Merge pull request 'feat(halacha-triage UI): wire gating + near-duplicate cluster cards (#84.2)' (#98) from worktree-task84.2-ui-clustering into main

mcp-server/src/legal_mcp/config.py

@@ -162,6 +162,13 @@ HALACHA_DEDUP_COSINE = float(os.environ.get("HALACHA_DEDUP_COSINE", "0.93"))
 # dropping a possibly-distinct principle unreviewed. 0.83 from the same cleanup.
 HALACHA_DEDUP_BAND_COSINE = float(os.environ.get("HALACHA_DEDUP_BAND_COSINE", "0.83"))
 
+# Halacha review-queue clustering (#84.2) — when the review queue is requested
+# with cluster=true, halachot of the SAME precedent whose rule-embeddings are
+# within this cosine are grouped into ONE review card (canonical + variants), so
+# the chair judges near-identical principles once instead of repeatedly. Display
+# only — never merges/deletes. 0.90 = "same principle, reworded".
+HALACHA_CLUSTER_COSINE = float(os.environ.get("HALACHA_CLUSTER_COSINE", "0.90"))
+
 # Halacha NLI entailment validator (#81.3) — after extraction, a claude_session
 # judge checks each halacha's rule_statement is entailed by its supporting_quote.
 # Non-entailed (neutral/contradiction) → quality flag 'nli_unsupported' that

mcp-server/src/legal_mcp/services/db.py

@@ -3794,6 +3794,7 @@ async def list_halachot(
     offset: int = 0,
     exclude_low_quality: bool = False,
     order_by_priority: bool = False,
+    cluster: bool = False,
 ) -> list[dict]:
     """List halachot with optional triage controls (#84).
 
@@ -3804,6 +3805,9 @@ async def list_halachot(
     order_by_priority — replace FIFO with an active-learning order (#84.3):
       negatively-treated first, then most-uncertain (lowest confidence), then
       oldest — so the chair sees the highest-value decisions first.
+    cluster — annotate each row with ``cluster_id`` + ``cluster_size`` (#84.2):
+      same-precedent halachot within HALACHA_CLUSTER_COSINE form one group so
+      the UI can collapse near-identical principles into a single review card.
     """
     pool = await get_pool()
     conditions = []
@@ -3868,9 +3872,47 @@ async def list_halachot(
         if d.get("decision_date") is not None:
             d["decision_date"] = d["decision_date"].isoformat()
         out.append(d)
+    if cluster and out:
+        await _annotate_clusters(pool, out)
     return out
 
 
+async def _annotate_clusters(pool, out: list[dict]) -> None:
+    """Add cluster_id + cluster_size to each row (#84.2), display-only.
+
+    Same-precedent halachot within HALACHA_CLUSTER_COSINE are unioned into one
+    group. Singletons get their own id as cluster_id and size 1. Pairwise is
+    confined to the returned set (cheap; the queue is ~hundreds of rows)."""
+    ids = [d["id"] for d in out]
+    max_dist = 1.0 - config.HALACHA_CLUSTER_COSINE
+    pairs = await pool.fetch(
+        "SELECT a.id AS a, b.id AS b FROM halachot a JOIN halachot b "
+        "ON a.case_law_id = b.case_law_id AND a.id < b.id "
+        "AND a.embedding IS NOT NULL AND b.embedding IS NOT NULL "
+        "AND (a.embedding <=> b.embedding) <= $2 "
+        "WHERE a.id = ANY($1::uuid[]) AND b.id = ANY($1::uuid[])",
+        ids, max_dist,
+    )
+    parent = {str(i): str(i) for i in ids}
+
+    def find(x: str) -> str:
+        while parent[x] != x:
+            parent[x] = parent[parent[x]]
+            x = parent[x]
+        return x
+
+    for p in pairs:
+        ra, rb = find(str(p["a"])), find(str(p["b"]))
+        if ra != rb:
+            parent[ra] = rb
+    from collections import Counter
+    sizes = Counter(find(str(i)) for i in ids)
+    for d in out:
+        root = find(str(d["id"]))
+        d["cluster_id"] = root
+        d["cluster_size"] = sizes[root]
+
+
 async def update_halacha(
     halacha_id: UUID,
     review_status: str | None = None,

web-ui/src/components/precedents/halacha-review-panel.tsx

@@ -1,6 +1,6 @@
 "use client";
 
-import { useEffect, useMemo, useState } from "react";
+import { useEffect, useMemo, useState, type ReactNode } from "react";
 import { Check, X, Edit2, ChevronDown, ChevronLeft, AlertTriangle, Clock, RotateCcw } from "lucide-react";
 import { toast } from "sonner";
 import { Button } from "@/components/ui/button";
@@ -20,6 +20,9 @@ const QUALITY_FLAG_LABELS: Record<string, string> = {
   thin_restatement: "ניסוח דק",
   quote_unverified: "ציטוט לא מאומת",
   nli_unsupported: "כלל לא נגזר מהציטוט",
+  application: "יישום תלוי-עובדות",
+  near_duplicate: "כפילות-קרובה",
+  nevo_preamble_leak: "דליפת רציו נבו",
 };
 
 function formatDate(iso: string | null | undefined) {
@@ -57,13 +60,15 @@ type EditState = { rule_statement: string; reasoning_summary: string };
 function HalachaCard({
   h, focused, onApprove, onReject, onDefer, onSave,
 }: {
-  h: Halacha;
+  h: Halacha & { variants?: Halacha[] };
   focused: boolean;
   onApprove: () => void;
   onReject: () => void;
   onDefer: () => void;
   onSave: (patch: Partial<EditState>) => Promise<void>;
 }) {
+  const variants = h.variants ?? [];
+  const [showVariants, setShowVariants] = useState(false);
   const [editing, setEditing] = useState(false);
   const [draft, setDraft] = useState<EditState>({
     rule_statement: h.rule_statement,
@@ -111,6 +116,12 @@ function HalachaCard({
           <Badge variant="outline" className="text-[0.65rem]">
             {ruleTypeLabel(h.rule_type)}
           </Badge>
+          {variants.length > 0 && (
+            <Badge variant="outline"
+              className="text-[0.65rem] bg-navy-soft/30 text-navy border-navy/30">
+              +{variants.length} וריאנטים
+            </Badge>
+          )}
           <CorroborationBadge halacha={h} />
         </span>
       </div>
@@ -180,6 +191,35 @@ function HalachaCard({
         ))}
       </div>
 
+      {variants.length > 0 && (
+        <div className="rounded-md border border-navy/20 bg-navy-soft/10">
+          <button
+            type="button"
+            onClick={() => setShowVariants((v) => !v)}
+            className="w-full flex items-center gap-2 px-3 py-2 text-[0.72rem] text-navy hover:bg-navy-soft/20 transition-colors"
+            aria-expanded={showVariants}
+          >
+            {showVariants ? <ChevronDown className="w-3.5 h-3.5" /> : <ChevronLeft className="w-3.5 h-3.5" />}
+            <span className="font-medium">
+              {variants.length} ניסוחים כמעט-זהים של אותו עיקרון
+            </span>
+            <span className="me-auto text-ink-muted">החלטה תחול על כולם</span>
+          </button>
+          {showVariants && (
+            <ul className="px-4 pb-3 pt-1 space-y-2">
+              {variants.map((v) => (
+                <li key={v.id} className="text-[0.78rem] text-ink-soft leading-relaxed border-r-2 border-navy/20 pr-3" dir="rtl">
+                  {v.rule_statement}
+                  <span className="text-[0.65rem] text-ink-muted tabular-nums ms-2">
+                    (ביטחון {v.confidence.toFixed(2)})
+                  </span>
+                </li>
+              ))}
+            </ul>
+          )}
+        </div>
+      )}
+
       <div className="flex items-center gap-2 justify-end pt-1 border-t border-rule-soft">
         {editing ? (
           <>
@@ -292,37 +332,64 @@ function HalachaRestoreCard({
 
 // ─── Shared group type ────────────────────────────────────────────────────────
 
+/** #84.2 — a review card: the canonical halacha plus its near-duplicate
+ * variants (empty for singletons). Acting on the card acts on the whole set. */
+type ReviewItem = Halacha & { variants: Halacha[] };
+
 type Group = {
   caseLawId: string;
   caseNumber: string;
   court: string;
   decisionDate: string | null;
   precedentLevel: string;
-  items: Halacha[];
+  items: ReviewItem[];   // canonicals (clusters collapsed)
+  pendingTotal: number;  // total halachot incl. variants (for the count badge)
 };
 
+/** All halacha ids represented by a review item (canonical + its variants). */
+function itemIds(it: ReviewItem): string[] {
+  return [it.id, ...it.variants.map((v) => v.id)];
+}
+
 function buildGroups(items: Halacha[]): Group[] {
-  const map = new Map<string, Group>();
+  const byCase = new Map<string, Halacha[]>();
   for (const h of items) {
-    const k = h.case_law_id;
+    const arr = byCase.get(h.case_law_id) ?? [];
-    let g = map.get(k);
+    arr.push(h);
-    if (!g) {
+    byCase.set(h.case_law_id, arr);
-      g = {
+  }
-        caseLawId: k,
+  const groups: Group[] = [];
-        caseNumber: h.case_number ?? "",
+  for (const [caseLawId, members] of byCase) {
-        court: h.court ?? "",
+    // collapse near-duplicate clusters (#84.2): one card per cluster_id.
-        decisionDate: h.decision_date ?? null,
+    const clusters = new Map<string, Halacha[]>();
-        precedentLevel: h.precedent_level ?? "",
+    for (const h of members) {
-        items: [],
+      const key = h.cluster_id ?? h.id;
-      };
+      const arr = clusters.get(key) ?? [];
-      map.set(k, g);
+      arr.push(h);
+      clusters.set(key, arr);
     }
-    g.items.push(h);
+    const reviewItems: ReviewItem[] = [];
+    for (const mem of clusters.values()) {
+      // canonical = strongest phrasing (highest confidence, verified wins ties)
+      mem.sort((a, b) =>
+        b.confidence - a.confidence
+        || Number(b.quote_verified) - Number(a.quote_verified));
+      reviewItems.push({ ...mem[0], variants: mem.slice(1) });
+    }
+    // active-learning order within the case: most-uncertain first
+    reviewItems.sort((a, b) => a.confidence - b.confidence);
+    const first = members[0];
+    groups.push({
+      caseLawId,
+      caseNumber: first.case_number ?? "",
+      court: first.court ?? "",
+      decisionDate: first.decision_date ?? null,
+      precedentLevel: first.precedent_level ?? "",
+      items: reviewItems,
+      pendingTotal: members.length,
+    });
   }
-  for (const g of map.values()) {
+  return groups.sort((a, b) => b.pendingTotal - a.pendingTotal);
-    g.items.sort((a, b) => a.confidence - b.confidence);
-  }
-  return Array.from(map.values()).sort((a, b) => b.items.length - a.items.length);
 }
 
 // ─── Restore panel (used for "rejected" and "approved" tabs) ──────────────────
@@ -422,7 +489,7 @@ function RestorePanel({
                 </div>
               </div>
               <Badge variant="outline" className="tabular-nums">
-                {g.items.length}
+                {g.pendingTotal}
               </Badge>
             </button>
 
@@ -450,7 +517,12 @@ function RestorePanel({
 // ─── Pending queue panel (main review flow) ───────────────────────────────────
 
 function PendingPanel() {
-  const { data, isPending, error } = useHalachotPending(500);
+  // #84.1 — "clean" = quality-gated + prioritized + clustered review queue;
+  // "needsfix" = the flagged 'needs extraction fix' bucket.
+  const [view, setView] = useState<"clean" | "needsfix">("clean");
+  const { data, isPending, error } = useHalachotPending({
+    limit: 500, needsFix: view === "needsfix",
+  });
   const update = useUpdateHalacha();
   const batch = useBatchReviewHalachot();
   const [expandedIds, setExpandedIds] = useState<Set<string>>(new Set());
@@ -463,8 +535,8 @@ function PendingPanel() {
 
   const totalCount = data?.items.length ?? 0;
 
-  const visibleItems = useMemo<Halacha[]>(() => {
+  const visibleItems = useMemo<ReviewItem[]>(() => {
-    const out: Halacha[] = [];
+    const out: ReviewItem[] = [];
     for (const g of groups) {
       if (expandedIds.has(g.caseLawId)) out.push(...g.items);
     }
@@ -483,7 +555,7 @@ function PendingPanel() {
     el?.scrollIntoView({ block: "nearest", behavior: "smooth" });
   }, [focusedId]);
 
-  const focused = focusedId
+  const focused: ReviewItem | null = focusedId
     ? visibleItems.find((h) => h.id === focusedId) ?? null
     : null;
 
@@ -503,16 +575,26 @@ function PendingPanel() {
   };
 
   const review = async (
-    h: Halacha,
+    it: ReviewItem,
     status: "approved" | "rejected" | "deferred",
     extra?: Partial<EditState>,
   ) => {
+    const ids = itemIds(it);
     try {
-      await update.mutateAsync({
+      // #84.2 — a cluster card applies the decision to all its variants at once
-        id: h.id,
+      // (an edit, which is canonical-specific, stays single).
-        patch: { review_status: status, ...extra },
+      if (ids.length > 1 && !extra) {
-      });
+        await batch.mutateAsync({ ids, status });
-      toast.success(REVIEW_TOAST[status] ?? "עודכן");
+      } else {
+        await update.mutateAsync({
+          id: it.id,
+          patch: { review_status: status, ...extra },
+        });
+      }
+      toast.success(
+        (REVIEW_TOAST[status] ?? "עודכן")
+        + (ids.length > 1 ? ` (${ids.length} וריאנטים)` : ""),
+      );
     } catch (e) {
       toast.error(e instanceof Error ? e.message : "שגיאה");
     }
@@ -521,7 +603,7 @@ function PendingPanel() {
   const reviewGroup = async (g: Group, status: "approved" | "rejected") => {
     try {
       const res = await batch.mutateAsync({
-        ids: g.items.map((h) => h.id), status,
+        ids: g.items.flatMap(itemIds), status,
       });
       toast.success(
         `${status === "approved" ? "אושרו" : "נדחו"} ${res.updated} הלכות`,
@@ -573,37 +655,63 @@ function PendingPanel() {
     // eslint-disable-next-line react-hooks/exhaustive-deps
   }, [focused, visibleItems]);
 
+  const viewToggle = (
+    <div className="flex items-center gap-1 rounded-lg border border-rule p-0.5 bg-rule-soft/30 w-fit">
+      <Button
+        size="sm"
+        variant={view === "clean" ? "default" : "ghost"}
+        className={view === "clean" ? "bg-gold text-navy hover:bg-gold-deep" : ""}
+        onClick={() => setView("clean")}
+      >
+        תור נקי
+      </Button>
+      <Button
+        size="sm"
+        variant={view === "needsfix" ? "default" : "ghost"}
+        className={view === "needsfix" ? "bg-gold text-navy hover:bg-gold-deep" : ""}
+        onClick={() => setView("needsfix")}
+      >
+        דורש תיקון-חילוץ
+      </Button>
+    </div>
+  );
+
+  let body: ReactNode;
   if (error) {
-    return (
+    body = (
       <div className="rounded bg-danger-bg border border-danger/40 px-6 py-5 text-danger text-center">
         {error.message}
       </div>
     );
-  }
+  } else if (isPending) {
-
+    body = (
-  if (isPending) {
-    return (
       <div className="space-y-3">
         {[...Array(3)].map((_, i) => <Skeleton key={i} className="h-24 w-full" />)}
       </div>
     );
-  }
+  } else if (!groups.length) {
-
+    body = (
-  if (!groups.length) {
-    return (
       <div className="text-center text-ink-muted py-16">
-        <p className="text-lg">אין הלכות הממתינות לאישור.</p>
+        <p className="text-lg">
-        <p className="text-sm mt-2">העלה פסיקה חדשה — ההלכות שיחולצו ממנה יופיעו כאן.</p>
+          {view === "needsfix"
+            ? "בקט התיקון ריק — אין הלכות מסומנות-איכות."
+            : "אין הלכות נקיות הממתינות לאישור."}
+        </p>
+        <p className="text-sm mt-2">
+          {view === "needsfix"
+            ? "פריטים שסומנו (ציטוט לא-מאומת, יישום, כפילות-קרובה וכו') יופיעו כאן."
+            : "העלה פסיקה חדשה — ההלכות שיחולצו ממנה יופיעו כאן."}
+        </p>
       </div>
     );
-  }
+  } else {
-
+    body = (
-  return (
     <div className="space-y-4">
       <div className="flex items-center gap-3 text-sm text-ink-muted flex-wrap">
         <span>
-          <span className="text-navy font-semibold">{totalCount}</span> ממתינות
+          <span className="text-navy font-semibold">{totalCount}</span>
-          ב-<span className="text-navy font-semibold">{groups.length}</span> פסיקות
+          {view === "needsfix" ? " מסומנות" : " ממתינות"}
+          {" "}ב-<span className="text-navy font-semibold">{groups.length}</span> פסיקות
         </span>
         <span className="me-auto text-[0.72rem]">
           ניווט: <kbd className="bg-rule-soft px-1.5 rounded">J</kbd>/<kbd className="bg-rule-soft px-1.5 rounded">K</kbd>
@@ -650,7 +758,8 @@ function PendingPanel() {
                   </div>
                 </div>
                 <Badge variant="outline" className="bg-gold-wash text-gold-deep border-gold/40 tabular-nums">
-                  {g.items.length} ממתינות
+                  {g.pendingTotal} ממתינות
+                  {g.pendingTotal !== g.items.length && ` · ${g.items.length} כרטיסים`}
                 </Badge>
               </button>
 
@@ -658,12 +767,12 @@ function PendingPanel() {
                 <div className="p-4 space-y-3 bg-rule-soft/20">
                   <div className="flex items-center gap-2 justify-end pb-1">
                     <span className="me-auto text-[0.72rem] text-ink-muted">
-                      פעולה קבוצתית על {g.items.length} ההלכות:
+                      פעולה קבוצתית על {g.pendingTotal} ההלכות:
                     </span>
                     <Button
                       size="sm" variant="ghost" disabled={batch.isPending}
                       onClick={() => {
-                        if (window.confirm(`לדחות את כל ${g.items.length} ההלכות בפסק זה?`))
+                        if (window.confirm(`לדחות את כל ${g.pendingTotal} ההלכות בפסק זה?`))
                           reviewGroup(g, "rejected");
                       }}
                       className="text-danger hover:text-danger hover:bg-danger-bg"
@@ -673,7 +782,7 @@ function PendingPanel() {
                     <Button
                       size="sm" disabled={batch.isPending}
                       onClick={() => {
-                        if (window.confirm(`לאשר את כל ${g.items.length} ההלכות בפסק זה?`))
+                        if (window.confirm(`לאשר את כל ${g.pendingTotal} ההלכות בפסק זה?`))
                           reviewGroup(g, "approved");
                       }}
                       className="bg-gold text-navy hover:bg-gold-deep"
@@ -708,6 +817,14 @@ function PendingPanel() {
         })}
       </div>
     </div>
+    );
+  }
+
+  return (
+    <div className="space-y-4">
+      {viewToggle}
+      {body}
+    </div>
   );
 }
 
@@ -730,7 +847,7 @@ const TAB_LABELS: Record<Tab, string> = {
 
 export function HalachaReviewPanel() {
   const [tab, setTab] = useState<Tab>("pending");
-  const { data: pendingData } = useHalachotPending(500);
+  const { data: pendingData } = useHalachotPending({ limit: 500 });
   const rejectedCount = useHalachaCount("rejected");
   const approvedCount = useHalachaCount("approved");
 

web-ui/src/lib/api/precedent-library.ts

@@ -92,6 +92,11 @@ export type Halacha = {
    * negatively (distinguished/criticized/overruled). */
   corroboration_count?: number;
   corroboration_negative?: boolean;
+  /* #84.2 near-duplicate clustering (present only when fetched with cluster=true):
+   * same-precedent halachot within the cluster cosine share a cluster_id, so the
+   * UI collapses them into one review card. cluster_size === 1 → singleton. */
+  cluster_id?: string;
+  cluster_size?: number;
 };
 
 export type RelatedCase = {
@@ -566,14 +571,32 @@ export function useRequestHalachotExtraction() {
   });
 }
 
-export function useHalachotPending(limit = 200) {
+/** #84.1/#84.2/#84.3 — the chair review queue.
+ *
+ * Default ("clean") view: quality-gated (flagged items hidden), priority-ordered
+ * (most-uncertain/negatively-treated first), and near-duplicate-clustered into
+ * one card. Pass `needsFix: true` for the 'needs extraction fix' bucket — every
+ * pending item carrying a quality flag (filtered client-side). */
+export function useHalachotPending(
+  opts: { limit?: number; needsFix?: boolean } = {},
+) {
+  const { limit = 200, needsFix = false } = opts;
+  const qs = needsFix
+    ? `review_status=pending_review&exclude_low_quality=false&limit=${limit}`
+    : `review_status=pending_review&exclude_low_quality=true`
+      + `&order_by_priority=true&cluster=true&limit=${limit}`;
   return useQuery({
-    queryKey: libraryKeys.halachotPending(),
+    queryKey: [...libraryKeys.halachotPending(), needsFix ? "needsfix" : "clean"],
-    queryFn: ({ signal }) =>
+    queryFn: async ({ signal }) => {
-      apiRequest<{ items: Halacha[]; count: number }>(
+      const res = await apiRequest<{ items: Halacha[]; count: number }>(
-        `/api/halachot?review_status=pending_review&limit=${limit}`,
+        `/api/halachot?${qs}`,
         { signal },
-      ),
+      );
+      if (!needsFix) return res;
+      // needs-fix bucket = pending items that carry a quality flag
+      const items = res.items.filter((h) => (h.quality_flags?.length ?? 0) > 0);
+      return { items, count: items.length };
+    },
     staleTime: 5_000,
     refetchOnMount: "always",
   });

web/app.py

@@ -6033,11 +6033,12 @@ async def halachot_list(
     offset: int = 0,
     exclude_low_quality: bool = False,
     order_by_priority: bool = False,
+    cluster: bool = False,
 ):
-    """List halachot. ``exclude_low_quality`` hides flagged items (#84.1) and
+    """List halachot. ``exclude_low_quality`` hides flagged items (#84.1),
-    ``order_by_priority`` switches to the active-learning order (#84.3). Both
+    ``order_by_priority`` switches to the active-learning order (#84.3), and
-    default off so existing callers are unaffected; the review-queue view opts
+    ``cluster`` annotates near-duplicate groups for one-card review (#84.2). All
-    in."""
+    default off so existing callers are unaffected; the review queue opts in."""
     cid: UUID | None = None
     if case_law_id:
         try:
@@ -6051,6 +6052,7 @@ async def halachot_list(
         limit=limit, offset=offset,
         exclude_low_quality=exclude_low_quality,
         order_by_priority=order_by_priority,
+        cluster=cluster,
     )
     return {"items": rows, "count": len(rows)}