{"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[674964ef] refactor: Deref for href newtypes, CanonicalItemUrl through resolve_item\n\n- Implement Deref<Target=str> for GardenItemUrl, ForumThreadUrl, TildeOntologyPath\n- resolve_item returns CanonicalItemUrl; validate uses HashSet<CanonicalItemUrl>\n- compute_scope_rank_changes keys are CanonicalItemUrl; pair RPC uses Vec pool\n- pick_random_distinct_canonical; connectivity stats on &[CanonicalItemUrl]\n- Global rank unranked uses stored ids before GardenItemUrl mapping\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 03b3e77911ccd662bec8635345dafe2593cf242e..1b291db83df7364a026f2e147e0a29a70a399371 100644\n--- a/server/src/api/helpers.rs\n+++ b/server/src/api/helpers.rs\n@@ -30,13 +30,13 @@ pub fn now_ms() -> i64 {\n     t.as_millis() as i64\n }\n \n-/// Resolve an item path as a first-class canonical path.\n-pub fn resolve_item(item: &str) -> Result<String, String> {\n+/// Resolve DSL/user input to a stored canonical item id.\n+pub fn resolve_item(item: &str) -> Result<CanonicalItemUrl, String> {\n     let canonical = canonicalize_item(item);\n     if canonical.is_empty() {\n         return Err(format!(\"empty item path: `{}`\", item));\n     }\n-    Ok(canonical)\n+    Ok(CanonicalItemUrl(canonical))\n }\n \n pub fn parse_parent_specs(parent: Option<&String>) -> Vec<String> {\n@@ -94,7 +94,7 @@ pub fn paginate_rankings(\n     (out_components, out_unranked)\n }\n \n-pub fn pick_random_distinct(items: &[String]) -> Option<(String, String)> {\n+pub fn pick_random_distinct_canonical(items: &[CanonicalItemUrl]) -> Option<(CanonicalItemUrl, CanonicalItemUrl)> {\n     use rand::seq::SliceRandom;\n     if items.len() < 2 {\n         return None;\n@@ -123,15 +123,12 @@ pub fn is_pair_voted(group: &crate::reducer::GroupState, a: &str, b: &str) -> bo\n     group.voted_pairs.contains(&(i, j))\n }\n \n-pub fn compute_connectivity_stats(group: &crate::reducer::GroupState, pool: &[String]) -> ConnectivityStats {\n+pub fn compute_connectivity_stats(group: &crate::reducer::GroupState, pool: &[CanonicalItemUrl]) -> ConnectivityStats {\n     let n = pool.len();\n \n     let global_idxs: Vec<Option<usize>> = pool\n         .iter()\n-        .map(|it| {\n-            let key = CanonicalItemUrl(it.clone());\n-            group.item_to_idx.get(&key).copied()\n-        })\n+        .map(|it| group.item_to_idx.get(it).copied())\n         .collect();\n     let present: Vec<usize> = global_idxs.iter().filter_map(|x| *x).collect();\n \ndiff --git a/server/src/api/mod.rs b/server/src/api/mod.rs\nindex cf22cb0129366c3aed031bc86f3197a4321cb806..a10ce662105cff8fad949c6b83f7035ce79bed18 100644\n--- a/server/src/api/mod.rs\n+++ b/server/src/api/mod.rs\n@@ -24,7 +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, resolve_item, sha256_hex, vote_touches_path,\n+    parse_parent_specs, pick_random_distinct_canonical, 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 5f7d50188f1381267402f2e57e671234ef5db2fd..de0955d0887d32740e1fd18365205c5bdb53c247 100644\n--- a/server/src/api/rpc.rs\n+++ b/server/src/api/rpc.rs\n@@ -29,7 +29,7 @@ use crate::{\n use super::auth::verify_bearer_principal;\n use super::helpers::{\n     compute_connectivity_stats, is_pair_voted, now_ms, paginate_rankings, parse_parent_specs,\n-    pick_random_distinct, resolve_item, vote_touches_path,\n+    pick_random_distinct_canonical, resolve_item, vote_touches_path,\n };\n use super::validate::{normalize_room_and_thread, validate_ingest_document};\n \n@@ -146,21 +146,21 @@ fn authorize_room_read(reduced: &ReducerState, headers: &HeaderMap, room: &str)\n }\n \n fn compute_scope_rank_changes(\n-    parent: &str,\n+    parent: &CanonicalItemUrl,\n     before: &crate::scope_rank::ChildrenRankings,\n     after: &crate::scope_rank::ChildrenRankings,\n     room_wire: &str,\n ) -> Option<ScopeRankChanges> {\n-    fn build_positions(rankings: &crate::scope_rank::ChildrenRankings) -> HashMap<String, Option<RankPosition>> {\n+    fn build_positions(rankings: &crate::scope_rank::ChildrenRankings) -> HashMap<CanonicalItemUrl, Option<RankPosition>> {\n         let mut map = HashMap::new();\n         for comp in &rankings.component_rankings {\n             let total = comp.ranked.len();\n             for (i, item) in comp.ranked.iter().enumerate() {\n-                map.insert(item.item.as_str().to_string(), Some(RankPosition { rank: i + 1, of: total }));\n+                map.insert(item.item.clone(), Some(RankPosition { rank: i + 1, of: total }));\n             }\n         }\n         for item in &rankings.unranked_items {\n-            map.insert(item.as_str().to_string(), None);\n+            map.insert(item.clone(), None);\n         }\n         map\n     }\n@@ -168,7 +168,7 @@ fn compute_scope_rank_changes(\n     let before_pos = build_positions(before);\n     let after_pos = build_positions(after);\n \n-    let all_items: std::collections::BTreeSet<String> = before_pos.keys().cloned()\n+    let all_items: std::collections::BTreeSet<CanonicalItemUrl> = before_pos.keys().cloned()\n         .chain(after_pos.keys().cloned())\n         .collect();\n \n@@ -184,7 +184,7 @@ fn compute_scope_rank_changes(\n         };\n         if changed {\n             changes.push(RankChange {\n-                item: GardenItemUrl::from_storage_str(&item, room_wire),\n+                item: GardenItemUrl::from_stored(&item, room_wire),\n                 before: b,\n                 after: a,\n             });\n@@ -203,11 +203,7 @@ fn compute_scope_rank_changes(\n     });\n \n     Some(ScopeRankChanges {\n-        parent: if parent.is_empty() {\n-            \"/\".to_string()\n-        } else {\n-            GardenItemUrl::from_storage_str(parent, room_wire).into_inner()\n-        },\n+        parent: GardenItemUrl::from_stored(parent, room_wire).into_inner(),\n         changes,\n     })\n }\n@@ -473,8 +469,8 @@ async fn rpc_post(\n         for s in &v.doc.statements {\n             if let dsl::Stmt::Vote { item1, item2, .. } = s {\n                 if let (Ok(a), Ok(b)) = (resolve_item(item1), resolve_item(item2)) {\n-                    if let Some(p) = CanonicalItemUrl::parse(&a).and_then(|c| c.parent()) { parents.insert(p); }\n-                    if let Some(p) = CanonicalItemUrl::parse(&b).and_then(|c| c.parent()) { parents.insert(p); }\n+                    if let Some(p) = a.parent() { parents.insert(p); }\n+                    if let Some(p) = b.parent() { parents.insert(p); }\n                 }\n             }\n         }\n@@ -525,7 +521,7 @@ async fn rpc_post(\n             .filter_map(|p| {\n                 let before = pre_rankings.get(p)?;\n                 let after = crate::scope_rank::build_children_rankings(content, p);\n-                compute_scope_rank_changes(p.as_str(), before, &after, &room_key)\n+                compute_scope_rank_changes(p, before, &after, &room_key)\n             })\n             .collect();\n         if v.is_empty() { None } else { Some(v) }\n@@ -638,8 +634,8 @@ async fn rpc_check(\n         for s in &v.doc.statements {\n             if let dsl::Stmt::Vote { item1, item2, .. } = s {\n                 if let (Ok(a), Ok(b)) = (resolve_item(item1), resolve_item(item2)) {\n-                    if let Some(p) = CanonicalItemUrl::parse(&a).and_then(|c| c.parent()) { parents.insert(p); }\n-                    if let Some(p) = CanonicalItemUrl::parse(&b).and_then(|c| c.parent()) { parents.insert(p); }\n+                    if let Some(p) = a.parent() { parents.insert(p); }\n+                    if let Some(p) = b.parent() { parents.insert(p); }\n                 }\n             }\n         }\n@@ -961,7 +957,7 @@ fn rpc_search(reduced: &ReducerState, q: &str, limit: usize, principal: Option<&\n async fn rpc_get_pair(state: &AppState, room: String, parent_path: String) -> Result<RpcResult, RpcErr> {\n     let scope = scope_from_room_wire(&room);\n     let reduced_arc = state.reduced.clone();\n-    let pool: Vec<String> = {\n+    let pool: Vec<CanonicalItemUrl> = {\n         let reduced = reduced_arc.read().await;\n         let content = content_for_room(&reduced, &room);\n         let tmp = if parent_path.trim().is_empty() {\n@@ -970,12 +966,11 @@ async fn rpc_get_pair(state: &AppState, room: String, parent_path: String) -> Re\n             Some(parent_path.clone())\n         };\n         let specs = parse_parent_specs(tmp.as_ref());\n-        let raw_pool: Vec<CanonicalItemUrl> = if specs.is_empty() {\n+        if specs.is_empty() {\n             content.ranking_group.idx_to_item.clone()\n         } else {\n             crate::scope_rank::resolve_scope(content, &specs)\n-        };\n-        raw_pool.into_iter().map(|it| it.0).collect()\n+        }\n     };\n     if pool.len() < 2 {\n         return Err((\n@@ -983,31 +978,30 @@ async fn rpc_get_pair(state: &AppState, room: String, parent_path: String) -> Re\n             Some(\"add items via ingest\".into()),\n         ));\n     }\n-    let selected: Option<(String, String)> = {\n+    let selected: Option<(CanonicalItemUrl, CanonicalItemUrl)> = {\n         let mut reduced = reduced_arc.write().await;\n         let content = reduced.content.entry(scope.clone()).or_default();\n         let group = &mut content.ranking_group;\n         if group.idx_to_item.is_empty() {\n-            pick_random_distinct(&pool)\n+            pick_random_distinct_canonical(&pool)\n         } else {\n             let mut rng = rand::thread_rng();\n-            let idxs: Vec<usize> = pool.iter()\n-                .filter_map(|it| {\n-                    let key = CanonicalItemUrl(it.clone());\n-                    group.item_to_idx.get(&key).copied()\n-                })\n+            let idxs: Vec<usize> = pool\n+                .iter()\n+                .filter_map(|it| group.item_to_idx.get(it).copied())\n                 .collect();\n             let ranked = ranked_items_subset(group, &idxs, 10000, 1e-8);\n-            let ranked_set: HashSet<String> = ranked.iter().map(|r| r.item.as_str().to_string()).collect();\n-            let unsorted: Vec<String> = pool.iter()\n+            let ranked_set: HashSet<CanonicalItemUrl> = ranked.iter().map(|r| r.item.clone()).collect();\n+            let unsorted: Vec<CanonicalItemUrl> = pool\n+                .iter()\n                 .filter(|it| !ranked_set.contains(*it))\n                 .cloned()\n                 .collect();\n-            let mut pick: Option<(String, String)> = None;\n+            let mut pick: Option<(CanonicalItemUrl, CanonicalItemUrl)> = None;\n             if !unsorted.is_empty() {\n                 if let Some(left) = unsorted.choose(&mut rng).cloned() {\n-                    let mut candidates: Vec<String> = if !ranked.is_empty() {\n-                        ranked.iter().map(|r| r.item.as_str().to_string()).collect()\n+                    let mut candidates: Vec<CanonicalItemUrl> = if !ranked.is_empty() {\n+                        ranked.iter().map(|r| r.item.clone()).collect()\n                     } else {\n                         pool.clone()\n                     };\n@@ -1021,21 +1015,21 @@ async fn rpc_get_pair(state: &AppState, room: String, parent_path: String) -> Re\n                     let a = ranked[i].item.as_str();\n                     let b = ranked[i + 1].item.as_str();\n                     if a != b && !is_pair_voted(group, a, b) {\n-                        pick = Some((a.to_string(), b.to_string()));\n+                        pick = Some((ranked[i].item.clone(), ranked[i + 1].item.clone()));\n                         break;\n                     }\n                 }\n                 if pick.is_none() {\n                     for _ in 0..64 {\n                         let (Some(a), Some(b)) = (pool.choose(&mut rng).cloned(), pool.choose(&mut rng).cloned()) else { break; };\n-                        if a != b && !is_pair_voted(group, &a, &b) {\n+                        if a != b && !is_pair_voted(group, a.as_str(), b.as_str()) {\n                             pick = Some((a, b));\n                             break;\n                         }\n                     }\n                 }\n             }\n-            pick.or_else(|| pick_random_distinct(&pool))\n+            pick.or_else(|| pick_random_distinct_canonical(&pool))\n         }\n     };\n     let Some((left, right)) = selected else {\n@@ -1043,8 +1037,8 @@ async fn rpc_get_pair(state: &AppState, room: String, parent_path: String) -> Re\n     };\n     let reduced = reduced_arc.read().await;\n     let content = content_for_room(&reduced, &room);\n-    let left_key = CanonicalItemUrl(left.clone());\n-    let right_key = CanonicalItemUrl(right.clone());\n+    let left_key = left.clone();\n+    let right_key = right.clone();\n     let lb = content.item_bodies.get(&left_key).cloned();\n     let rb = content.item_bodies.get(&right_key).cloned();\n     let th: Vec<String> = content\n@@ -1058,8 +1052,8 @@ 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: GardenItemUrl::from_storage_str(&left, &room),\n-        right: GardenItemUrl::from_storage_str(&right, &room),\n+        left: GardenItemUrl::from_stored(&left, &room),\n+        right: GardenItemUrl::from_stored(&right, &room),\n         left_body: lb,\n         right_body: rb,\n         threads: th,\n@@ -1554,7 +1548,7 @@ 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: GardenItemUrl::from_storage_str(r.item.as_str(), &room),\n+                            item: GardenItemUrl::from_stored(&r.item, &room),\n                             score: r.score,\n                             percent: pct,\n                         });\n@@ -1562,11 +1556,11 @@ pub async fn handle_rpc_batch(\n                 }\n \n                 let ranked_total = ranked.len();\n-                let mut unranked: Vec<String> = content\n+                let mut unranked: Vec<CanonicalItemUrl> = content\n                     .items\n                     .iter()\n                     .filter(|it| !group.item_to_idx.contains_key(*it))\n-                    .map(|it| it.as_str().to_string())\n+                    .cloned()\n                     .collect();\n                 unranked.sort();\n                 let unranked_total = unranked.len();\n@@ -1574,7 +1568,7 @@ pub async fn handle_rpc_batch(\n                 let page: Vec<RankRow> = ranked\n                     .into_iter()\n                     .chain(unranked.into_iter().map(|it| RankRow {\n-                        item: GardenItemUrl::from_storage_str(&it, &room),\n+                        item: GardenItemUrl::from_stored(&it, &room),\n                         score: 0.0,\n                         percent: want_percent.then_some(0.0),\n                     }))\n@@ -1722,7 +1716,7 @@ pub async fn handle_rpc_batch(\n                     .filter(|p| !parents.contains(p.as_str()))\n                     .map(|p| GardenItemUrl::from_stored(p, &room))\n                     .collect();\n-                paths.sort_by(|a, b| a.as_str().cmp(b.as_str()));\n+                paths.sort();\n                 line_ok(RpcResult::Leaves(LeavesResponse { paths }))\n                 }\n             },\ndiff --git a/server/src/api/validate.rs b/server/src/api/validate.rs\nindex a51c783ee9785569b5a44c0b1572471fe00d174b..3c7aa80fd485cf247231fe5c5c7e6fea62f22534 100644\n--- a/server/src/api/validate.rs\n+++ b/server/src/api/validate.rs\n@@ -52,7 +52,7 @@ pub fn validate_ingest_document(\n     };\n \n     let ts = super::helpers::now_ms();\n-    let mut defined_in_doc: HashSet<String> = HashSet::new();\n+    let mut defined_in_doc: HashSet<CanonicalItemUrl> = HashSet::new();\n \n     for s in &doc.statements {\n         match s {\n@@ -66,14 +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: {}\", GardenItemUrl::from_storage_str(&item, room_wire)),\n+                        format!(\"item missing body: {}\", GardenItemUrl::from_stored(&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: {}\", GardenItemUrl::from_storage_str(&item, room_wire)),\n+                        format!(\"item body is empty: {}\", GardenItemUrl::from_stored(&item, room_wire)),\n                         Some(\"write at least one sentence inside `{ ... }`\".to_string()),\n                     ));\n                 }\n@@ -102,11 +102,8 @@ pub fn validate_ingest_document(\n                 };\n                 let missing: Vec<String> = [&a, &b]\n                     .into_iter()\n-                    .filter(|it| {\n-                        let key = CanonicalItemUrl((*it).clone());\n-                        !defined_in_doc.contains(*it) && !item_exists(&key)\n-                    })\n-                    .map(|it| GardenItemUrl::from_storage_str(it, room_wire).into_inner())\n+                    .filter(|it| !defined_in_doc.contains(*it) && !item_exists(it))\n+                    .map(|it| GardenItemUrl::from_stored(it, room_wire).into_inner())\n                     .collect();\n                 if !missing.is_empty() {\n                     return Err((\n@@ -120,11 +117,8 @@ pub fn validate_ingest_document(\n                 }\n                 let missing_body: Vec<String> = [&a, &b]\n                     .into_iter()\n-                    .filter(|it| {\n-                        let key = CanonicalItemUrl((*it).clone());\n-                        !defined_in_doc.contains(*it) && !body_exists(&key)\n-                    })\n-                    .map(|it| GardenItemUrl::from_storage_str(it, room_wire).into_inner())\n+                    .filter(|it| !defined_in_doc.contains(*it) && !body_exists(it))\n+                    .map(|it| GardenItemUrl::from_stored(it, room_wire).into_inner())\n                     .collect();\n                 if !missing_body.is_empty() {\n                     return Err((\ndiff --git a/server/src/html/editor.rs b/server/src/html/editor.rs\nindex ecdd226b1b17d5f11d1b79f99add5759ef918281..26d648d7c8d6e5d53ce5ed7a051b44856fca2fcf 100644\n--- a/server/src/html/editor.rs\n+++ b/server/src/html/editor.rs\n@@ -130,8 +130,8 @@ pub async fn editor_check(\n                 for s in &v.doc.statements {\n                     if let crate::dsl::Stmt::Vote { item1, item2, .. } = s {\n                         if let (Ok(a), Ok(b)) = (resolve_item(item1), resolve_item(item2)) {\n-                            if let Some(p) = crate::path_types::CanonicalItemUrl::parse(&a).and_then(|c| c.parent()) { parents.insert(p); }\n-                            if let Some(p) = crate::path_types::CanonicalItemUrl::parse(&b).and_then(|c| c.parent()) { parents.insert(p); }\n+                            if let Some(p) = a.parent() { parents.insert(p); }\n+                            if let Some(p) = b.parent() { parents.insert(p); }\n                         }\n                     }\n                 }\ndiff --git a/types/src/paths.rs b/types/src/paths.rs\nindex 2950a7502255927583fbacdfd2adb700f0b0c221..839684dfa0ecdd6c2572e2d8132ecee4d5c41bf8 100644\n--- a/types/src/paths.rs\n+++ b/types/src/paths.rs\n@@ -3,6 +3,7 @@\n \n use std::borrow::Borrow;\n use std::fmt;\n+use std::ops::Deref;\n \n use serde::{Deserialize, Serialize};\n \n@@ -319,6 +320,14 @@ impl fmt::Display for GardenItemUrl {\n     }\n }\n \n+impl Deref for GardenItemUrl {\n+    type Target = str;\n+\n+    fn deref(&self) -> &Self::Target {\n+        &self.0\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@@ -386,6 +395,14 @@ impl fmt::Display for ForumThreadUrl {\n     }\n }\n \n+impl Deref for ForumThreadUrl {\n+    type Target = str;\n+\n+    fn deref(&self) -> &Self::Target {\n+        &self.0\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@@ -412,6 +429,14 @@ impl fmt::Display for TildeOntologyPath {\n     }\n }\n \n+impl Deref for TildeOntologyPath {\n+    type Target = str;\n+\n+    fn deref(&self) -> &Self::Target {\n+        &self.0\n+    }\n+}\n+\n #[cfg(test)]\n mod tests {\n     use super::*;\n@@ -452,6 +477,13 @@ mod tests {\n         assert_eq!(c.tilde_segments(), Vec::<&str>::new());\n     }\n \n+    #[test]\n+    fn garden_item_url_deref_to_str() {\n+        let g = GardenItemUrl::from_storage_str(\"https://slug.social/~/x\", \"public\");\n+        let s: &str = &*g;\n+        assert_eq!(s, \"https://slug.social/~/x\");\n+    }\n+\n     #[test]\n     fn garden_public_passthrough_https() {\n         let u = \"https://slug.social/~/a/b\";\n\n\nSide B — contributor: tommy-mor\nSide B — commit message:\n[bda5f8aa] Remove legacy evidence projection; Evidence envelopes only.\n\nEpoch and commit pages no longer invent history from bare GitDiscovery rows. Production ledger will be wiped to re-emit under the current schema.\n\nCo-authored-by: Cursor <cursoragent@cursor.com>\n\nSide B — unified diff (full patch):\ndiff --git a/constitution.py b/constitution.py\nindex 4dd5b9dfbba231d46289c490f91b1dd5b1018bcf..26ba130e885e0e69fb7874ca5c3f07f42100a150 100644\n--- a/constitution.py\n+++ b/constitution.py\n@@ -210,10 +210,10 @@ class Emission:\n     distributions: dict   # author -> amount str\n     ranking: dict         # author -> score str\n     models_used: list\n-    discovery_snapshot_id: str = \"\"  # empty only for pre-discovery ledger history\n-    evidence_schema_version: int = 1\n-    ranking_run_id: str = \"\"\n-    ranking_event_id: str = \"\"\n+    discovery_snapshot_id: str\n+    evidence_schema_version: int\n+    ranking_run_id: str\n+    ranking_event_id: str\n \n \n @event\n@@ -502,26 +502,6 @@ def _epochs_in_ledger() -> list[int]:\n     return sorted(epochs)\n \n \n-def _legacy_commit_row(commit_id: str) -> tuple[GitDiscovery | None, dict | None]:\n-    for discovery in store.read():\n-        if not isinstance(discovery, GitDiscovery):\n-            continue\n-        for commit in discovery.commits:\n-            if commit_id_for_oid(commit[\"oid\"]) == commit_id:\n-                return discovery, commit\n-    return None, None\n-\n-\n-def _legacy_observation(commit_id: str) -> tuple[GitDiscovery | None, dict | None]:\n-    for discovery in store.read():\n-        if not isinstance(discovery, GitDiscovery):\n-            continue\n-        for obs in discovery.observations:\n-            if commit_id_for_oid(obs[\"oid\"]) == commit_id:\n-                return discovery, obs\n-    return None, None\n-\n-\n def build_pairwise_prompt(side_a: dict, side_b: dict) -> str:\n     return f\"\"\"You are ranking contributions to an open source project.\n Compare these two sides (each may be one or more commits). Decide which side contributed more.\n@@ -2040,7 +2020,7 @@ def _strip_heavy_fields(obj: dict) -> dict:\n \n @app.get(\"/api/ledger\")\n async def get_ledger(offset: int = 0, limit: int = 100, full: int = 0):\n-    \"\"\"List of ledger dicts (backward-compatible). Heavy blobs stripped unless full=1.\"\"\"\n+    \"\"\"List of ledger dicts. Heavy blobs stripped unless full=1.\"\"\"\n     limit = max(1, min(limit, 500))\n     rows = []\n     for e in store.read()[offset:offset + limit]:\n@@ -2274,23 +2254,25 @@ async def epochs_index():\n     epochs = _epochs_in_ledger()\n     rows = []\n     for epoch in epochs:\n-        discovery = _discovery_for_epoch(epoch)\n         emission = _emission_for_epoch(epoch)\n-        evidence_n = sum(\n-            1 for e in evidence_by_kind() if e.epoch == epoch\n+        evidence_n = sum(1 for e in evidence_by_kind() if e.epoch == epoch)\n+        disc = next(\n+            (\n+                e for e in evidence_by_kind(\"git.discovery_completed\")\n+                if e.epoch == epoch\n+            ),\n+            None,\n         )\n         detail = []\n-        if discovery:\n+        if disc:\n             detail.append(\n-                f\"{len(discovery.commits)} eligible / \"\n-                f\"{len(discovery.observations)} observed\"\n+                f\"{disc.payload.get('eligible_count', 0)} eligible / \"\n+                f\"{disc.payload.get('observation_count', 0)} observed\"\n             )\n         if emission:\n             detail.append(f\"emitted {emission.total_emitted}\")\n         if evidence_n:\n             detail.append(f\"{evidence_n} evidence events\")\n-        elif discovery or emission:\n-            detail.append(\"legacy (no Evidence envelopes)\")\n         rows.append([\"li\",\n             _a(_evidence_path(\"epoch\", str(epoch)), f\"epoch {epoch}\"),\n             \" — \",\n@@ -2307,37 +2289,37 @@ async def epochs_index():\n \n @app.get(\"/epochs/{epoch}\")\n async def epoch_detail(epoch: int):\n-    discovery = _discovery_for_epoch(epoch)\n     emission = _emission_for_epoch(epoch)\n     evidence_rows = [e for e in evidence_by_kind() if e.epoch == epoch]\n+    if not evidence_rows and emission is None:\n+        return _evidence_page(f\"epoch {epoch}\", [\n+            _evidence_nav(),\n+            [\"h1\", f\"epoch {epoch}\"],\n+            [\"p.note\", \"No evidence for this epoch.\"],\n+        ])\n+\n     commit_evs = [e for e in evidence_rows if e.kind == \"git.commit\"]\n     comparison_evs = [e for e in evidence_rows if e.kind == \"comparison.input\"]\n     judgment_evs = [e for e in evidence_rows if e.kind == \"llm.judgment\"]\n+    discovery_ev = next(\n+        (e for e in evidence_rows if e.kind == \"git.discovery_completed\"), None\n+    )\n     ranking_started = next(\n         (e for e in evidence_rows if e.kind == \"ranking.started\"), None\n     )\n     ranking_completed = next(\n         (e for e in evidence_rows if e.kind == \"ranking.completed\"), None\n     )\n-    legacy = not evidence_rows and (discovery is not None or emission is not None)\n-\n-    commit_links: list[tuple[str, str]] = []\n-    if commit_evs:\n-        for e in commit_evs:\n-            cid = e.payload.get(\"commit_id\") or \"\"\n-            label = (\n-                f\"{e.payload.get('oid', cid)[:24]} \"\n-                f\"({e.payload.get('contributor', '?')})\"\n-            )\n-            commit_links.append((label, _evidence_path(\"commit\", cid)))\n-    elif discovery:\n-        for c in discovery.commits:\n-            cid = commit_id_for_oid(c[\"oid\"])\n-            commit_links.append((\n-                f\"{c['oid'][:24]} ({c.get('contributor', '?')})\",\n-                _evidence_path(\"commit\", cid),\n-            ))\n \n+    commit_links = [\n+        (\n+            f\"{e.payload.get('oid', e.payload.get('commit_id', ''))[:24]} \"\n+            f\"({e.payload.get('contributor', '?')})\",\n+            _evidence_path(\"commit\", e.payload[\"commit_id\"]),\n+        )\n+        for e in commit_evs\n+        if e.payload.get(\"commit_id\")\n+    ]\n     comparison_links = [\n         (\n             e.payload.get(\"summary\") or e.payload.get(\"comparison_id\", e.event_id),\n@@ -2360,16 +2342,13 @@ async def epoch_detail(epoch: int):\n     ]\n \n     excluded = []\n-    if discovery:\n-        for obs in discovery.observations:\n+    if discovery_ev:\n+        for obs in discovery_ev.payload.get(\"observations\") or []:\n             if obs.get(\"eligible\"):\n                 continue\n             oid = obs.get(\"oid\", \"?\")\n             reason = obs.get(\"exclusion_reason\") or \"excluded\"\n-            excluded.append([\"li\",\n-                f\"{oid[:28]} — {reason} — \",\n-                [\"span.note\", \"legacy evidence unavailable\"],\n-            ])\n+            excluded.append([\"li\", f\"{oid[:28]} — {reason}\"])\n \n     ranking_nodes: list = []\n     if ranking_completed:\n@@ -2388,21 +2367,10 @@ async def epoch_detail(epoch: int):\n                 indent=2, sort_keys=True,\n             )],\n         ]\n-    elif emission:\n-        if legacy and len(emission.ranking or {}) <= 1:\n-            ranking_nodes.append([\"p.note\",\n-                \"Single-contributor epoch — no LLM judgments.\"\n-            ])\n-        ranking_nodes.extend([\n-            [\"p\", \"Projected from Emission (no ranking Evidence event).\"],\n-            [\"pre.blob\", json.dumps(emission.ranking, indent=2, sort_keys=True)],\n-        ])\n+    elif ranking_started:\n+        ranking_nodes = [[\"p.note\", f\"Ranking started: {ranking_started.event_id}\"]]\n     else:\n-        ranking_nodes = [[\"p.note\", \"No ranking recorded.\"]]\n-    if ranking_started and not ranking_completed:\n-        ranking_nodes.insert(0, [\"p.note\",\n-            f\"Ranking started: {ranking_started.event_id}\"\n-        ])\n+        ranking_nodes = [[\"p.note\", \"No ranking evidence.\"]]\n \n     if emission:\n         emission_node = _dl_rows([\n@@ -2411,44 +2379,41 @@ async def epoch_detail(epoch: int):\n             (\"pool_after\", emission.pool_after),\n             (\"discovery_snapshot_id\", emission.discovery_snapshot_id),\n             (\"ranking_run_id\", emission.ranking_run_id or None),\n+            (\"ranking_event_id\", emission.ranking_event_id or None),\n             (\"models_used\", \", \".join(emission.models_used or [])),\n             (\"distributions\", json.dumps(emission.distributions, sort_keys=True)),\n         ])\n     else:\n         emission_node = [\"p.note\", \"No emission for this epoch.\"]\n \n-    single_contributor = False\n-    if discovery:\n-        single_contributor = len({c.get(\"contributor\") for c in discovery.commits}) <= 1\n-    elif emission:\n-        single_contributor = len(emission.ranking or {}) <= 1\n+    contributors = {\n+        e.payload.get(\"contributor\")\n+        for e in commit_evs\n+        if e.payload.get(\"contributor\")\n+    }\n+    no_comparisons_note = \"No comparisons.\"\n+    if len(contributors) <= 1:\n+        no_comparisons_note += \" Single-contributor — no LLM judgments.\"\n \n     body = [\n         _evidence_nav(),\n         [\"div.eyebrow\", f\"epoch {epoch}\"],\n         [\"h1\", f\"epoch {epoch}\"],\n     ]\n-    if legacy:\n-        body.append([\"p.note\",\n-            \"Legacy epoch: projected from GitDiscovery/Emission without Evidence \"\n-            \"envelopes. Eligible commits use discovery patches; discarded observation \"\n-            \"metadata is marked legacy evidence unavailable. Single-contributor \"\n-            \"epochs have no LLM judgments.\"\n-        ])\n-    if discovery:\n+    if discovery_ev:\n         body.extend([\n             [\"h2\", \"discovery\"],\n             _dl_rows([\n-                (\"snapshot_id\", discovery.snapshot_id),\n-                (\"config_digest\", discovery.config_digest),\n-                (\"initial_snapshot\", discovery.initial_snapshot),\n-                (\"observations\", len(discovery.observations)),\n-                (\"eligible\", len(discovery.commits)),\n+                (\"snapshot_id\", discovery_ev.payload.get(\"snapshot_id\")),\n+                (\"config_digest\", discovery_ev.payload.get(\"config_digest\")),\n+                (\"observations\", discovery_ev.payload.get(\"observation_count\")),\n+                (\"eligible\", discovery_ev.payload.get(\"eligible_count\")),\n+                (\"event\", _a(\n+                    _evidence_path(\"event\", discovery_ev.event_id),\n+                    discovery_ev.event_id,\n+                )),\n             ]),\n         ])\n-    no_comparisons_note = \"No comparisons.\"\n-    if single_contributor:\n-        no_comparisons_note += \" Single-contributor — no LLM judgments.\"\n     body.extend([\n         [\"h2\", \"commits\"],\n         _link_list(commit_links),\n@@ -2471,92 +2436,42 @@ async def epoch_detail(epoch: int):\n @app.get(\"/commits/{commit_id}\")\n async def commit_detail(commit_id: str):\n     ev = find_evidence_payload(\"git.commit\", \"commit_id\", commit_id)\n-    discovery, legacy_row = (None, None)\n     if not ev:\n-        discovery, legacy_row = _legacy_commit_row(commit_id)\n-    if not ev and not legacy_row:\n-        discovery, obs = _legacy_observation(commit_id)\n-        if obs is not None:\n-            epoch = discovery.epoch if discovery else \"?\"\n-            return _evidence_page(f\"commit {commit_id[:24]}\", [\n-                _evidence_nav(\n-                    _a(_evidence_path(\"epoch\", str(epoch)), f\"epoch {epoch}\")\n-                ),\n-                [\"div.eyebrow\", \"commit\"],\n-                [\"h1\", commit_id],\n-                [\"p.note\", \"legacy evidence unavailable\"],\n-                _dl_rows([\n-                    (\"oid\", obs.get(\"oid\")),\n-                    (\"eligible\", obs.get(\"eligible\")),\n-                    (\"exclusion_reason\", obs.get(\"exclusion_reason\")),\n-                    (\"epoch\", str(epoch)),\n-                ]),\n-            ])\n         return _evidence_page(\"commit not found\", [\n             _evidence_nav(),\n             [\"h1\", \"commit not found\"],\n             [\"p\", commit_id],\n         ])\n-    if ev:\n-        p = ev.payload\n-        epoch = ev.epoch\n-        oid = p.get(\"oid\", \"\")\n-        contributor = p.get(\"contributor\", \"\")\n-        message = _blob_text(p.get(\"message\"))\n-        patch = _blob_text(p.get(\"patch\"))\n-        meta = _dl_rows([\n+    p = ev.payload\n+    epoch = ev.epoch\n+    return _evidence_page(f\"commit {commit_id[:24]}\", [\n+        _evidence_nav(_a(_evidence_path(\"epoch\", str(epoch)), f\"epoch {epoch}\")),\n+        [\"div.eyebrow\", \"commit\"],\n+        [\"h1\", commit_id],\n+        _dl_rows([\n             (\"commit_id\", commit_id),\n-            (\"oid\", oid),\n-            (\"contributor\", contributor),\n+            (\"oid\", p.get(\"oid\", \"\")),\n+            (\"contributor\", p.get(\"contributor\", \"\")),\n             (\"patch_sha256\", p.get(\"patch_sha256\")),\n             (\"patch_identity\", p.get(\"patch_identity\")),\n             (\"committer_timestamp_ms\", p.get(\"committer_timestamp_ms\")),\n             (\"evidence_event\", _a(_evidence_path(\"event\", ev.event_id), ev.event_id)),\n             (\"epoch\", _a(_evidence_path(\"epoch\", str(epoch)), str(epoch))),\n-        ])\n-        legacy_note = None\n-    else:\n-        assert legacy_row is not None and discovery is not None\n-        epoch = discovery.epoch\n-        oid = legacy_row.get(\"oid\", \"\")\n-        contributor = legacy_row.get(\"contributor\", \"\")\n-        message = legacy_row.get(\"message\") or \"\"\n-        patch = legacy_row.get(\"patch\") or \"\"\n-        meta = _dl_rows([\n-            (\"commit_id\", commit_id),\n-            (\"oid\", oid),\n-            (\"contributor\", contributor),\n-            (\"patch_sha256\", legacy_row.get(\"patch_sha256\")),\n-            (\"patch_identity\", legacy_row.get(\"patch_identity\")),\n-            (\"committer_timestamp_ms\", legacy_row.get(\"committer_timestamp_ms\")),\n-            (\"epoch\", _a(_evidence_path(\"epoch\", str(epoch)), str(epoch))),\n-            (\"source\", \"legacy GitDiscovery projection\"),\n-        ])\n-        legacy_note = [\"p.note\", \"Projected from GitDiscovery — Evidence envelope absent.\"]\n-    return _evidence_page(f\"commit {commit_id[:24]}\", [\n-        _evidence_nav(_a(_evidence_path(\"epoch\", str(epoch)), f\"epoch {epoch}\")),\n-        [\"div.eyebrow\", \"commit\"],\n-        [\"h1\", commit_id],\n-        *([legacy_note] if legacy_note else []),\n-        meta,\n+        ]),\n         [\"p\", _a(f\"/commits/{commit_id}/patch\", \"download patch\")],\n         [\"h2\", \"message\"],\n-        _pre_blob(message),\n+        _pre_blob(_blob_text(p.get(\"message\"))),\n         [\"h2\", \"patch\"],\n-        _pre_blob(patch),\n+        _pre_blob(_blob_text(p.get(\"patch\"))),\n     ])\n \n \n @app.get(\"/commits/{commit_id}/patch\")\n async def commit_patch_download(commit_id: str):\n     ev = find_evidence_payload(\"git.commit\", \"commit_id\", commit_id)\n-    if ev:\n-        raw = _decode_blob(ev.payload.get(\"patch\")) or _blob_text(ev.payload.get(\"patch\")).encode()\n-    else:\n-        _, row = _legacy_commit_row(commit_id)\n-        if not row:\n-            return PlainTextResponse(\"not found\", status_code=404)\n-        raw = (row.get(\"patch\") or \"\").encode(\"utf-8\")\n+    if not ev:\n+        return PlainTextResponse(\"not found\", status_code=404)\n+    raw = _decode_blob(ev.payload.get(\"patch\")) or _blob_text(ev.payload.get(\"patch\")).encode()\n     return Response(\n         content=raw,\n         media_type=\"text/plain; charset=utf-8\",\n@@ -3226,7 +3141,9 @@ async def watch():\n                 [\"div.controls\",\n                     [\"button#play\", {\"type\": \"button\", \"disabled\": \"true\"}, \"▶ Play live feed\"],\n                     [\"button#pause\", {\"type\": \"button\"}, \"Ⅱ Pause feed\"],\n-                    [\"span.note\", \"Pause stops local updates; the constitutional process continues.\"],\n+                    [\"span.note\",\n+                     \"Play/pause only affect this browser feed — they do not run or stop emission. \"\n+                     \"The server emits at each epoch boundary; status above is that process.\"],\n                 ],\n             ],\n             [\"section.panel\",\ndiff --git a/tests/integration.clj b/tests/integration.clj\nindex 204b0fedfbad57846205cb140c4ed9406b5f8e0e..11140e95a8cd86768a661a30e6b29a3ddfc95fcc 100644\n--- a/tests/integration.clj\n+++ b/tests/integration.clj\n@@ -247,7 +247,10 @@\n                :decay_rate   \"0.003253356063468\"\n                :distributions {\"alice\" \"381.4282558872\" \"bob\" \"190.7141279436\"}\n                :ranking       {\"alice\" \"0.6666\" \"bob\" \"0.3334\"}\n-               :models_used   [\"mock/chat-v1\" \"mock/chat-v2\"]}]\n+               :models_used   [\"mock/chat-v1\" \"mock/chat-v2\"]\n+               :evidence_schema_version 2\n+               :ranking_run_id \"seed-rank\"\n+               :ranking_event_id \"seed-rank-ev\"}]\n     (spit path (str (json/generate-string entry) \"\\n\"))))\n \n ;; ---------------------------------------------------------------------------\ndiff --git a/tests/test_evidence.py b/tests/test_evidence.py\nindex 76adcd343eec3a65dec58fda93b068356fb1adcd..7cb74fd7fb1bcd0ab17d2cbe2e6ca7e61e164221 100644\n--- a/tests/test_evidence.py\n+++ b/tests/test_evidence.py\n@@ -1,4 +1,4 @@\n-\"\"\"HTML evidence graph: byte fidelity, resume, legacy projection, private ack.\"\"\"\n+\"\"\"HTML evidence graph: byte fidelity, resume, and Evidence-only pages.\"\"\"\n \n from __future__ import annotations\n \n@@ -86,55 +86,10 @@ def test_html_evidence_pages_escape_and_link(evidence_store):\n     assert patch_resp.headers[\"content-disposition\"].startswith(\"attachment\")\n \n \n-def test_legacy_epoch_projects_from_gitdiscovery_without_evidence(evidence_store):\n-    oid = \"sha1:\" + \"b\" * 40\n-    discovery = c.GitDiscovery(\n-        schema_version=1,\n-        epoch=3,\n-        snapshot_id=\"legacy-snap\",\n-        timestamp_ms=1,\n-        config_digest=\"d\",\n-        initial_snapshot=True,\n-        configuration={\"repositories\": [], \"contributors\": {}},\n-        repositories=[],\n-        observations=[{\n-            \"oid\": oid,\n-            \"eligible\": False,\n-            \"exclusion_reason\": \"before_genesis\",\n-            \"first_sources\": [],\n-        }, {\n-            \"oid\": \"sha1:\" + \"c\" * 40,\n-            \"eligible\": True,\n-            \"exclusion_reason\": None,\n-            \"first_sources\": [],\n-        }],\n-        commits=[{\n-            \"oid\": \"sha1:\" + \"c\" * 40,\n-            \"contributor\": \"tommy-mor\",\n-            \"message\": \"eligible\",\n-            \"patch\": \"diff --git a/x b/x\\n\",\n-        }],\n-    )\n-    emission = c.Emission(\n-        epoch=3,\n-        timestamp_ms=2,\n-        pool_before=\"1\",\n-        total_emitted=\"0.1\",\n-        pool_after=\"0.9\",\n-        decay_rate=\"0.1\",\n-        distributions={\"tommy-mor\": \"0.1\"},\n-        ranking={\"tommy-mor\": \"1\"},\n-        models_used=[],\n-        discovery_snapshot_id=\"legacy-snap\",\n-    )\n-    asyncio.run(c.store.append(discovery))\n-    asyncio.run(c.store.append(emission))\n-    html = asyncio.run(c.epoch_detail(3)).body.decode()\n-    assert \"legacy\" in html.lower()\n-    assert \"Single-contributor\" in html or \"no LLM\" in html\n-    excluded_id = c.commit_id_for_oid(oid)\n-    excluded_html = asyncio.run(c.commit_detail(excluded_id)).body.decode()\n-    assert \"legacy evidence unavailable\" in excluded_html.lower()\n+def test_commit_without_evidence_is_not_found(evidence_store):\n+    html = asyncio.run(c.commit_detail(\"c_missing\")).body.decode()\n+    assert \"commit not found\" in html\n+    assert \"legacy\" not in html.lower()\n \n \n def test_ranking_resume_skips_duplicate_provider_calls(evidence_store, monkeypatch):\n@@ -202,6 +157,10 @@ def test_epochs_index_lists_epochs(evidence_store):\n         distributions={},\n         ranking={},\n         models_used=[],\n+        discovery_snapshot_id=\"snap\",\n+        evidence_schema_version=c.EVIDENCE_SCHEMA_VERSION,\n+        ranking_run_id=\"r\",\n+        ranking_event_id=\"e\",\n     )))\n     html = asyncio.run(c.epochs_index()).body.decode()\n     assert \"/epochs/3\" in html\n","role":"user"}],"model":"~x-ai/grok-latest"}