UI changes to halacha-review-panel.tsx:
- instance_type badge (עיקרון מקורי / ציטוט / יישום) in meta row
- "מוזכר ב-N פסיקות" pill when instance_count > 1
- CanonicalSection component: canonical_statement (view + edit), instances accordion
Backend:
- list_halachot SQL: adds canonical_id, instance_type, canonical_statement,
instance_count via LEFT JOIN canonical_halachot
- list_canonical_instances(canonical_id) → compact rows for accordion
- GET /api/canonical-halachot/{canonical_id}/instances endpoint
- PATCH /api/halachot/{id}: canonical_statement propagates to canonical_halachot
- HalachaUpdateRequest: canonical_statement field
- useCanonicalInstances hook + CanonicalInstance type in precedent-library.ts
INV-G10 (chair gate): only the chair can edit canonical_statement (same
flow as rule_statement — PATCH /api/halachot/{id} with reviewer="דפנה").
G2: canonical data flows through canonical_halachot, not a parallel store.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
תור-ההלכות שלף רק 500 ממתינות בעלות-עדיפות מתוך ~1,372, בלי שום דרך
לאתר פס"ד מסוים. הלכה מדורגת מתחת לחלון (למשל 1180-11-25, מקומות 921/1305)
פשוט נעלמה — הספירה בספרייה הציגה "2 ממתינות" אך התור לא הראה אותן.
- list_halachot: פרמטר search (case_number/case_name/rule_statement, ILIKE)
— סינון בצד-השרת כך שפריט מתחת לחלון נשאר נגיש. מרחיב את מסלול-השליפה
היחיד, לא יוצר מסלול מקביל (G2).
- count_halachot: ספירה מלאה לאותו פילטר (ל-"N מתוך TOTAL").
- /api/halachot: search + with_total (ברירת-מחדל off; קוראים קיימים לא מושפעים).
- UI (תור-הלכות): שורת-חיפוש מהוקצבת (debounce 300ms), הערת "חלון התצוגה"
(500 מתוך הסך), ושורת-הקשר-תוצאה עם ניקוי. בחיפוש — כל הקבוצות התואמות
נפתחות; הניווט המקלדתי והשערים (G10) ללא שינוי.
מאומת מול ה-DB: search='1180-11-25' → 2 הממתינות (index 20 נקייה→להכרעתך,
index 23 nli_unsupported→דורש תיקון-חילוץ); count=2.
עיצוב: עבר שער Claude Design (X17, כרטיס 19-halacha-queue-unified) ואושר.
Invariants: מקיים G2 (מסלול-שליפה יחיד), INV-G10 (שער-יו"ר ללא שינוי),
INV-IA (מקור-אמת יחיד לתור). ללא בליעת-שגיאות.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
המספרים בתגי תור-ההלכות היו תקרות-שאילתה ולא ספירה אמיתית:
- "ממתינות 500" = pendingData.items.length עם limit=500
- "נדחו 1000 / אושרו 1000" = useHalachotByStatus(...,1000) — תקרה 1000
ובלי refetchInterval התגים התעדכנו רק בכניסה לדף.
המקור האמיתי כבר קיים: /api/precedent-library/stats מריץ COUNT(*) אמיתי
(pending=1373, approved=2100). מוסיף לו halachot_rejected + halachot_deferred,
מחבר את תגי-ה-HalachaReviewPanel למקור הזה, ומוסיף polling (30s) כדי שהם
יתעדכנו חי. מסיר את useHalachaCount המיותר.
תור-העבודה עצמו עדיין נטען עד 500 פריטים (cap-עבודה לגיטימי); רק תצוגת
הספירות תוקנה להציג את הסך-האמיתי.
Invariants: מקיים G1 (נרמול-במקור — ספירה אמיתית מ-COUNT(*) במקום len(rows)
מתוקרת בקריאה) ו-G2 (מאחד על מקור-הספירה הקיים, ללא endpoint-ספירה מקביל).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
מבטל את ה-toggle "תור נקי / דורש תיקון-חילוץ" שבו "תור נקי" ריק
לגמרי (כל ההלכות-הנקיות נפתרו), והעבודה האמיתית חבויה מאחורי
הכפתור השני שגם מערבב התלבטות-פאנל עם פגמי-חילוץ. אושר ב-Claude
Design (כרטיס 19-halacha-queue-unified).
במקום זה — תור אחד, fetch אחד, פיצול client-side לפי **סוג-הפעולה**:
- "להכרעתך" = הלכות שהפאנל דן בהן (יש panel_round) או נקיות →
אשר/דחה, עם טבלת-ההתלבטות; ממוין פיצול-פאנל-תחילה (FU-3).
- "דורש תיקון-חילוץ" = מסומנות-דגל שלא עברו התלבטות → תיקון-חילוץ.
`useHalachotPending` אוחד לקריאה אחת (exclude_low_quality=false +
order_by_priority + cluster + include_equivalents + include_panel_round);
נוסף `isExtractionFixItem(h)` (= !panel_round && יש דגל). PendingPanel
מפצל ב-useMemo, segmented-control עם מוני שני הדליים. אפס שינוי-backend
(הפרמטרים כבר קיימים מ-#220/#222).
display-only, שער-אישור יחיד (INV-IA/G10). ולידציה: tsc + eslint נקי.
חלק מ-#133.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
מציג את התלבטות 3-השופטים (הצבעה+נימוק לכל לינאז' + ה-verdict)
בתוך כרטיס-האישור הקיים של דפנה ב-/precedents → "ממתין לאישור",
כדי שהכרעתה — תווית-הזהב שהלולאה לומדת ממנה — תהיה מיודעת ב*למה*
הפאנל נחלק. אושר ב-Claude Design (כרטיס 18-halacha-deliberation).
Backend (opt-in, ברירת-מחדל off — קוראים קיימים לא מושפעים):
- db.list_halachot(include_panel_round=True) → _annotate_panel_rounds
מצרף את הסבב האחרון מ-halacha_panel_rounds (DISTINCT ON, latest).
- GET /api/halachot?include_panel_round=true.
Frontend:
- Halacha.panel_round (טיפוס ידני; ה-endpoint מחזיר dict).
- תור-הסקירה (useHalachotPending) מבקש include_panel_round בשני
הדליים (clean=keep, needsFix=nli/entailed).
- רכיב PanelDeliberation: טבלת 3-שופטים (✓נתמך/✗הכלל-חורג + נימוק),
תג-ורדיקט "פיצול 2:1", ושורת "שורש המחלוקת" (קפדני↔תמצית) רק
בפיצול-entailment. מוזרק אחרי רשת הכלל/ציטוט.
שער יחיד — אין עמוד/שער חדש (INV-IA/G10); display-only, לא נוגע
ב-review_status. ולידציה: py_compile + tsc --noEmit + eslint נקיים;
בדיקה פונקציונלית: panel_round מצורף ל-6 שיש להן סבב, 1994 בלי.
חלק מ-#133 (FU-2). דורש deploy + (אופ') npm run api:types אחרי.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The extractor classified rule_type by SOURCE bindingness (higher-court→binding,
committee→persuasive) instead of by rule KIND. The gold-set proved it: 'binding'
appeared on 19/19 external rulings & 0 committees; 'persuasive' on 13/13
committees & 0 external — only 58% agreement with the human role tags. The two
axes (authority vs rule role) were crammed into one enum.
This splits them per INV-DM7:
- authority (binding/persuasive) — DERIVED from case_law.precedent_level
(עליון/מנהלי→binding, ועדת_ערר_מחוזית→persuasive), never stored, never
LLM-guessed. New helper halacha_quality.derive_authority; surfaced read-only
in list_halachot / goldset_list / search results.
- rule_type — now the rule ROLE only: holding/interpretive/procedural/
application/obiter. Both extractor prompts unified to this vocabulary;
_coerce_halacha no longer defaults rule_type from the source; legacy
binding→holding / persuasive→interpretive fold for safety.
UI: authority shown as a separate read-only badge (gold=מחייב / muted=משכנע)
across the review queue, precedent detail, and gold-set; the gold-set role
selector drops binding/persuasive and adds מהותי (holding).
Migration: scripts/halacha_rule_role_backfill.py re-classifies the 276 pre-split
binding/persuasive rows into a genuine role via local claude_session (run after
deploy). Gold-set correct_type/ai_correct_type 'binding'→'holding' via SQL.
Sources (≥3, per research-decision policy): OASIS LegalRuleML v1.0
(appliesAuthority/Strength as metadata orthogonal to rule logic) · SemEval-2023
Task 6 LegalEval (rhetorical roles by function, authority kept separate) ·
Bluebook signals (weight-of-authority is a separate dimension).
Invariants: ESTABLISHES INV-DM7. Upholds G1 (normalize at source — extractor
classifies role, system derives authority) and G2 (single source of truth —
authority derived, not a parallel stored field). Tests: 211 pass + new
derive_authority/coerce coverage. web-ui build + tsc clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Cross-precedent recurrence of a principle is real but is NOT citation
corroboration (X11) — the 5 candidate pairs have ZERO citations between their
precedents. Recording them in halacha_citation_corroboration would fabricate
citation data and inflate corroboration_count. This adds a proper, separate
halacha-level link for parallel authority.
Schema (V28): equivalent_halachot — symmetric (halacha_a < halacha_b, CHECK +
UNIQUE), non-citation, cross-precedent-only. ON DELETE CASCADE.
db.py:
- link_equivalent_halachot (idempotent; rejects same-id and SAME-precedent pairs
— parallel authority is cross-precedent by definition), unlink, and
list_equivalent_for_halacha.
- list_halachot gains include_equivalents → _annotate_equivalents attaches an
`equivalents` list (both directions) per row.
API: include_equivalents on GET /api/halachot; GET/POST/DELETE
/api/halachot/{id}/equivalents for the chair to view/link/unlink manually.
scripts/halacha_batch_reconcile.py: --link records found cross-precedent pairs
as equivalent_halachot (non-destructive, idempotent).
web-ui: Halacha.equivalents type; the clean review queue fetches
include_equivalents; the review card shows a gold "עיקרון מקביל ב-N" badge + an
expandable list (case + rule + similarity) labeled "אסמכתה מקבילה — לא ציטוט".
Populated the 5 reviewed pairs (chair decision: keep all + link as parallel
authority). Verified: 5 rows; the 1023-20 hub annotates 3 of its halachot with
equivalents; tsc --noEmit exits 0.
Invariants: G1 (model recurrence at source in its own table, not by abusing the
citator); G2 (no parallel path — extends list_halachot); citator integrity
preserved (corroboration stays citation-only).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Completes #84 — surfaces the backend gating/prioritization (#84.1/#84.3, PR
#93) in the chair's review UI and adds near-duplicate clustering (#84.2).
Backend
- db.list_halachot gains `cluster` (#84.2): annotates each row with cluster_id +
cluster_size by unioning same-precedent halachot within HALACHA_CLUSTER_COSINE
(0.90, new config). Display-only — never merges/deletes. Pairwise is confined
to the returned set (cheap).
- GET /api/halachot exposes the `cluster` query param (default off).
Frontend (web-ui)
- Halacha type gains optional cluster_id / cluster_size (hand-written module; no
api:types regen needed — halachot aren't typed off the generated schema).
- useHalachotPending(opts): the default "clean" queue now fetches
exclude_low_quality + order_by_priority + cluster; needsFix:true returns the
flagged 'needs extraction fix' bucket (filtered client-side).
- HalachaReviewPanel: a "תור נקי / דורש תיקון-חילוץ" toggle (#84.1); near-dup
clusters collapse into ONE card showing "+N וריאנטים" with an expandable list,
and approve/reject/defer on a clustered card applies to all variants via the
batch endpoint (#84.2 + #84.4). Counts show true halacha totals (pendingTotal).
New flag labels added (application / near_duplicate / nevo_preamble_leak).
Verified:
- backend: list_halachot(cluster=True) on the live queue — algorithm correct
(groups related same-precedent rules at 0.78; none at the production 0.90
because dedup #82 already removed near-dups — the desired state).
- frontend: `tsc --noEmit` exits 0 (type-clean); no new lint errors (the one
lint error is pre-existing in training/learning-panel.tsx from #94). Local
Turbopack build can't run on the worktree node_modules symlink — CI builds in
a clean checkout.
Invariants: G1 (gate/cluster at source in SQL, not post-hoc); G2 (same
list_halachot path); §6 (flagged items routed to a visible bucket, not dropped).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Make the chair's pending-halacha review faster and less exhausting.
Backend:
- New 'deferred' review_status (snooze): stays out of the active library AND
out of the default pending queue, without the finality of 'rejected'.
update_halacha stamps reviewer+reviewed_at on defer; HALACHA_REVIEW_STATUSES
is the single source of valid statuses (PATCH validation now uses it).
- db.update_halachot_batch(ids, status, reviewer) — one atomic UPDATE for a
whole group; invalid status / empty ids are a no-op.
- POST /api/halachot/batch (HalachaBatchReviewRequest) wraps it.
- update_halacha now RETURNs quality_flags too (parity with list_halachot).
Frontend (halacha-review-panel):
- Quality-flag badges (#81: non_decision / truncated_quote / thin_restatement /
quote_unverified) so the chair sees WHY an item was held back.
- Defer action — button + keyboard 'D' — to snooze without rejecting (fixes the
'leave in pending forever' anti-pattern; reject stays the junk verb).
- Per-precedent batch bar: 'אשר הכל' / 'דחה הכל' via useBatchReviewHalachot
(one request, one refetch) with confirm guards.
- Halacha/HalachaPatch types gain quality_flags + 'deferred'.
Verified: mcp-server suite 156 passed; web build green; end-to-end integration
against dev DB (batch approve/reject, defer sets status+timestamp, pending
excludes approved+deferred, deferred queryable, invalid status no-op).
Note: api:types regen deferred until deploy (the batch hook is hand-typed, not
dependent on generated types).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The halacha-review panel was rendering raw slugs (`betterment_levy`,
`rishuy_uvniya`, `compensation_197`) as English badges. Pipe them through
the existing `practiceAreaLabel()` helper so the chair sees
"היטל השבחה", "רישוי ובניה", "פיצויים לפי ס' 197".
All other UI sites (library-list-panel, library-stats-panel,
precedent-edit-sheet) were already using the helper — this was the
sole place left rendering the raw slug.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
After running the dual-mode halacha extractor on a real appeals committee
decision (403-17), the pending-review tab surfaced 351 halachot in a
single flat list — the chair correctly pointed out that this is unusable
without grouping. Three fixes:
1. Group pending halachot by precedent (case_law_id). Each group shows
the citation, court, date, level and item count; default state is
collapsed so the chair picks one ruling at a time. Within a group,
items still sort by confidence ascending so the doubtful ones surface
first. J/K/A/R/E now scope to currently-expanded groups; toggling
open auto-focuses the first item.
2. Translate the badges that were leaking English: rule_type values
(`persuasive`, `interpretive`, `binding`, `application`, `procedural`,
`obiter`) now render as Hebrew labels, and `confidence X.XX` becomes
`ביטחון X.XX`. The card header no longer repeats the citation since
it's already in the group header.
3. Strip Unicode bidi marks (U+200E/F/202A-E/2066-9) from displayed
citations. Nevo PDFs and the upload form embed these in the
case_number; they render as zero-width but visually push the text
away from the right edge of the table cell. Also: hide the empty
court line under the case name in the list (was rendering as a
stray em-dash), and use a muted em-dash for empty date/level rather
than blank/dash inconsistency across columns.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a third corpus of legal authority distinct from style_corpus
(Daphna's prior decisions for voice) and case_precedents (chair-attached
quotes per case). The new corpus holds chair-uploaded court rulings and
other appeals committee decisions, with binding rules (הלכות) extracted
automatically and queued for chair approval.
Pipeline (web/app.py + services/precedent_library.py):
file → extract → chunk → Voyage embed → halacha_extractor → store +
publish progress over the existing Redis SSE channel.
Schema V7 (services/db.py): extends case_law with source_kind +
extraction status fields under a CHECK constraint pinning practice_area
to the three appeals committee domains (rishuy_uvniya, betterment_levy,
compensation_197). New precedent_chunks (vector(1024)) and halachot
tables (vector(1024) over rule_statement, IVFFlat indexes, gin on
practice_areas/subject_tags). Halachot start as pending_review; only
approved/published rows are visible to search_precedent_library.
Agents: legal-writer, legal-researcher, legal-analyst, legal-ceo,
legal-qa get search_precedent_library. legal-writer prompt explains
the three-corpus distinction and CREAC use; legal-qa now verifies that
every cited halacha resolves to an approved row in the corpus.
UI: /precedents page with four tabs — library / semantic search /
pending review (J/K nav, A/R/E shortcuts, badge count) / stats.
Reuses the existing upload-sheet progress + SSE pattern.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
