Add content checklists for block-yod and chair feedback system

Addresses Dafna's observation that licensing decisions lack comprehensive
planning discussion. Systematic corpus analysis of all 24 training decisions
revealed the system learned writing style but not substantive content.

Changes:
- Corpus analysis of all 24 decisions (docs/corpus-analysis.md)
- 5 content checklists by appeal subtype injected into block-yod prompt
- chair_feedback DB table + API endpoints + MCP tools
- Feedback management page in Next.js UI (/feedback)
- Navigation updated with "הערות יו״ר" link

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

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

@@ -358,6 +358,22 @@ CREATE TABLE IF NOT EXISTS case_law_embeddings (
     created_at TIMESTAMPTZ DEFAULT now()
 );
 
+-- ═══════════════════════════════════════════════════════════════════
+-- Chair Feedback (הערות דפנה על טיוטות)
+-- ═══════════════════════════════════════════════════════════════════
+
+CREATE TABLE IF NOT EXISTS chair_feedback (
+    id UUID PRIMARY KEY DEFAULT uuid_generate_v4(),
+    case_id UUID REFERENCES cases(id) ON DELETE SET NULL,
+    block_id TEXT DEFAULT '',                    -- block-yod, block-vav, etc.
+    feedback_text TEXT NOT NULL,                 -- ההערה של דפנה
+    category TEXT DEFAULT 'other',              -- missing_content/wrong_tone/wrong_structure/factual_error/style/other
+    lesson_extracted TEXT DEFAULT '',            -- הלקח שהופק
+    applied_to TEXT[] DEFAULT '{}',             -- לאילו קבצים/כללים הלקח יושם
+    resolved BOOLEAN DEFAULT FALSE,             -- האם הלקח יושם
+    created_at TIMESTAMPTZ DEFAULT now()
+);
+
 -- ═══════════════════════════════════════════════════════════════════
 -- Indexes
 -- ═══════════════════════════════════════════════════════════════════
@@ -986,3 +1002,72 @@ async def search_precedents(
 
     results.sort(key=lambda x: x["score"], reverse=True)
     return results[:limit]
+
+
+# ── Chair feedback ────────────────────────────────────────────────
+
+async def record_chair_feedback(
+    case_id: UUID | None,
+    block_id: str,
+    feedback_text: str,
+    category: str = "other",
+    lesson_extracted: str = "",
+) -> UUID:
+    """Record feedback from the chair (Dafna) on a draft block."""
+    pool = await get_pool()
+    feedback_id = uuid4()
+    async with pool.acquire() as conn:
+        await conn.execute(
+            """INSERT INTO chair_feedback
+               (id, case_id, block_id, feedback_text, category, lesson_extracted)
+               VALUES ($1, $2, $3, $4, $5, $6)""",
+            feedback_id, case_id, block_id, feedback_text, category,
+            lesson_extracted,
+        )
+    return feedback_id
+
+
+async def list_chair_feedback(
+    case_id: UUID | None = None,
+    category: str | None = None,
+    unresolved_only: bool = False,
+) -> list[dict]:
+    """List chair feedback, optionally filtered."""
+    pool = await get_pool()
+    conditions = []
+    params: list = []
+    idx = 1
+
+    if case_id:
+        conditions.append(f"case_id = ${idx}")
+        params.append(case_id)
+        idx += 1
+    if category:
+        conditions.append(f"category = ${idx}")
+        params.append(category)
+        idx += 1
+    if unresolved_only:
+        conditions.append("resolved = FALSE")
+
+    where = f"WHERE {' AND '.join(conditions)}" if conditions else ""
+    async with pool.acquire() as conn:
+        rows = await conn.fetch(
+            f"SELECT * FROM chair_feedback {where} ORDER BY created_at DESC",
+            *params,
+        )
+    return [dict(r) for r in rows]
+
+
+async def resolve_chair_feedback(
+    feedback_id: UUID,
+    applied_to: list[str],
+) -> None:
+    """Mark feedback as resolved and record where it was applied."""
+    pool = await get_pool()
+    async with pool.acquire() as conn:
+        await conn.execute(
+            """UPDATE chair_feedback
+               SET resolved = TRUE, applied_to = $2
+               WHERE id = $1""",
+            feedback_id, applied_to,
+        )