@\n-//! Path representation types.\n-//!\n-//! The codebase currently treats item identifiers as strings in a few different\n-//! encodings:\n-//! - user/DSL input like `~/a/b`\n-//! - canonical item URLs like `https://slug.social/~/a/b`\n-//! - relative paths within a rooted tree view (e.g. `llms/openai` under a root)\n-//!\n-//! This module adds lightweight newtypes so code can be explicit about what it\n-//! expects without changing core storage formats.\n-//!\n-//! **Storage vs wire:** [`CanonicalItemUrl`] values are shared across scopes\n-//! (`https://slug.social/~/…`); which [`crate::reducer::ContentState`] they live in\n-//! is determined by scope, not by embedding the room id in the string. For JSON/RPC\n-//! and browser links in a private room, use [`crate::api::helpers::item_path_for_api_in_room`]\n-//! so ontology items become `https://slug.social/r/{short}/{slug}/~/…`.\n+//! Re-exports — implementations live in `slug-types` (`paths` module).\n \n-use std::borrow::Borrow;\n-use std::fmt;\n-\n-use serde::{Deserialize, Serialize};\n-\n-use crate::canonical_path::canonicalize_item;\n-\n-/// Canonical item identifier as produced by `canonical_path::canonicalize_item`.\n-///\n-/// In practice this is usually:\n-/// - `https://slug.social/~/...` for ontology items, or\n-/// - `https://...` / `http://...` for URL items.\n-#[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Ord, Hash, Serialize, Deserialize)]\n-pub struct CanonicalItemUrl(pub String);\n-\n-impl CanonicalItemUrl {\n- pub fn parse(input: &str) -> Option {\n- let c = canonicalize_item(input);\n- if c.is_empty() {\n- None\n- } else {\n- Some(Self(c))\n- }\n- }\n-\n- pub fn as_str(&self) -> &str {\n- &self.0\n- }\n-\n- /// Returns the `~/...` tail for ontology items (`https://slug.social/~/...`).\n- pub fn tilde_tail(&self) -> Option<&str> {\n- self.0.strip_prefix(\"https://slug.social/~/\")\n- }\n-\n- /// Returns the final non-empty `/`-separated segment of the path.\n- ///\n- /// `https://slug.social/~/a/b/c` → `\"c\"`\n- /// `https://slug.social/~/a` → `\"a\"`\n- pub fn last_segment(&self) -> &str {\n- self.0\n- .rsplit('/')\n- .find(|s| !s.is_empty())\n- .unwrap_or(self.0.as_str())\n- }\n-\n- /// The ontology root key as stored in `item_children`: `\"https://slug.social/~\"`.\n- /// Use this (not `parse(\"~/\")`) when looking up top-level children.\n- pub fn ontology_root() -> Self {\n- Self(\"https://slug.social/~\".to_string())\n- }\n-\n- /// Returns the parent of this canonical item URL by stripping the last\n- /// path segment, or `None` if there is no parent (already at root).\n- ///\n- /// `https://slug.social/~/a/b/c` → `Some(\"https://slug.social/~/a/b\")`\n- /// `https://slug.social/~/a` → `Some(\"https://slug.social/~\")`\n- /// `https://slug.social/~/` → `None` (tilde root)\n- pub fn parent(&self) -> Option {\n- // tilde_tail() is None for non-ontology URLs and \"\" for the root ~/\n- if self.tilde_tail().map(|t| t.is_empty()).unwrap_or(true) {\n- return None;\n- }\n- // Strip everything from the last '/' onwards.\n- let last_slash = self.0.rfind('/')?;\n- let parent_str = &self.0[..last_slash];\n- if parent_str.is_empty() {\n- None\n- } else {\n- Some(Self(parent_str.to_string()))\n- }\n- }\n-\n- /// Segments of an ontology path suitable for breadcrumb rendering.\n- /// Strips the `https://slug.social` prefix and returns the `~/…` parts.\n- ///\n- /// `https://slug.social/~/a/b` → `[\"~\", \"a\", \"b\"]`\n- /// `https://slug.social/~/` → `[\"~\"]`\n- pub fn tilde_segments(&self) -> Vec<&str> {\n- match self.tilde_tail() {\n- Some(tail) if !tail.is_empty() => {\n- std::iter::once(\"~\")\n- .chain(tail.split('/').filter(|s| !s.is_empty()))\n- .collect()\n- }\n- Some(_) => vec![\"~\"],\n- None => vec![],\n- }\n- }\n-}\n-\n-impl fmt::Display for CanonicalItemUrl {\n- fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {\n- self.0.fmt(f)\n- }\n-}\n-\n-/// Allow `HashMap` to be searched by `&str`.\n-impl Borrow for CanonicalItemUrl {\n- fn borrow(&self) -> &str {\n- &self.0\n- }\n-}\n-\n-impl PartialEq for CanonicalItemUrl {\n- fn eq(&self, other: &str) -> bool {\n- self.0 == other\n- }\n-}\n-\n-impl PartialEq<&str> for CanonicalItemUrl {\n- fn eq(&self, other: &&str) -> bool {\n- self.0 == *other\n- }\n-}\n-\n-impl PartialEq for CanonicalItemUrl {\n- fn eq(&self, other: &String) -> bool {\n- &self.0 == other\n- }\n-}\n-\n-/// A `~/...` input path (as used in the DSL and UX).\n-///\n-/// This is not canonicalized; it is a presentation/input form.\n-#[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Ord, Hash, Serialize, Deserialize)]\n-pub struct TildePath(pub String);\n-\n-impl TildePath {\n- pub fn new(input: &str) -> Option {\n- let s = input.trim();\n- if s.starts_with(\"~/\") && s.len() > 2 {\n- Some(Self(s.to_string()))\n- } else if s == \"~/\" {\n- Some(Self(\"~/\".to_string()))\n- } else {\n- None\n- }\n- }\n-\n- pub fn as_str(&self) -> &str {\n- &self.0\n- }\n-\n- pub fn canonicalize(&self) -> Option {\n- CanonicalItemUrl::parse(&self.0)\n- }\n-}\n-\n-impl fmt::Display for TildePath {\n- fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {\n- self.0.fmt(f)\n- }\n-}\n-\n-/// A path relative to a chosen root in a tree UI.\n-///\n-/// This is intended for compact state encodings (blobs). It must be joined to a\n-/// root `CanonicalItemUrl` (typically an ontology root) to become a full item.\n-#[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Ord, Hash, Serialize, Deserialize)]\n-pub struct RelativePath(pub String);\n-\n-impl RelativePath {\n- pub fn new(input: &str) -> Option {\n- let s = input.trim().trim_matches('/');\n- if s.is_empty() {\n- Some(Self(String::new()))\n- } else {\n- // Keep this permissive: the DSL parser is the main gatekeeper.\n- Some(Self(s.to_string()))\n- }\n- }\n-\n- pub fn as_str(&self) -> &str {\n- &self.0\n- }\n-\n- /// Join this relative path under a canonical ontology root\n- /// (`https://slug.social/~/...`) to form a canonical item URL.\n- pub fn join_under_ontology_root(&self, root: &CanonicalItemUrl) -> Option {\n- let base = root.tilde_tail()?;\n- // base is the tail after https://slug.social/~/, e.g. \"models\" or \"models/llms\"\n- let joined = if base.is_empty() {\n- if self.0.is_empty() {\n- \"~/\".to_string()\n- } else {\n- format!(\"~/{}\", self.0)\n- }\n- } else if self.0.is_empty() {\n- format!(\"~/{}\", base)\n- } else {\n- format!(\"~/{}/{}\", base.trim_end_matches('/'), self.0)\n- };\n- CanonicalItemUrl::parse(&joined)\n- }\n-}\n-\n-impl fmt::Display for RelativePath {\n- fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {\n- self.0.fmt(f)\n- }\n-}\n-\n-\n-#[cfg(test)]\n-mod tests {\n- use super::*;\n-\n- #[test]\n- fn canonical_parent_deep() {\n- let c = CanonicalItemUrl::parse(\"~/a/b/c\").unwrap();\n- assert_eq!(c.parent().unwrap().as_str(), \"https://slug.social/~/a/b\");\n- }\n-\n- #[test]\n- fn canonical_parent_one_level() {\n- let c = CanonicalItemUrl::parse(\"~/a\").unwrap();\n- assert_eq!(c.parent().unwrap().as_str(), \"https://slug.social/~\");\n- }\n-\n- #[test]\n- fn canonical_parent_root_is_none() {\n- let root = CanonicalItemUrl::parse(\"~/\").unwrap();\n- assert!(root.parent().is_none());\n- }\n-\n- #[test]\n- fn tilde_segments_deep() {\n- let c = CanonicalItemUrl::parse(\"~/a/b\").unwrap();\n- assert_eq!(c.tilde_segments(), vec![\"~\", \"a\", \"b\"]);\n- }\n-\n- #[test]\n- fn tilde_segments_root() {\n- let c = CanonicalItemUrl::parse(\"~/\").unwrap();\n- assert_eq!(c.tilde_segments(), vec![\"~\"]);\n- }\n-\n- #[test]\n- fn tilde_segments_non_ontology_is_empty() {\n- let c = CanonicalItemUrl::parse(\"https://example.com/foo\").unwrap();\n- assert_eq!(c.tilde_segments(), Vec::<&str>::new());\n- }\n-}\n+pub use slug_types::paths::{CanonicalItemUrl, RelativePath, TildePath};\ndiff --git a/types/src/lib.rs b/types/src/lib.rs\nindex c1cde3b783d03b02783385b5f07659fb112aae3e..5fc867bf2af84c2ca63fa1cdd03413110ad784a3 100644\n--- a/types/src/lib.rs\n+++ b/types/src/lib.rs\n@@ -1,7 +1,13 @@\n use serde::{Deserialize, Serialize};\n \n+pub mod paths;\n pub mod timeago;\n \n+pub use paths::{\n+ canonicalize_item, canonicalize_tag, item_parent_path, item_path_segments, CanonicalItemUrl,\n+ ForumThreadUrl, GardenItemUrl, RelativePath, TildeOntologyPath, TildePath,\n+};\n+\n #[derive(Debug, Serialize, Deserialize)]\n pub struct ApiError {\n pub ok: bool,\n@@ -12,7 +18,7 @@ pub struct ApiError {\n \n #[derive(Debug, Clone, Serialize, Deserialize)]\n pub struct RankRow {\n- pub item: String,\n+ pub item: GardenItemUrl,\n pub score: f64,\n /// Normalized score as a percentage of the top item (0–100). Present when ?percent=true.\n #[serde(skip_serializing_if = \"Option::is_none\")]\n@@ -43,7 +49,7 @@ pub struct RankComponent {\n #[derive(Debug, Serialize, Deserialize)]\n pub struct RankResponse {\n pub components: Vec,\n- pub unranked_items: Vec,\n+ pub unranked_items: Vec,\n }\n \n /// Graph connectivity stats for a scope, returned with pair suggestions.\n@@ -63,8 +69,8 @@ pub struct ConnectivityStats {\n \n #[derive(Debug, Serialize, Deserialize)]\n pub struct PairResponse {\n- pub left: String,\n- pub right: String,\n+ pub left: GardenItemUrl,\n+ pub right: GardenItemUrl,\n pub left_body: Option,\n pub right_body: Option,\n /// Thread tags that discuss either item (connective tissue to forum).\n@@ -79,7 +85,7 @@ pub struct PairResponse {\n pub struct NextMoves {\n pub pair: String,\n pub rank: String,\n- pub web: String,\n+ pub web: ForumThreadUrl,\n }\n \n #[derive(Debug, Serialize, Deserialize)]\n@@ -90,14 +96,14 @@ pub struct PathsResponse {\n /// Leaf items only (no children). For search / \"full path list\" — does not scale, works for now.\n #[derive(Debug, Serialize, Deserialize)]\n pub struct LeavesResponse {\n- pub paths: Vec,\n+ pub paths: Vec,\n }\n \n #[derive(Debug, Serialize, Deserialize)]\n pub struct PathSummary {\n- pub path: String,\n+ pub path: TildeOntologyPath,\n pub children: usize,\n- pub web: String,\n+ pub web: GardenItemUrl,\n }\n \n #[derive(Debug, Clone, Serialize, Deserialize)]\n@@ -109,7 +115,7 @@ pub struct ThreadsResponse {\n pub struct ThreadSummary {\n pub thread: String,\n pub last_activity_ts: i64,\n- pub web: String,\n+ pub web: ForumThreadUrl,\n }\n \n #[derive(Debug, Serialize, Deserialize)]\n@@ -178,7 +184,7 @@ pub struct IngestRow {\n \n #[derive(Debug, Serialize, Deserialize)]\n pub struct ItemResponse {\n- pub item: String,\n+ pub item: GardenItemUrl,\n pub body: Option,\n /// True when the body was truncated due to size. Fetch with `?full=true` for the complete body.\n #[serde(default, skip_serializing_if = \"std::ops::Not::not\")]\n@@ -201,15 +207,15 @@ pub struct RecentVotesResponse {\n /// Vote history for one item (matchup: wins/losses + thread per vote).\n #[derive(Debug, Serialize, Deserialize)]\n pub struct MatchupResponse {\n- pub item: String,\n+ pub item: GardenItemUrl,\n pub votes: Vec,\n }\n \n #[derive(Debug, Clone, Serialize, Deserialize)]\n pub struct VoteRow {\n pub ts: i64,\n- pub a: String,\n- pub b: String,\n+ pub a: GardenItemUrl,\n+ pub b: GardenItemUrl,\n pub ratio: String,\n /// Principal username when present (stored form, no `@`).\n pub actor: Option,\n@@ -510,7 +516,7 @@ pub struct RankPosition {\n /// How one item's rank changed after a vote.\n #[derive(Debug, Clone, Serialize, Deserialize)]\n pub struct RankChange {\n- pub item: String,\n+ pub item: GardenItemUrl,\n /// Position before the vote. None = was unranked (no voted connections in this scope).\n pub before: Option,\n /// Position after the vote. None = became unranked (e.g. component split, unlikely).\n@@ -544,7 +550,7 @@ pub struct CheckScopeRanking {\n /// Parent scope path (e.g. \"/models\" or \"/\" for root).\n pub parent: String,\n pub components: Vec,\n- pub unranked_items: Vec,\n+ pub unranked_items: Vec,\n }\n \n #[derive(Debug, Serialize, Deserialize)]\n@@ -567,7 +573,7 @@ pub struct SearchResponse {\n \n #[derive(Debug, Serialize, Deserialize)]\n pub struct SearchItemHit {\n- pub path: String,\n+ pub path: GardenItemUrl,\n #[serde(skip_serializing_if = \"Option::is_none\")]\n pub body: Option,\n }\n@@ -614,7 +620,7 @@ pub struct RankHistoryRow {\n \n #[derive(Debug, Serialize, Deserialize)]\n pub struct RankHistoryResponse {\n- pub item: String,\n+ pub item: GardenItemUrl,\n pub history: Vec,\n }\n \ndiff --git a/types/src/paths.rs b/types/src/paths.rs\nnew file mode 100644\nindex 0000000000000000000000000000000000000000..2950a7502255927583fbacdfd2adb700f0b0c221\n--- /dev/null\n+++ b/types/src/paths.rs\n@@ -0,0 +1,498 @@\n+//! Canonical paths, storage ids, and JSON href newtypes. All normalization and\n+//! room-aware URL rules for items live here.\n+\n+use std::borrow::Borrow;\n+use std::fmt;\n+\n+use serde::{Deserialize, Serialize};\n+\n+// ---------------------------------------------------------------------------\n+// Normalization (moved from server `canonical_path`)\n+// ---------------------------------------------------------------------------\n+\n+/// Thread / public tag: stored without leading `#`, lowercase.\n+pub fn canonicalize_tag(input: &str) -> String {\n+ input.trim().trim_start_matches('#').to_lowercase()\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+ if s.is_empty() {\n+ return String::new();\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+ } else {\n+ return 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+ } else {\n+ return format!(\"http://{}/{}\", host, tail);\n+ }\n+ }\n+\n+ let is_tilde = s.starts_with(\"~/\");\n+ let rest = s.strip_prefix(\"~/\").or_else(|| s.strip_prefix(\"/\")).unwrap_or(s);\n+\n+ let tail = rest\n+ .split('/')\n+ .filter_map(|seg| {\n+ let t = seg.trim();\n+ if t.is_empty() {\n+ None\n+ } else {\n+ Some(t.to_lowercase())\n+ }\n+ })\n+ .collect::>()\n+ .join(\"/\");\n+\n+ if is_tilde {\n+ format!(\"https://slug.social/~/{}\", tail)\n+ } else if tail.is_empty() {\n+ \"https://slug.social\".to_string()\n+ } else {\n+ format!(\"https://slug.social/{}\", tail)\n+ }\n+}\n+\n+pub fn item_path_segments(input: &str) -> Vec {\n+ let canonical = canonicalize_item(input);\n+ if canonical.is_empty() {\n+ return vec![];\n+ }\n+\n+ if let Some(rest) = canonical.strip_prefix(\"https://\") {\n+ let (host, tail) = rest.split_once('/').map_or((rest, \"\"), |(h, t)| (h, t));\n+ let mut out = vec![format!(\"https://{}\", host)];\n+ out.extend(tail.split('/').filter(|s| !s.is_empty()).map(|s| s.to_string()));\n+ return out;\n+ }\n+ if let Some(rest) = canonical.strip_prefix(\"http://\") {\n+ let (host, tail) = rest.split_once('/').map_or((rest, \"\"), |(h, t)| (h, t));\n+ let mut out = vec![format!(\"http://{}\", host)];\n+ out.extend(tail.split('/').filter(|s| !s.is_empty()).map(|s| s.to_string()));\n+ return out;\n+ }\n+\n+ canonical\n+ .split('/')\n+ .filter(|s| !s.is_empty())\n+ .map(|s| s.to_string())\n+ .collect()\n+}\n+\n+pub fn item_parent_path(input: &str) -> Option {\n+ let segs = item_path_segments(input);\n+ if segs.len() <= 1 {\n+ return None;\n+ }\n+ Some(segs[..segs.len() - 1].join(\"/\"))\n+}\n+\n+// ---------------------------------------------------------------------------\n+// Storage + input path newtypes\n+// ---------------------------------------------------------------------------\n+\n+/// Canonical item identifier as produced by [`canonicalize_item`].\n+///\n+/// Shared across all scopes; room is not embedded. Usually\n+/// `https://slug.social/~/…` or an external `http(s)://…` URL item.\n+#[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Ord, Hash, Serialize, Deserialize)]\n+pub struct CanonicalItemUrl(pub String);\n+\n+impl CanonicalItemUrl {\n+ pub fn parse(input: &str) -> Option {\n+ let c = canonicalize_item(input);\n+ if c.is_empty() {\n+ None\n+ } else {\n+ Some(Self(c))\n+ }\n+ }\n+\n+ pub fn as_str(&self) -> &str {\n+ &self.0\n+ }\n+\n+ pub fn tilde_tail(&self) -> Option<&str> {\n+ self.0.strip_prefix(\"https://slug.social/~/\")\n+ }\n+\n+ pub fn last_segment(&self) -> &str {\n+ self.0\n+ .rsplit('/')\n+ .find(|s| !s.is_empty())\n+ .unwrap_or(self.0.as_str())\n+ }\n+\n+ pub fn ontology_root() -> Self {\n+ Self(\"https://slug.social/~\".to_string())\n+ }\n+\n+ pub fn parent(&self) -> Option {\n+ if self.tilde_tail().map(|t| t.is_empty()).unwrap_or(true) {\n+ return None;\n+ }\n+ let last_slash = self.0.rfind('/')?;\n+ let parent_str = &self.0[..last_slash];\n+ if parent_str.is_empty() {\n+ None\n+ } else {\n+ Some(Self(parent_str.to_string()))\n+ }\n+ }\n+\n+ pub fn tilde_segments(&self) -> Vec<&str> {\n+ match self.tilde_tail() {\n+ Some(tail) if !tail.is_empty() => {\n+ std::iter::once(\"~\")\n+ .chain(tail.split('/').filter(|s| !s.is_empty()))\n+ .collect()\n+ }\n+ Some(_) => vec![\"~\"],\n+ None => vec![],\n+ }\n+ }\n+\n+ /// `~/…` list label for ontology items (paths index, CLI).\n+ pub fn tilde_list_label(&self) -> TildeOntologyPath {\n+ TildeOntologyPath::from_stored(self)\n+ }\n+\n+ /// Absolute href for JSON/RPC and browsers for this stored id in `room`.\n+ pub fn json_href(&self, room_wire: &str) -> GardenItemUrl {\n+ GardenItemUrl::from_stored(self, room_wire)\n+ }\n+}\n+\n+impl fmt::Display for CanonicalItemUrl {\n+ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {\n+ self.0.fmt(f)\n+ }\n+}\n+\n+impl Borrow for CanonicalItemUrl {\n+ fn borrow(&self) -> &str {\n+ &self.0\n+ }\n+}\n+\n+impl PartialEq for CanonicalItemUrl {\n+ fn eq(&self, other: &str) -> bool {\n+ self.0 == other\n+ }\n+}\n+\n+impl PartialEq<&str> for CanonicalItemUrl {\n+ fn eq(&self, other: &&str) -> bool {\n+ self.0 == *other\n+ }\n+}\n+\n+impl PartialEq for CanonicalItemUrl {\n+ fn eq(&self, other: &String) -> bool {\n+ &self.0 == other\n+ }\n+}\n+\n+#[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Ord, Hash, Serialize, Deserialize)]\n+pub struct TildePath(pub String);\n+\n+impl TildePath {\n+ pub fn new(input: &str) -> Option {\n+ let s = input.trim();\n+ if s.starts_with(\"~/\") && s.len() > 2 {\n+ Some(Self(s.to_string()))\n+ } else if s == \"~/\" {\n+ Some(Self(\"~/\".to_string()))\n+ } else {\n+ None\n+ }\n+ }\n+\n+ pub fn as_str(&self) -> &str {\n+ &self.0\n+ }\n+\n+ pub fn canonicalize(&self) -> Option {\n+ CanonicalItemUrl::parse(&self.0)\n+ }\n+}\n+\n+impl fmt::Display for TildePath {\n+ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {\n+ self.0.fmt(f)\n+ }\n+}\n+\n+#[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Ord, Hash, Serialize, Deserialize)]\n+pub struct RelativePath(pub String);\n+\n+impl RelativePath {\n+ pub fn new(input: &str) -> Option {\n+ let s = input.trim().trim_matches('/');\n+ if s.is_empty() {\n+ Some(Self(String::new()))\n+ } else {\n+ Some(Self(s.to_string()))\n+ }\n+ }\n+\n+ pub fn as_str(&self) -> &str {\n+ &self.0\n+ }\n+\n+ pub fn join_under_ontology_root(&self, root: &CanonicalItemUrl) -> Option {\n+ let base = root.tilde_tail()?;\n+ let joined = if base.is_empty() {\n+ if self.0.is_empty() {\n+ \"~/\".to_string()\n+ } else {\n+ format!(\"~/{}\", self.0)\n+ }\n+ } else if self.0.is_empty() {\n+ format!(\"~/{}\", base)\n+ } else {\n+ format!(\"~/{}/{}\", base.trim_end_matches('/'), self.0)\n+ };\n+ CanonicalItemUrl::parse(&joined)\n+ }\n+}\n+\n+impl fmt::Display for RelativePath {\n+ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {\n+ self.0.fmt(f)\n+ }\n+}\n+\n+// ---------------------------------------------------------------------------\n+// Wire / JSON: correct-by-construction hrefs\n+// ---------------------------------------------------------------------------\n+\n+fn api_path_or_url(item: &str) -> String {\n+ if item.starts_with(\"http://\") || item.starts_with(\"https://\") {\n+ item.to_string()\n+ } else {\n+ format!(\"/{}\", item)\n+ }\n+}\n+\n+/// Ontology item as serialized in JSON (absolute URL or `/`-prefixed path).\n+#[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Ord, Hash, Serialize, Deserialize)]\n+#[serde(transparent)]\n+pub struct GardenItemUrl(pub String);\n+\n+impl GardenItemUrl {\n+ pub fn as_str(&self) -> &str {\n+ &self.0\n+ }\n+\n+ pub fn into_inner(self) -> String {\n+ self.0\n+ }\n+\n+ /// Stored canonical id + RPC `room` field (`\"public\"` or `\"short/slug\"`).\n+ pub fn from_stored(stored: &CanonicalItemUrl, room_wire: &str) -> Self {\n+ Self(garden_href_string(stored.as_str(), room_wire))\n+ }\n+\n+ /// Like [`Self::from_stored`] but accepts a string that may already be canonical.\n+ pub fn from_storage_str(stored: &str, room_wire: &str) -> Self {\n+ Self(garden_href_string(stored, room_wire))\n+ }\n+}\n+\n+impl fmt::Display for GardenItemUrl {\n+ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {\n+ self.0.fmt(f)\n+ }\n+}\n+\n+fn garden_href_string(item: &str, room_wire: &str) -> String {\n+ let room = room_wire.trim();\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+ 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+ let root = CanonicalItemUrl::ontology_root();\n+ let item_norm = c.as_str().trim_end_matches('/');\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+ } else {\n+ format!(\"https://slug.social/r/{short}/{slug}/~/{}\", tail)\n+ };\n+ }\n+ if item_norm == root_norm {\n+ return format!(\"https://slug.social/r/{short}/{slug}/~\");\n+ }\n+ api_path_or_url(item)\n+}\n+\n+/// Forum thread URL for JSON (`/t/…` or `/r/…/t/…` on slug.social).\n+#[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Ord, Hash, Serialize, Deserialize)]\n+#[serde(transparent)]\n+pub struct ForumThreadUrl(pub String);\n+\n+impl ForumThreadUrl {\n+ pub fn as_str(&self) -> &str {\n+ &self.0\n+ }\n+\n+ pub fn into_inner(self) -> String {\n+ self.0\n+ }\n+\n+ pub fn from_room_tag(room_wire: &str, thread_tag: &str) -> Self {\n+ let room = room_wire.trim();\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 {\n+ format!(\"https://slug.social/t/{tag}\")\n+ })\n+ }\n+}\n+\n+impl fmt::Display for ForumThreadUrl {\n+ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {\n+ self.0.fmt(f)\n+ }\n+}\n+\n+/// `~/a/b` style path for list UIs (paths index `path` field).\n+#[derive(Debug, Clone, PartialEq, Eq, Hash, Serialize, Deserialize)]\n+#[serde(transparent)]\n+pub struct TildeOntologyPath(pub String);\n+\n+impl TildeOntologyPath {\n+ pub fn from_stored(c: &CanonicalItemUrl) -> Self {\n+ let s = match c.tilde_tail() {\n+ Some(tail) if !tail.is_empty() => format!(\"~/{}\", tail),\n+ Some(_) => \"~/\".to_string(),\n+ None => c.to_string(),\n+ };\n+ Self(s)\n+ }\n+\n+ pub fn as_str(&self) -> &str {\n+ &self.0\n+ }\n+}\n+\n+impl fmt::Display for TildeOntologyPath {\n+ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {\n+ self.0.fmt(f)\n+ }\n+}\n+\n+#[cfg(test)]\n+mod tests {\n+ use super::*;\n+\n+ #[test]\n+ fn canonical_parent_deep() {\n+ let c = CanonicalItemUrl::parse(\"~/a/b/c\").unwrap();\n+ assert_eq!(c.parent().unwrap().as_str(), \"https://slug.social/~/a/b\");\n+ }\n+\n+ #[test]\n+ fn canonical_parent_one_level() {\n+ let c = CanonicalItemUrl::parse(\"~/a\").unwrap();\n+ assert_eq!(c.parent().unwrap().as_str(), \"https://slug.social/~\");\n+ }\n+\n+ #[test]\n+ fn canonical_parent_root_is_none() {\n+ let root = CanonicalItemUrl::parse(\"~/\").unwrap();\n+ assert!(root.parent().is_none());\n+ }\n+\n+ #[test]\n+ fn tilde_segments_deep() {\n+ let c = CanonicalItemUrl::parse(\"~/a/b\").unwrap();\n+ assert_eq!(c.tilde_segments(), vec![\"~\", \"a\", \"b\"]);\n+ }\n+\n+ #[test]\n+ fn tilde_segments_root() {\n+ let c = CanonicalItemUrl::parse(\"~/\").unwrap();\n+ assert_eq!(c.tilde_segments(), vec![\"~\"]);\n+ }\n+\n+ #[test]\n+ fn tilde_segments_non_ontology_is_empty() {\n+ let c = CanonicalItemUrl::parse(\"https://example.com/foo\").unwrap();\n+ assert_eq!(c.tilde_segments(), Vec::<&str>::new());\n+ }\n+\n+ #[test]\n+ fn garden_public_passthrough_https() {\n+ let u = \"https://slug.social/~/a/b\";\n+ assert_eq!(GardenItemUrl::from_storage_str(u, \"public\").as_str(), u);\n+ }\n+\n+ #[test]\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+ );\n+ }\n+\n+ #[test]\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+ );\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+ );\n+ }\n+\n+ #[test]\n+ fn garden_external_url_untouched_in_private_room() {\n+ let u = \"https://example.com/z\";\n+ assert_eq!(GardenItemUrl::from_storage_str(u, \"9ab12cd/my-room\").as_str(), u);\n+ }\n+\n+ #[test]\n+ fn forum_web_public_vs_room() {\n+ assert_eq!(\n+ ForumThreadUrl::from_room_tag(\"public\", \"debate\").as_str(),\n+ \"https://slug.social/t/debate\"\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+ );\n+ }\n+}\n\n\nSide B — contributor: tommy-mor\nSide B — commit message:\n[6d04afc2] refactor\n\nSide B — unified diff (full patch):\ndiff --git a/Cargo.lock b/Cargo.lock\nindex 2cea973082716e761ef6f5dd5886acc08ff9aac0..8c43fb75c472b102e6e1d3b837dce3355be898f2 100644\n--- a/Cargo.lock\n+++ b/Cargo.lock\n@@ -17,6 +17,28 @@ version = \"1.0.102\"\n source = \"registry+https://github.com/rust-lang/crates.io-index\"\n checksum = \"7f202df86484c868dbad7eaa557ef785d5c66295e41b460ef922eca0723b842c\"\n \n+[[package]]\n+name = \"async-stream\"\n+version = \"0.3.6\"\n+source = \"registry+https://github.com/rust-lang/crates.io-index\"\n+checksum = \"0b5a71a6f37880a80d1d7f19efd781e4b5de42c88f0722cc13bcb6cc2cfe8476\"\n+dependencies = [\n+ \"async-stream-impl\",\n+ \"futures-core\",\n+ \"pin-project-lite\",\n+]\n+\n+[[package]]\n+name = \"async-stream-impl\"\n+version = \"0.3.6\"\n+source = \"registry+https://github.com/rust-lang/crates.io-index\"\n+checksum = \"c7c24de15d275a1ecfd47a380fb4d5ec9bfe0933f309ed5e705b775596a3574d\"\n+dependencies = [\n+ \"proc-macro2\",\n+ \"quote\",\n+ \"syn\",\n+]\n+\n [[package]]\n name = \"async-trait\"\n version = \"0.1.89\"\n@@ -1242,9 +1264,11 @@ dependencies = [\n name = \"sorter2-server\"\n version = \"0.0.1\"\n dependencies = [\n+ \"async-stream\",\n \"axum\",\n \"axum-extra\",\n \"dotenvy\",\n+ \"futures-util\",\n \"maud\",\n \"reqwest\",\n \"serde\",\ndiff --git a/server/Cargo.toml b/server/Cargo.toml\nindex bd600138b613bd0f546bdec217a5334cdcb20aa5..c940acb687fb141d21760a3d6656172013cf6f41 100644\n--- a/server/Cargo.toml\n+++ b/server/Cargo.toml\n@@ -18,6 +18,8 @@ tracing = \"0.1\"\n tracing-subscriber = { version = \"0.3\", features = [\"env-filter\"] }\n reqwest = { version = \"0.12\", features = [\"json\"] }\n dotenvy = \"0.15\"\n+async-stream = \"0.3\"\n+futures-util = { version = \"0.3\", default-features = false, features = [\"std\"] }\n \n [dev-dependencies]\n reqwest = { version = \"0.12\", features = [\"json\"] }\ndiff --git a/server/src/api/ui_html.rs b/server/src/api/ui_html.rs\nindex b33a84e8bb5e817b26592868d88090e6d664d950..7af6527d03c483f33f3469ce6766c01a554c5fe3 100644\n--- a/server/src/api/ui_html.rs\n+++ b/server/src/api/ui_html.rs\n@@ -6,7 +6,8 @@ use axum::{\n use std::collections::HashMap;\n \n use crate::{\n- html::{entity_section, input_panel, js_string_literal, ranking_panel, JsBuilder},\n+ fetch,\n+ html::{input_panel, js_string_literal, ranking_panel, JsBuilder},\n parser::parse_reddit_url,\n path_types::ItemId,\n reddit::ensure_partial_tree,\n@@ -89,18 +90,8 @@ pub async fn post_ui_html(\n },\n HtmlUiAction::FetchEntity { item } => {\n let id = parse_item_param(&item);\n- if id.is_root() {\n- return ui_js_warn(\"nothing to fetch for the root\").into_response();\n- }\n- state.queue_entity_fetch(id.clone());\n- let tree = state.tree.read().await;\n- let empty = crate::reducer::NodeState::default();\n- let node = tree.get(&id).unwrap_or(&empty);\n- let panel = entity_section(&id, node, true);\n- JsBuilder::new()\n- .morph_selector(\"#entity-section\", panel)\n- .into_response()\n- },\n+ fetch::fetch_entity_stream(state, id).into_response()\n+ }\n }\n }\n \ndiff --git a/server/src/fetch/html.rs b/server/src/fetch/html.rs\nnew file mode 100644\nindex 0000000000000000000000000000000000000000..63634508496e224c38b9ec0308b7a6086462f925\n--- /dev/null\n+++ b/server/src/fetch/html.rs\n@@ -0,0 +1,67 @@\n+//! Markup for entity import / “Fetch from Reddit” (`POST /ui`, SSE response).\n+\n+use maud::{html, Markup};\n+\n+use crate::{\n+ form_template::template_json_compact,\n+ path_types::ItemId,\n+ reddit::is_fetchable,\n+ reducer::NodeState,\n+ ui_action::UI_RPC_FIELD,\n+};\n+\n+fn entity_panel(node: &NodeState) -> Markup {\n+ html! {\n+ @if let Some(data) = &node.data {\n+ div id=\"entity-panel\" class=\"entity-card\" {\n+ h2 { (data.title) }\n+ @if let Some(author) = &data.author {\n+ p class=\"muted small\" { \"by \" (author) }\n+ }\n+ @if let Some(body) = &data.body_html {\n+ div class=\"entity-body\" { (maud::PreEscaped(body)) }\n+ }\n+ }\n+ }\n+ }\n+}\n+\n+/// Reddit/API import — `POST /ui` with `fetch_entity` returns an SSE stream.\n+pub fn fetch_entity_panel(item: &ItemId, has_data: bool, fetching: bool) -> Markup {\n+ if !is_fetchable(item) {\n+ return html! {};\n+ }\n+ let label = if fetching {\n+ \"Fetching…\"\n+ } else if has_data {\n+ \"Fetch more\"\n+ } else {\n+ \"Fetch from Reddit\"\n+ };\n+ let rpc = template_json_compact(&serde_json::json!({\n+ \"action\": \"fetch_entity\",\n+ \"item\": item.as_str(),\n+ }))\n+ .expect(\"fetch_entity rpc template\");\n+ html! {\n+ form method=\"post\" action=\"/ui\" id=\"fetch-entity-form\" class=\"fetch-entity-form\" {\n+ input type=\"hidden\" name=(UI_RPC_FIELD) value=(rpc);\n+ @if fetching {\n+ button type=\"submit\" class=\"btn-secondary\" disabled { (label) }\n+ } @else {\n+ button type=\"submit\" class=\"btn-secondary\" { (label) }\n+ }\n+ }\n+ }\n+}\n+\n+/// Entity card + fetch control (target `#entity-section` for Idiomorph / SSE).\n+pub fn entity_section(item: &ItemId, node: &NodeState, fetching: bool) -> Markup {\n+ let has_data = node.data.is_some();\n+ html! {\n+ section id=\"entity-section\" class=\"demo-panel\" {\n+ (entity_panel(node))\n+ (fetch_entity_panel(item, has_data, fetching))\n+ }\n+ }\n+}\ndiff --git a/server/src/fetch/mod.rs b/server/src/fetch/mod.rs\nnew file mode 100644\nindex 0000000000000000000000000000000000000000..2290f9d3a0f1cbf1806c6339f82a4515c11cc3d3\n--- /dev/null\n+++ b/server/src/fetch/mod.rs\n@@ -0,0 +1,115 @@\n+//! Entity import over `POST /ui` as SSE (Reddit worker in [`crate::reddit`]).\n+\n+pub mod html;\n+\n+use std::convert::Infallible;\n+use std::time::Duration;\n+\n+use async_stream::stream;\n+use axum::response::sse::{Event, KeepAlive, Sse};\n+use futures_util::Stream;\n+use serde::Serialize;\n+use tokio::sync::oneshot;\n+\n+use crate::{\n+ path_types::ItemId,\n+ reddit::FetchJobResult,\n+ reducer::NodeState,\n+ state::AppState,\n+};\n+\n+pub fn now_ms() -> i64 {\n+ let t = std::time::SystemTime::now()\n+ .duration_since(std::time::UNIX_EPOCH)\n+ .unwrap_or_default();\n+ t.as_millis() as i64\n+}\n+\n+#[derive(Serialize)]\n+struct SseMorphPayload {\n+ selector: &'static str,\n+ html: String,\n+}\n+\n+fn morph_complete_event(html: maud::Markup) -> Event {\n+ let payload = SseMorphPayload {\n+ selector: \"#entity-section\",\n+ html: html.into_string(),\n+ };\n+ let data = serde_json::to_string(&payload).unwrap_or_else(|_| \"{}\".into());\n+ Event::default().event(\"complete\").data(data)\n+}\n+\n+/// Stream `fetching` → `complete` / `error` for [`crate::ui_action::HtmlUiAction::FetchEntity`].\n+pub fn fetch_entity_stream(\n+ state: AppState,\n+ id: ItemId,\n+) -> Sse>> {\n+ tracing::debug!(item = %id, \"fetch entity stream opened\");\n+\n+ let stream = stream! {\n+ if id.is_root() {\n+ yield Ok(Event::default().event(\"error\").data(\"{\\\"message\\\":\\\"nothing to fetch for the root\\\"}\"));\n+ return;\n+ }\n+\n+ if !crate::reddit::is_fetchable(&id) {\n+ tracing::debug!(item = %id, \"fetch stream: not fetchable\");\n+ yield Ok(Event::default().event(\"error\").data(\"{\\\"message\\\":\\\"this page cannot be fetched from Reddit\\\"}\"));\n+ return;\n+ }\n+\n+ let fetching_html = {\n+ let tree = state.tree.read().await;\n+ let empty = NodeState::default();\n+ let node = tree.get(&id).unwrap_or(&empty);\n+ html::entity_section(&id, node, true).into_string()\n+ };\n+ let fetching_payload = serde_json::json!({\n+ \"selector\": \"#entity-section\",\n+ \"html\": fetching_html,\n+ });\n+ yield Ok(Event::default().event(\"fetching\").data(fetching_payload.to_string()));\n+\n+ let (tx, rx) = oneshot::channel();\n+ state.reddit.request_fetch(id.clone(), true, Some(tx));\n+ tracing::debug!(item = %id, \"fetch stream: queued reddit job\");\n+\n+ let result = match rx.await {\n+ Ok(r) => r,\n+ Err(_) => {\n+ tracing::warn!(item = %id, \"fetch stream: worker dropped oneshot\");\n+ FetchJobResult::Failed(\"reddit worker stopped\".into())\n+ }\n+ };\n+\n+ tracing::debug!(item = %id, ?result, \"fetch stream: job finished\");\n+\n+ match result {\n+ FetchJobResult::Imported | FetchJobResult::NotFound => {\n+ let tree = state.tree.read().await;\n+ let empty = NodeState::default();\n+ let node = tree.get(&id).unwrap_or(&empty);\n+ yield Ok(morph_complete_event(html::entity_section(&id, node, false)));\n+ }\n+ FetchJobResult::SkippedCached | FetchJobResult::SkippedDuplicate => {\n+ let tree = state.tree.read().await;\n+ let empty = NodeState::default();\n+ let node = tree.get(&id).unwrap_or(&empty);\n+ yield Ok(morph_complete_event(html::entity_section(&id, node, false)));\n+ }\n+ FetchJobResult::RateLimited { reset_secs } => {\n+ yield Ok(Event::default().event(\"error\").data(\n+ serde_json::json!({\"message\": format!(\"Reddit rate limit — retry in {reset_secs}s\")}).to_string(),\n+ ));\n+ }\n+ FetchJobResult::Failed(msg) => {\n+ yield Ok(Event::default().event(\"error\").data(\n+ serde_json::json!({\"message\": msg}).to_string(),\n+ ));\n+ }\n+ }\n+ };\n+\n+ Sse::new(stream).keep_alive(KeepAlive::new().interval(Duration::from_secs(15)))\n+}\ndiff --git a/server/src/html/mod.rs b/server/src/html/mod.rs\nindex db5b4c7f06b0be64603981166835cde268234f67..9314a7556306ddab969b896dbf4126b542a46722 100644\n--- a/server/src/html/mod.rs\n+++ b/server/src/html/mod.rs\n@@ -7,10 +7,10 @@ use axum::{\n use maud::{html, Markup, DOCTYPE};\n \n use crate::{\n+ fetch::html::entity_section,\n form_template::template_json_compact,\n path_types::ItemId,\n ranking::{top_bottom, RankedItem},\n- reddit::is_fetchable,\n reducer::{GroupState, NodeState},\n state::AppState,\n ui_action::UI_RPC_FIELD,\n@@ -149,62 +149,6 @@ pub fn breadcrumb_path(item: &ItemId) -> Markup {\n }\n }\n \n-fn entity_panel(node: &NodeState) -> Markup {\n- html! {\n- @if let Some(data) = &node.data {\n- div id=\"entity-panel\" class=\"entity-card\" {\n- h2 { (data.title) }\n- @if let Some(author) = &data.author {\n- p class=\"muted small\" { \"by \" (author) }\n- }\n- @if let Some(body) = &data.body_html {\n- div class=\"entity-body\" { (maud::PreEscaped(body)) }\n- }\n- }\n- }\n- }\n-}\n-\n-/// Reddit/API import control — only shown on fetchable pages; never auto-fires.\n-pub fn fetch_entity_panel(item: &ItemId, has_data: bool, fetching: bool) -> Markup {\n- if !is_fetchable(item) {\n- return html! {};\n- }\n- let label = if fetching {\n- \"Fetching…\"\n- } else if has_data {\n- \"Fetch more\"\n- } else {\n- \"Fetch from Reddit\"\n- };\n- let rpc = template_json_compact(&serde_json::json!({\n- \"action\": \"fetch_entity\",\n- \"item\": item.as_str(),\n- }))\n- .expect(\"fetch_entity rpc template\");\n- html! {\n- form method=\"post\" action=\"/ui\" id=\"fetch-entity-form\" class=\"fetch-entity-form\" {\n- input type=\"hidden\" name=(UI_RPC_FIELD) value=(rpc);\n- @if fetching {\n- button type=\"submit\" class=\"btn-secondary\" disabled { (label) }\n- } @else {\n- button type=\"submit\" class=\"btn-secondary\" { (label) }\n- }\n- }\n- }\n-}\n-\n-/// Entity card + explicit fetch control (morphed as `#entity-section`).\n-pub fn entity_section(item: &ItemId, node: &NodeState, fetching: bool) -> Markup {\n- let has_data = node.data.is_some();\n- html! {\n- section id=\"entity-section\" class=\"demo-panel\" {\n- (entity_panel(node))\n- (fetch_entity_panel(item, has_data, fetching))\n- }\n- }\n-}\n-\n fn rank_list(label: &str, items: &[RankedItem], start_rank: usize) -> Markup {\n html! {\n @if !items.is_empty() {\ndiff --git a/server/src/lib.rs b/server/src/lib.rs\nindex 79b173f391a96ae5d0d96fd656e1e8d2dd070d09..0677363e0ed21d244bfa065f7ec728549ddd9e50 100644\n--- a/server/src/lib.rs\n+++ b/server/src/lib.rs\n@@ -1,6 +1,7 @@\n pub mod api;\n pub mod event_log;\n pub mod events;\n+pub mod fetch;\n pub mod form_template;\n pub mod html;\n pub mod parser;\ndiff --git a/server/src/reddit.rs b/server/src/reddit.rs\nindex ff0f01e57b18af878eb5be3efc47204a7673589d..0e6ce32720951a58456852b67fb76a85dd9f4aad 100644\n--- a/server/src/reddit.rs\n+++ b/server/src/reddit.rs\n@@ -7,12 +7,12 @@ use std::time::{Duration, Instant};\n use reqwest::{header, Client, StatusCode};\n use serde::Deserialize;\n use serde_json::Value;\n-use tokio::sync::{mpsc, RwLock};\n+use tokio::sync::{mpsc, oneshot, RwLock};\n \n use crate::{\n event_log::EventLog,\n events::Event,\n- html::now_ms,\n+ fetch::now_ms,\n path_types::ItemId,\n reducer::GlobalTree,\n };\n@@ -22,10 +22,21 @@ pub fn ensure_partial_tree(tree: &mut GlobalTree, id: &ItemId) {\n tree.ensure_path(id);\n }\n \n+#[derive(Debug, Clone, PartialEq, Eq)]\n+pub enum FetchJobResult {\n+ Imported,\n+ NotFound,\n+ SkippedDuplicate,\n+ SkippedCached,\n+ RateLimited { reset_secs: u64 },\n+ Failed(String),\n+}\n+\n pub struct RedditCommand {\n pub id: ItemId,\n /// User-initiated fetch bypasses the in-memory \"recently fetched\" cache.\n pub force: bool,\n+ pub done: Option>,\n }\n \n #[derive(Clone)]\n@@ -72,14 +83,29 @@ impl RedditBroker {\n .build()\n .expect(\"reqwest client\");\n \n+ tracing::debug!(\n+ api_base = %config.api_base,\n+ oauth_base = %config.oauth_base,\n+ oauth = config.creds.is_some(),\n+ \"reddit worker started\"\n+ );\n+\n tokio::spawn(reddit_worker(rx, tree, event_log, client, config));\n \n Self { tx }\n }\n \n /// Queue a fetch; drops when the channel is full (backpressure).\n- pub fn request_fetch(&self, id: ItemId, force: bool) {\n- let _ = self.tx.try_send(RedditCommand { id, force });\n+ pub fn request_fetch(\n+ &self,\n+ id: ItemId,\n+ force: bool,\n+ done: Option>,\n+ ) {\n+ match self.tx.try_send(RedditCommand { id: id.clone(), force, done }) {\n+ Ok(()) => tracing::debug!(item = %id, force, \"reddit fetch queued\"),\n+ Err(_) => tracing::warn!(item = %id, \"reddit fetch queue full, dropped\"),\n+ }\n }\n }\n \n@@ -95,8 +121,6 @@ impl RedditApiConfig {\n }\n \n impl RedditCredentials {\n- /// Reddit's OAuth docs call these \"client id\" and \"client secret\"; the app\n- /// registration UI often labels them \"app id\" / \"app secret\" — same values.\n fn from_env() -> Option {\n let client_id = std::env::var(\"REDDIT_CLIENT_ID\")\n .or_else(|_| std::env::var(\"REDDIT_APP_ID\"))\n@@ -128,12 +152,10 @@ pub fn default_user_agent() -> String {\n })\n }\n \n-/// True when this node can be loaded from the Reddit JSON API.\n pub fn is_fetchable(id: &ItemId) -> bool {\n !map_item_to_reddit_api(id, \"https://example.com\").is_empty()\n }\n \n-/// Derive UI-facing fields from a stored payload (Reddit-specific when under reddit.com).\n pub fn entity_view_from_payload(id: &ItemId, payload: &Value) -> Option {\n if id.as_str().starts_with(\"reddit.com\") {\n return parse_reddit_view(id, payload);\n@@ -141,12 +163,17 @@ pub fn entity_view_from_payload(id: &ItemId, payload: &Value) -> Option>, result: FetchJobResult) {\n+ if let Some(tx) = done {\n+ let _ = tx.send(result);\n+ }\n+}\n+\n async fn reddit_worker(\n mut rx: mpsc::Receiver,\n tree: Arc>,\n@@ -168,15 +195,25 @@ async fn reddit_worker(\n recently_fetched.retain(|_, t| now.duration_since(*t) < cache_ttl);\n \n if in_flight.contains(&cmd.id) {\n+ tracing::debug!(item = %cmd.id, \"reddit fetch skipped: already in flight\");\n+ notify(cmd.done, FetchJobResult::SkippedDuplicate);\n continue;\n }\n if !cmd.force && recently_fetched.contains_key(&cmd.id) {\n+ tracing::debug!(item = %cmd.id, \"reddit fetch skipped: recently fetched cache\");\n+ notify(cmd.done, FetchJobResult::SkippedCached);\n continue;\n }\n \n in_flight.insert(cmd.id.clone());\n let fetch_id = cmd.id.clone();\n+ let done = cmd.done;\n \n+ tracing::debug!(\n+ item = %fetch_id,\n+ delay_ms = current_delay.as_millis(),\n+ \"reddit fetch starting after delay\"\n+ );\n tokio::time::sleep(current_delay).await;\n \n if let Some(c) = &creds {\n@@ -184,8 +221,18 @@ async fn reddit_worker(\n }\n \n let token = oauth.as_ref().map(|t| t.access_token.as_str());\n+ if token.is_some() {\n+ tracing::debug!(item = %fetch_id, \"reddit fetch using OAuth bearer\");\n+ }\n+\n+ let fetch_base = if token.is_some() {\n+ &oauth_base\n+ } else {\n+ &api_base\n+ };\n+ let outcome = do_fetch(&client, fetch_base, &fetch_id, token).await;\n \n- match do_fetch(&client, &api_base, &fetch_id, token).await {\n+ match outcome {\n Ok(FetchOutcome::Payload(payload)) => {\n let ts = now_ms();\n let event = Event::EntityImported {\n@@ -193,30 +240,49 @@ async fn reddit_worker(\n ts,\n payload: payload.clone(),\n };\n- if let Err(e) = event_log.append(&event).await {\n- tracing::warn!(\"event log append failed for {}: {}\", fetch_id, e);\n- } else {\n- apply_entity_import(&mut *tree.write().await, &fetch_id, payload);\n- recently_fetched.insert(fetch_id.clone(), Instant::now());\n- current_delay = Duration::from_millis(600);\n+ tracing::debug!(\n+ item = %fetch_id,\n+ ts,\n+ payload_keys = ?payload.as_object().map(|o| o.len()),\n+ \"reddit fetch got JSON payload, appending event\"\n+ );\n+ match event_log.append(&event).await {\n+ Err(e) => {\n+ tracing::warn!(\n+ item = %fetch_id,\n+ err = %e,\n+ \"reddit event log append failed\"\n+ );\n+ notify(done, FetchJobResult::Failed(e.to_string()));\n+ }\n+ Ok(()) => {\n+ apply_entity_import(&mut *tree.write().await, &fetch_id, payload);\n+ recently_fetched.insert(fetch_id.clone(), Instant::now());\n+ current_delay = Duration::from_millis(600);\n+ tracing::info!(item = %fetch_id, \"reddit entity imported\");\n+ notify(done, FetchJobResult::Imported);\n+ }\n }\n }\n Ok(FetchOutcome::NotFound) => {\n+ tracing::debug!(item = %fetch_id, \"reddit fetch: not found (no event written)\");\n recently_fetched.insert(fetch_id.clone(), Instant::now());\n+ notify(done, FetchJobResult::NotFound);\n }\n Ok(FetchOutcome::RateLimited { reset_secs }) => {\n- let wait = Duration::from_secs(reset_secs.max(1));\n tracing::warn!(\n- \"Reddit rate limit for {}; sleeping {}s\",\n- fetch_id,\n- wait.as_secs()\n+ item = %fetch_id,\n+ reset_secs,\n+ \"reddit rate limited\"\n );\n- tokio::time::sleep(wait).await;\n+ tokio::time::sleep(Duration::from_secs(reset_secs.max(1))).await;\n current_delay = (current_delay * 2).min(Duration::from_secs(60));\n+ notify(done, FetchJobResult::RateLimited { reset_secs });\n }\n Err(e) => {\n- tracing::warn!(\"Reddit fetch failed for {}: {}\", fetch_id, e);\n+ tracing::warn!(item = %fetch_id, err = %e, \"reddit fetch failed\");\n current_delay = (current_delay * 2).min(Duration::from_secs(60));\n+ notify(done, FetchJobResult::Failed(e));\n }\n }\n \n@@ -238,6 +304,7 @@ async fn ensure_oauth_token(\n ) -> Option {\n if let Some(t) = existing {\n if Instant::now() < t.expires_at - Duration::from_secs(60) {\n+ tracing::debug!(\"reddit OAuth token still valid\");\n return Some(t);\n }\n }\n@@ -246,6 +313,7 @@ async fn ensure_oauth_token(\n \"{}/api/v1/access_token\",\n oauth_base.trim_end_matches('/')\n );\n+ tracing::debug!(%url, \"reddit OAuth token request\");\n \n let resp = client\n .post(&url)\n@@ -257,13 +325,13 @@ async fn ensure_oauth_token(\n let resp = match resp {\n Ok(r) => r,\n Err(e) => {\n- tracing::warn!(\"Reddit OAuth token request failed: {e}\");\n+ tracing::warn!(\"reddit OAuth token request failed: {e}\");\n return None;\n }\n };\n \n if !resp.status().is_success() {\n- tracing::warn!(\"Reddit OAuth token HTTP {}\", resp.status());\n+ tracing::warn!(\"reddit OAuth token HTTP {}\", resp.status());\n return None;\n }\n \n@@ -276,11 +344,12 @@ async fn ensure_oauth_token(\n let body: TokenResponse = match resp.json().await {\n Ok(b) => b,\n Err(e) => {\n- tracing::warn!(\"Reddit OAuth token parse failed: {e}\");\n+ tracing::warn!(\"reddit OAuth token parse failed: {e}\");\n return None;\n }\n };\n \n+ tracing::debug!(expires_in = body.expires_in, \"reddit OAuth token acquired\");\n Some(OAuthToken {\n access_token: body.access_token,\n expires_at: Instant::now() + Duration::from_secs(body.expires_in),\n@@ -295,35 +364,72 @@ async fn do_fetch(\n ) -> Result {\n let url = map_item_to_reddit_api(id, api_base);\n if url.is_empty() {\n+ tracing::debug!(item = %id, \"reddit do_fetch: no API URL for item\");\n return Ok(FetchOutcome::NotFound);\n }\n \n+ tracing::debug!(item = %id, %url, bearer = bearer.is_some(), \"reddit HTTP GET\");\n+\n let mut req = client.get(&url);\n if let Some(token) = bearer {\n req = req.bearer_auth(token);\n }\n \n- let resp = req.send().await.map_err(|e| e.to_string())?;\n+ let resp = req.send().await.map_err(|e| {\n+ tracing::debug!(item = %id, %url, err = %e, \"reddit HTTP transport error\");\n+ e.to_string()\n+ })?;\n+\n+ let status = resp.status();\n+ tracing::debug!(\n+ item = %id,\n+ %url,\n+ %status,\n+ remaining = ?rate_limit_remaining(&resp),\n+ reset = ?rate_limit_reset_secs(&resp),\n+ \"reddit HTTP response\"\n+ );\n \n- if resp.status() == StatusCode::TOO_MANY_REQUESTS {\n+ if status == StatusCode::TOO_MANY_REQUESTS {\n let reset = rate_limit_reset_secs(&resp);\n return Ok(FetchOutcome::RateLimited { reset_secs: reset });\n }\n \n- if resp.status() == StatusCode::SERVICE_UNAVAILABLE {\n- return Err(\"Reddit unavailable (503)\".to_string());\n+ if status == StatusCode::SERVICE_UNAVAILABLE {\n+ return Err(\"Reddit unavailable (503)\".into());\n }\n \n- if !resp.status().is_success() {\n+ if !status.is_success() {\n+ let body = resp.text().await.unwrap_or_default();\n+ tracing::debug!(\n+ item = %id,\n+ %status,\n+ body_len = body.len(),\n+ body_prefix = %body.chars().take(240).collect::(),\n+ \"reddit non-success body\"\n+ );\n return Ok(FetchOutcome::NotFound);\n }\n \n if rate_limit_remaining(&resp) == Some(0) {\n let reset = rate_limit_reset_secs(&resp);\n+ tracing::debug!(item = %id, reset_secs = reset, \"reddit headers: rate limit exhausted\");\n return Ok(FetchOutcome::RateLimited { reset_secs: reset });\n }\n \n- let payload: Value = resp.json().await.map_err(|e| e.to_string())?;\n+ let text = resp.text().await.map_err(|e| e.to_string())?;\n+ tracing::debug!(item = %id, bytes = text.len(), \"reddit response body received\");\n+\n+ let payload: Value = serde_json::from_str(&text).map_err(|e| {\n+ tracing::debug!(\n+ item = %id,\n+ err = %e,\n+ body_prefix = %text.chars().take(240).collect::(),\n+ \"reddit JSON parse failed\"\n+ );\n+ format!(\"invalid JSON: {e}\")\n+ })?;\n+\n Ok(FetchOutcome::Payload(payload))\n }\n \n@@ -344,7 +450,6 @@ fn rate_limit_reset_secs(resp: &reqwest::Response) -> u64 {\n .unwrap_or(5)\n }\n \n-/// Map canonical item id to a Reddit JSON API URL under `api_base`.\n pub fn map_item_to_reddit_api(id: &ItemId, api_base: &str) -> String {\n let path = id.as_str();\n if !path.starts_with(\"reddit.com/\") && path != \"reddit.com\" {\n@@ -445,26 +550,6 @@ mod tests {\n map_item_to_reddit_api(&id, \"https://www.reddit.com\"),\n \"https://www.reddit.com/r/rust/about.json?raw_json=1\"\n );\n- assert_eq!(\n- map_item_to_reddit_api(&id, \"http://127.0.0.1:9999\"),\n- \"http://127.0.0.1:9999/r/rust/about.json?raw_json=1\"\n- );\n- }\n-\n- #[test]\n- fn map_post_url() {\n- let id = ItemId::parse(\"reddit.com/r/amitheasshole/comments/1trnvdl\").unwrap();\n- assert_eq!(\n- map_item_to_reddit_api(&id, \"https://www.reddit.com\"),\n- \"https://www.reddit.com/r/amitheasshole/comments/1trnvdl.json?raw_json=1\"\n- );\n- }\n-\n- #[test]\n- fn is_fetchable_reddit_sub() {\n- let id = ItemId::parse(\"reddit.com/r/rust\").unwrap();\n- assert!(is_fetchable(&id));\n- assert!(!is_fetchable(&ItemId::opaque(\"example.com/x\")));\n }\n \n #[test]\n@@ -477,19 +562,5 @@ mod tests {\n )\n .unwrap();\n assert_eq!(entity.title, \"The Rust Programming Language\");\n- assert!(entity.body_html.as_ref().is_some_and(|b| b.contains(\"Rust\")));\n- }\n-\n- #[test]\n- fn parse_post_fixture() {\n- let json = r#\"[{\"kind\":\"Listing\",\"data\":{\"children\":[{\"kind\":\"t3\",\"data\":{\"title\":\"AITA\",\"author\":\"op\",\"selftext_html\":\"<p>hi</p>\",\"thumbnail\":\"https://b.thumbs.redditmedia.com/x.jpg\"}}]}}]\"#;\n- let v: Value = serde_json::from_str(json).unwrap();\n- let entity = entity_view_from_payload(\n- &ItemId::parse(\"reddit.com/r/x/comments/abc\").unwrap(),\n- &v,\n- )\n- .unwrap();\n- assert_eq!(entity.title, \"AITA\");\n- assert_eq!(entity.author.as_deref(), Some(\"op\"));\n }\n }\ndiff --git a/server/src/state.rs b/server/src/state.rs\nindex d71d1079a8f486cdab15795384aef0b81b32544d..e7ff9f663e45b5e168d6a3869948e3bd890966d4 100644\n--- a/server/src/state.rs\n+++ b/server/src/state.rs\n@@ -143,9 +143,9 @@ impl AppState {\n Ok(())\n }\n \n- /// User-initiated Reddit/API import (via \"Fetch more\" — never on paste or navigate).\n- pub fn queue_entity_fetch(&self, id: ItemId) {\n- self.reddit.request_fetch(id, true);\n+ /// User-initiated Reddit/API import (SSE / fetch module only).\n+ pub fn queue_entity_fetch(&self, id: ItemId, done: Option>) {\n+ self.reddit.request_fetch(id, true, done);\n }\n \n pub async fn record_vote(\ndiff --git a/server/src/ui_action.rs b/server/src/ui_action.rs\nindex 3d6a49a2a3fb950752827efe1f5a049308f09baf..ef9ac873fc0442e0b960f144309c8e91124d7884 100644\n--- a/server/src/ui_action.rs\n+++ b/server/src/ui_action.rs\n@@ -26,7 +26,7 @@ pub enum HtmlUiAction {\n ParseQuery {\n query: String,\n },\n- /// Fetch upstream entity data for the current page (explicit user action only).\n+ /// Import entity data; `POST /ui` responds with `text/event-stream` (not JS).\n FetchEntity {\n item: String,\n },\ndiff --git a/server/static/sorter_ui.js b/server/static/sorter_ui.js\nindex d9b016f197547f37ca4b2bcdd7ee6b673d0fb3f0..fe7bfc657c0fccae5c596d005b0e807abefec677 100644\n--- a/server/static/sorter_ui.js\n+++ b/server/static/sorter_ui.js\n@@ -1,5 +1,5 @@\n /**\n- * sorter2 web UI: fetch/eval for POST /ui. No product logic here.\n+ * sorter2 web UI: POST /ui returns JS (morph) or SSE (entity fetch).\n */\n (function () {\n function evalJs(js) {\n@@ -8,15 +8,98 @@\n }\n }\n \n+ function morphSelector(selector, html) {\n+ var el = document.querySelector(selector);\n+ if (el && typeof Idiomorph !== 'undefined') {\n+ Idiomorph.morph(el, html);\n+ }\n+ }\n+\n+ function handleSseEvent(eventType, data, form) {\n+ if (eventType === 'fetching' || eventType === 'complete') {\n+ try {\n+ var msg = JSON.parse(data);\n+ morphSelector(msg.selector || '#entity-section', msg.html);\n+ } catch (err) {\n+ console.warn('fetch morph parse', err);\n+ }\n+ }\n+ if (eventType === 'complete' || eventType === 'error') {\n+ var btn = form && form.querySelector('button[type=\"submit\"]');\n+ if (btn) btn.disabled = false;\n+ }\n+ if (eventType === 'error') {\n+ try {\n+ var err = JSON.parse(data);\n+ console.warn('fetch error:', err.message || data);\n+ } catch (_e) {\n+ console.warn('fetch error:', data);\n+ }\n+ }\n+ }\n+\n+ function consumeSseStream(response, form) {\n+ var reader = response.body.getReader();\n+ var decoder = new TextDecoder();\n+ var buffer = '';\n+ var eventType = '';\n+ var dataLines = [];\n+\n+ function dispatch() {\n+ if (!eventType && dataLines.length === 0) return;\n+ handleSseEvent(eventType || 'message', dataLines.join('\\n'), form);\n+ eventType = '';\n+ dataLines = [];\n+ }\n+\n+ function pump() {\n+ return reader.read().then(function (chunk) {\n+ if (chunk.done) {\n+ dispatch();\n+ return;\n+ }\n+ buffer += decoder.decode(chunk.value, { stream: true });\n+ var parts = buffer.split('\\n');\n+ buffer = parts.pop() || '';\n+ for (var i = 0; i < parts.length; i++) {\n+ var line = parts[i].replace(/\\r$/, '');\n+ if (line === '') {\n+ dispatch();\n+ } else if (line.indexOf('event:') === 0) {\n+ eventType = line.slice(6).trim();\n+ } else if (line.indexOf('data:') === 0) {\n+ dataLines.push(line.slice(5).trim());\n+ }\n+ }\n+ return pump();\n+ });\n+ }\n+\n+ return pump();\n+ }\n+\n function postUiForm(form) {\n+ var btn = form.querySelector('button[type=\"submit\"]');\n+ if (form.id === 'fetch-entity-form' && btn) {\n+ btn.disabled = true;\n+ }\n return fetch(form.action, {\n method: 'POST',\n body: new URLSearchParams(new FormData(form)),\n headers: { 'Content-Type': 'application/x-www-form-urlencoded' },\n credentials: 'same-origin',\n }).then(function (resp) {\n- return resp.text();\n- }).then(evalJs);\n+ var ct = resp.headers.get('content-type') || '';\n+ if (ct.indexOf('text/event-stream') !== -1) {\n+ return consumeSseStream(resp, form);\n+ }\n+ return resp.text().then(evalJs);\n+ }).catch(function (err) {\n+ if (form.id === 'fetch-entity-form' && btn) {\n+ btn.disabled = false;\n+ }\n+ console.warn('POST /ui failed', err);\n+ });\n }\n \n function initSorterUi() {\ndiff --git a/test/reddit_import.clj b/test/reddit_import.clj\nindex 54edaedeef08718c8f184d6aa468d8e6415068c7..17f2ee39e1498b0b6bb6a9d8a7e35608b0bd1b32 100644\n--- a/test/reddit_import.clj\n+++ b/test/reddit_import.clj\n@@ -44,10 +44,12 @@\n (do (Thread/sleep 200) (recur))\n false))))))\n \n-(defn- curl-post-ui [base rpc-json]\n+(defn- curl-fetch-ui-sse [base item]\n (process/shell {:out :string :err :string}\n- \"curl\" \"-sf\" \"-X\" \"POST\" (str base \"/ui\")\n- \"--data-urlencode\" (str \"__rpc__=\" rpc-json)))\n+ \"curl\" \"-sfN\" \"--max-time\" \"20\"\n+ \"-X\" \"POST\" (str base \"/ui\")\n+ \"--data-urlencode\"\n+ (str \"__rpc__={\\\"action\\\":\\\"fetch_entity\\\",\\\"item\\\":\\\"\" item \"\\\"}\")))\n \n (defn- wait-event-log [path ms]\n (let [deadline (+ (System/currentTimeMillis) ms)]\n@@ -98,11 +100,12 @@\n \"curl\" \"-sf\" browse-url))]\n (is (str/includes? before \"Fetch from Reddit\"))\n (is (not (str/includes? before \"The Rust Programming Language\")))\n- (let [rpc \"{\\\"action\\\":\\\"fetch_entity\\\",\\\"item\\\":\\\"reddit.com/r/rust\\\"}\"\n- post (curl-post-ui app-base rpc)\n- log-path (str data-dir \"/events.jsonl\")]\n- (is (zero? (:exit post)) \"fetch_entity POST succeeds\")\n- (is (wait-event-log log-path 10000) \"event log written\")\n+ (let [log-path (str data-dir \"/events.jsonl\")\n+ sse (curl-fetch-ui-sse app-base \"reddit.com/r/rust\")]\n+ (is (zero? (:exit sse)) \"POST /ui fetch_entity SSE succeeds\")\n+ (is (str/includes? (:out sse) \"event: complete\"))\n+ (is (str/includes? (:out sse) \"The Rust Programming Language\"))\n+ (is (wait-event-log log-path 2000) \"event log written\")\n (let [after (:out (process/shell {:out :string :err :string}\n \"curl\" \"-sf\" browse-url))\n log (slurp (io/file log-path))]\n","role":"user"}],"model":"~x-ai/grok-latest"}