Add case_precedents: attached legal support for the compose phase

New self-contained table + MCP tools + FastAPI endpoints for letting
the chair attach external case-law quotes (quote + citation מראה מקום,
optional chair note, optional archived PDF) to either a specific
threshold_claim / issue or the case as a whole.

Data model
  - case_precedents (SCHEMA_V5_SQL) — case_id, section_id NULL/
    "threshold_N"/"issue_N", quote, citation (free-text), chair_note,
    pdf_document_id FK to documents, denormalized practice_area for
    cross-case library filtering.
  - Deliberately NOT linked to the existing case_law table — that one
    has UNIQUE(case_number) which would force parsing the free-text
    citation into a structured key. A backfill pass into case_law is
    a later follow-up once the UI stabilizes.
  - db.py gains 4 helpers: create_case_precedent, list_case_precedents,
    delete_case_precedent, search_precedent_library. The last uses
    DISTINCT ON (citation) for the cross-case typeahead so each
    precedent appears once even if reused across many cases.

MCP tools (legal_mcp/tools/precedents.py)
  - precedent_attach, precedent_list, precedent_remove,
    precedent_search_library — registered in server.py.

FastAPI (web/app.py)
  - POST /api/cases/{n}/precedents — create, with PrecedentCreateRequest
  - POST /api/cases/{n}/precedents/upload-pdf — one-shot PDF upload to
    a dedicated documents/precedents/ subdirectory, creates a
    documents row with doc_type="precedent_archive" and no text
    extraction (archive only)
  - GET /api/cases/{n}/precedents — list
  - DELETE /api/precedents/{id} — uses path param since precedent_id
    is a UUID (slash-safe, unlike case numbers)
  - GET /api/precedents/search?q=...&practice_area=... — library
    typeahead

Block-writer integration into _build_precedents_context is a deferred
follow-up — Phase 1 surfaces the feature in the compose UI only.

Plan: ~/.claude/plans/woolly-cooking-graham.md

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

mcp-server/src/legal_mcp/tools/precedents.py

@@ -0,0 +1,95 @@
+"""MCP tools for attached legal precedents (user-supplied case-law quotes).
+
+These complement the existing `case_law` table (which is populated from
+structured sources and is what the block-writer RAG searches) by storing
+free-text citations the chair attaches during the compose phase.
+"""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from uuid import UUID
+
+from legal_mcp.services import db
+
+
+async def precedent_attach(
+    case_number: str,
+    quote: str,
+    citation: str,
+    section_id: str = "",
+    chair_note: str = "",
+    pdf_document_id: str = "",
+) -> str:
+    """צירוף פסיקה תומכת לתיק ערר.
+
+    Args:
+        case_number: מספר תיק הערר
+        quote: הציטוט המדויק שיוכנס להחלטה
+        citation: מראה המקום (ערר 1126-08-25 ... נ' ... (נבו 9.3.2026))
+        section_id: מזהה הטענה/סוגיה (threshold_1, issue_3); ריק = כללי לתיק
+        chair_note: הערה אופציונלית — למה הציטוט תומך בעמדה
+        pdf_document_id: מזהה קובץ PDF מצורף (אופציונלי)
+    """
+    case = await db.get_case_by_number(case_number)
+    if not case:
+        return json.dumps({"error": f"תיק {case_number} לא נמצא."}, ensure_ascii=False)
+
+    pdf_uuid: UUID | None = None
+    if pdf_document_id:
+        try:
+            pdf_uuid = UUID(pdf_document_id)
+        except ValueError:
+            return json.dumps({"error": "pdf_document_id לא תקין"}, ensure_ascii=False)
+
+    row = await db.create_case_precedent(
+        case_id=UUID(case["id"]),
+        quote=quote,
+        citation=citation,
+        section_id=section_id or None,
+        chair_note=chair_note,
+        pdf_document_id=pdf_uuid,
+        practice_area=case.get("practice_area"),
+    )
+    return json.dumps(row, ensure_ascii=False, indent=2)
+
+
+async def precedent_list(case_number: str) -> str:
+    """רשימת כל הפסיקות שצורפו לתיק, ממוינות לפי סעיף ואז לפי זמן יצירה."""
+    case = await db.get_case_by_number(case_number)
+    if not case:
+        return json.dumps({"error": f"תיק {case_number} לא נמצא."}, ensure_ascii=False)
+
+    rows = await db.list_case_precedents(UUID(case["id"]))
+    return json.dumps(rows, ensure_ascii=False, indent=2)
+
+
+async def precedent_remove(precedent_id: str) -> str:
+    """הסרת פסיקה מצורפת. קובץ ה-PDF (אם צורף) נשאר ב-documents לצורך audit."""
+    try:
+        pid = UUID(precedent_id)
+    except ValueError:
+        return json.dumps({"error": "precedent_id לא תקין"}, ensure_ascii=False)
+
+    ok = await db.delete_case_precedent(pid)
+    return json.dumps(
+        {"deleted": ok, "precedent_id": precedent_id}, ensure_ascii=False,
+    )
+
+
+async def precedent_search_library(
+    query: str, practice_area: str = "", limit: int = 10,
+) -> str:
+    """חיפוש בספרייה הרוחבית — כל הפסיקות שצורפו אי-פעם בכל התיקים.
+
+    Args:
+        query: מחרוזת חיפוש (מתחרה מול citation ומול quote)
+        practice_area: אופציונלי — סינון לתחום משפטי מסוים
+        limit: מספר תוצאות מקסימלי
+    """
+    if not query or len(query.strip()) < 2:
+        return json.dumps([], ensure_ascii=False)
+
+    rows = await db.search_precedent_library(query.strip(), practice_area, limit)
+    return json.dumps(rows, ensure_ascii=False, indent=2)