{"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[1531154d] dequeue -> vec\n\nSide A — unified diff (full patch):\ndiff --git a/server/src/projection_apply.rs b/server/src/projection_apply.rs\nindex 9c8990a8af927f35d3344c8d0872a516aba56b86..ad404bacb8bcdd5ae0e682cff97f974fd44528ea 100644\n--- a/server/src/projection_apply.rs\n+++ b/server/src/projection_apply.rs\n@@ -6,8 +6,6 @@\n //! batch as the (non-idempotent) edge merges guarantees exactly-once application\n //! across replay.\n \n-use std::collections::BTreeSet;\n-\n use crate::{\n     event_log::EventLogError,\n     events::{Event, EventRecord},\n@@ -44,7 +42,6 @@ pub fn apply_records(\n \n     let db = projection_store.db();\n     let mut batch = db.batch();\n-    let mut vote_parents: BTreeSet<ItemId> = BTreeSet::new();\n     let mut last_seq = 0u64;\n \n     for record in records {\n@@ -70,7 +67,6 @@ pub fn apply_records(\n                     *ts,\n                 )\n                 .map_err(|e| EventLogError::Apply(e.to_string()))?;\n-                vote_parents.insert(parent);\n             }\n             Event::NodeEnsured { id } => {\n                 let parsed = parse_event_id(id)?;\n@@ -85,11 +81,5 @@ pub fn apply_records(\n         .commit_with(durable::Durability::DisableWal)\n         .map_err(|e| EventLogError::Apply(e.to_string()))?;\n \n-    for parent in vote_parents {\n-        projection_store\n-            .trim_recent_votes(&parent)\n-            .map_err(|e| EventLogError::Apply(e.to_string()))?;\n-    }\n-\n     Ok(())\n }\ndiff --git a/server/src/projection_store.rs b/server/src/projection_store.rs\nindex 8576d671f351004426207894ac35594ddb0f70cf..9a8953d010029d3639dc3987687554bab8b7663e 100644\n--- a/server/src/projection_store.rs\n+++ b/server/src/projection_store.rs\n@@ -18,7 +18,7 @@ use crate::{\n \n const PROJECTION_CURSOR_KEY: &str = \"cursor\";\n const PROJECTION_SCHEMA_KEY: &str = \"schema_version\";\n-const PROJECTION_SCHEMA_VERSION: u64 = 3;\n+const PROJECTION_SCHEMA_VERSION: u64 = 4;\n \n #[derive(Debug, thiserror::Error)]\n pub enum ProjectionStoreError {\n@@ -142,16 +142,6 @@ impl ProjectionStore {\n         Ok(tree)\n     }\n \n-    /// Cap a node's recent-vote window after applying votes (best-effort, blind).\n-    pub(crate) fn trim_recent_votes(&self, parent: &ItemId) -> Result<(), ProjectionStoreError> {\n-        node(parent).recent_votes().truncate_back(\n-            &self.db,\n-            crate::storage_schema::RECENT_VOTES_CAP,\n-            Durability::DisableWal,\n-        )?;\n-        Ok(())\n-    }\n-\n     /// Cache Reddit display content outside the event log (must be evicted per policy).\n     pub fn put_ephemeral_content(\n         &self,\ndiff --git a/server/src/reducer.rs b/server/src/reducer.rs\nindex 0c75c85150bb9e5f578bbadf58b3e43f8a80be4b..759918b8c0eb8f8bf1ed0911d8877adaa55c8ea6 100644\n--- a/server/src/reducer.rs\n+++ b/server/src/reducer.rs\n@@ -1,4 +1,4 @@\n-use std::collections::{HashMap, HashSet, VecDeque};\n+use std::collections::{HashMap, HashSet};\n \n use serde::{Deserialize, Serialize};\n \n@@ -52,7 +52,7 @@ pub struct GroupState {\n     pub idx_to_item: Vec<ItemId>,\n     pub edges: HashMap<(usize, usize), f64>,\n     pub voted_pairs: HashSet<(usize, usize)>,\n-    pub recent_votes: VecDeque<VoteData>,\n+    pub recent_votes: Vec<VoteData>,\n }\n \n impl GroupState {\n@@ -62,7 +62,7 @@ impl GroupState {\n             idx_to_item: Vec::new(),\n             edges: HashMap::new(),\n             voted_pairs: HashSet::new(),\n-            recent_votes: VecDeque::with_capacity(200),\n+            recent_votes: Vec::new(),\n         }\n     }\n \n@@ -111,10 +111,7 @@ impl GroupState {\n         self.add_edge_weight(b_idx, a_idx, w_a);\n         self.add_edge_weight(a_idx, b_idx, w_b);\n \n-        self.recent_votes.push_front(vote);\n-        while self.recent_votes.len() > 200 {\n-            self.recent_votes.pop_back();\n-        }\n+        self.recent_votes.push(vote);\n     }\n }\n \ndiff --git a/server/src/storage_dto.rs b/server/src/storage_dto.rs\nindex 9dfb13c53efe4389277625a6ab3bfc18f566a453..3fd6db5cb909ac4896bd8a3ecace796de5f08781 100644\n--- a/server/src/storage_dto.rs\n+++ b/server/src/storage_dto.rs\n@@ -39,7 +39,7 @@ pub struct StoredEntityDataV1 {\n     pub link_url: Option<String>,\n }\n \n-/// One vote stored in a node's `recent_votes` deque.\n+/// One vote stored in a node's `recent_votes` list.\n #[derive(Debug, Clone, Serialize, Deserialize)]\n pub struct StoredVoteV1 {\n     pub version: u32,\ndiff --git a/server/src/storage_schema.rs b/server/src/storage_schema.rs\nindex bd26e665e084b95b10fdfff091c31e8dc84d07b8..5d2bb1d56927fb61c7c6d2d8602bd6882327f862 100644\n--- a/server/src/storage_schema.rs\n+++ b/server/src/storage_schema.rs\n@@ -2,13 +2,13 @@\n //! durable collections instead of one blob per node.\n //!\n //! A vote updates a handful of keys: a few edge-weight merges, a voted-pair flag,\n-//! a recent-vote deque push, and child-link set entries. The in-memory\n+//! a recent-vote list append, and child-link set entries. The in-memory\n //! [`crate::reducer::GroupState`] is reconstructed from these keys on read for\n //! rank-centrality.\n \n use std::collections::{BTreeSet, HashMap, HashSet};\n \n-use durable::{Batch, Db, Deque, Durable, Leaf, Map, Sum};\n+use durable::{Batch, Db, Durable, Leaf, List, Map, Sum};\n \n use crate::{\n     path_types::ItemId,\n@@ -38,8 +38,8 @@ pub struct NodeSchema {\n     pub edges: Map<EdgeKey, Sum<f64>>,\n     /// Voted pairs `(min, max) -> true`.\n     pub voted_pairs: Map<PairKey, Leaf<bool>>,\n-    /// Recent votes, newest at the front (capped on write).\n-    pub recent_votes: Deque<Leaf<StoredVoteV1>>,\n+    /// Recent votes, append-only oldest-first (cap applied on read).\n+    pub recent_votes: List<Leaf<StoredVoteV1>>,\n     /// When ephemeral Reddit display content was last fetched (ms); absent after eviction.\n     pub fetched_at: Leaf<i64>,\n }\n@@ -55,7 +55,7 @@ pub struct Store {\n     pub view_meta: Map<String, Leaf<u64>>,\n }\n \n-/// Cap on the per-node recent-vote window (matches the in-memory reducer).\n+/// Max recent votes returned when loading a node (query-time cap only).\n pub const RECENT_VOTES_CAP: u64 = 200;\n \n fn id_key(id: &ItemId) -> String {\n@@ -148,11 +148,14 @@ fn build_group_state(\n         }\n     }\n \n-    // Deque is front=newest; in-memory VecDeque is also front=newest.\n-    let mut recent_votes = std::collections::VecDeque::new();\n-    for stored in np.recent_votes().iter(db)? {\n-        recent_votes.push_back(decode_vote(stored).map_err(durable::Error::Deserialize)?);\n-    }\n+    // List is index order (oldest first); keep the newest RECENT_VOTES_CAP entries.\n+    let stored = np.recent_votes().iter(db)?;\n+    let cap = RECENT_VOTES_CAP as usize;\n+    let start = stored.len().saturating_sub(cap);\n+    let recent_votes = stored[start..]\n+        .iter()\n+        .map(|s| decode_vote(s.clone()).map_err(durable::Error::Deserialize))\n+        .collect::<Result<Vec<_>, _>>()?;\n \n     Ok(GroupState {\n         item_to_idx,\n@@ -248,7 +251,7 @@ pub fn vote_writes(\n     };\n     batch.write(pnode.voted_pairs().key(&(lo, hi)).set(&true));\n \n-    // Recent votes (newest at front).\n+    // Recent votes (append-only; cap on read).\n     let stored = encode_vote(&VoteData {\n         ts,\n         a: a_id,\n@@ -260,7 +263,7 @@ pub fn vote_writes(\n         delegate: None,\n         thread_tag: \"default\".to_string(),\n     });\n-    batch.push_front(&pnode.recent_votes(), &stored)?;\n+    batch.push(&pnode.recent_votes(), &stored)?;\n     Ok(())\n }\n \n@@ -314,6 +317,35 @@ mod tests {\n         assert!(load_node_state(&db, &parent).unwrap().is_none());\n     }\n \n+    #[test]\n+    fn load_caps_recent_votes_at_query_time() {\n+        let dir = tempfile::tempdir().unwrap();\n+        let db = Db::open(dir.path()).unwrap();\n+        let parent = ItemId::root();\n+\n+        let mut batch = db.batch();\n+        for i in 0..RECENT_VOTES_CAP + 10 {\n+            vote_writes(&mut batch, &parent, \"alpha\", \"beta\", 1, 0, i as i64).unwrap();\n+        }\n+        batch.commit().unwrap();\n+\n+        assert_eq!(\n+            node(&parent).recent_votes().len(&db).unwrap(),\n+            RECENT_VOTES_CAP + 10\n+        );\n+\n+        let node_state = load_node_state(&db, &parent).unwrap().unwrap();\n+        assert_eq!(node_state.local_ranking.recent_votes.len(), RECENT_VOTES_CAP as usize);\n+        assert_eq!(\n+            node_state.local_ranking.recent_votes.first().map(|v| v.ts),\n+            Some(10)\n+        );\n+        assert_eq!(\n+            node_state.local_ranking.recent_votes.last().map(|v| v.ts),\n+            Some(RECENT_VOTES_CAP as i64 + 9)\n+        );\n+    }\n+\n     #[test]\n     fn missing_node_is_none() {\n         let dir = tempfile::tempdir().unwrap();\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"}