docs: add changelog for hooks/jobs/sync improvements (2026-05-17)

Replace deprecated datetime.utcnow() with datetime.now(timezone.utc)
to avoid Python 3.12+ DeprecationWarning.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

docs/changelog-2026-05-hooks-jobs.md

@@ -0,0 +1,21 @@
+# שינויים — legal-ai backend (2026-05-17)
+
+## הוספת webhook emitter לסטטוס תיק
+
+### `web/paperclip_api.py`
+- נוספה `emit_case_status_webhook()` — fire-and-forget helper שמדווח ל-Paperclip plugin על שינוי סטטוס
+- שימוש ב-`datetime.now(timezone.utc)` במקום `datetime.utcnow()` המיושן (תואם Python 3.12+)
+
+### `web/app.py`
+- `PUT /api/cases/{case_number}` — שולח webhook ב-BackgroundTask כשהסטטוס משתנה
+  - שומר `old_status` לפני העדכון → משווה עם `new_status` → מפעיל webhook רק אם שונה
+- `GET /api/cases/stale?days=3` — מחזיר תיקים שלא עודכנו N+ ימים (לשימוש `stale-case-reminder` job)
+- `GET /api/chair-feedback/weekly-summary?days=7` — מסכם פידבק יו"ר לשבוע אחרון (לשימוש `weekly-feedback-analysis` job)
+
+## שינויים ב-sync script
+
+### `scripts/sync_agents_across_companies.py`
+- `--check-instructions`: מדפיס טבלה עם סטטוס הוראות לכל 14 הסוכנים (✅ מעודכן / DRIFT / ⚠ NOT SET)
+- pre-flight validation לפני `--apply`: אם קובץ הוראות חסר → מבטל בעדינות
+- מעקב `claude_md_mtime` + `claude_md_last_synced` ב-metadata של הסוכן
+- alias: `check-agents` ב-`.bashrc`

mcp-server/src/legal_mcp/server.py

@@ -216,6 +216,22 @@ async def precedent_library_delete(case_law_id: str) -> str:
     return await plib.precedent_library_delete(case_law_id)
 
 
+@mcp.tool()
+async def precedent_link_cases(
+    case_law_id_a: str,
+    case_law_id_b: str,
+    relation_type: str = "same_case_chain",
+) -> str:
+    """קישור שתי פסיקות כקשורות (דו-כיווני, idempotent). relation_type: same_case_chain | overruled_by | distinguished."""
+    return await plib.precedent_link_cases(case_law_id_a, case_law_id_b, relation_type)
+
+
+@mcp.tool()
+async def precedent_unlink_cases(case_law_id_a: str, case_law_id_b: str) -> str:
+    """הסרת קישור בין שתי פסיקות (דו-כיווני)."""
+    return await plib.precedent_unlink_cases(case_law_id_a, case_law_id_b)
+
+
 @mcp.tool()
 async def precedent_extract_halachot(case_law_id: str) -> str:
     """הרצה מחדש של חילוץ הלכות לפסיקה קיימת. ההלכות הקיימות נמחקות, החדשות חוזרות לסטטוס pending_review."""

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

@@ -360,13 +360,9 @@ async def write_block(
         post_hearing_context=post_hearing_context,
     )
 
-    # Restructure: sources first, then instructions
+    # source_context is already embedded inside formatted_prompt via {source_context} in the
-    prompt = (
+    # template. Do NOT prepend it again — doing so doubles the prompt size (was 465K chars).
-        f"## חומרי מקור (מסמכים מלאים — צטט מהם מילה במילה כשאפשר):\n\n"
+    prompt = formatted_prompt
-        f"{source_context}\n\n"
-        f"---\n\n"
-        f"{formatted_prompt}"
-    )
 
     if instructions:
         prompt += f"\n\n## הנחיות נוספות:\n{instructions}"
@@ -377,6 +373,19 @@ async def write_block(
         if not dir_doc.get("approved"):
             raise ValueError("לא ניתן לכתוב בלוק דיון ללא כיוון מאושר. הפעל brainstorm → approve_direction קודם.")
 
+    # Guard against context overflow before calling claude -p.
+    # Sonnet: 200K context → ~800K chars max; Opus: 200K context → same.
+    # In practice the CLI has crashed on prompts above ~400K chars, so use
+    # that as a conservative ceiling (well below the token limit).
+    _MAX_PROMPT_CHARS = 400_000
+    if len(prompt) > _MAX_PROMPT_CHARS:
+        raise RuntimeError(
+            f"Prompt too large for {block_id}: {len(prompt):,} chars "
+            f"(limit {_MAX_PROMPT_CHARS:,}). "
+            f"source_context: {len(source_context):,} chars. "
+            f"Reduce documents or call extract_appraiser_facts first."
+        )
+
     # Call Claude via Claude Code session (no API)
     model_key = block_cfg["model"]
     timeout = claude_session.LONG_TIMEOUT if model_key == "opus" else claude_session.DEFAULT_TIMEOUT
@@ -414,16 +423,35 @@ def _build_case_context(case: dict, decision: dict | None) -> str:
 - תוצאה: {outcome_heb}"""
 
 
+# Which doc_types are relevant per block.
+# None  → skip source docs entirely (block uses other context, e.g. claims_context)
+# []    → include all doc types (default for unspecified blocks)
+# [..] → include only the listed doc_type values
+_BLOCK_DOC_TYPES: dict[str, list[str] | None] = {
+    "block-he":    None,                      # only case_context needed; no full docs
+    "block-vav":   ["appeal", "protocol"],    # כתב ערר + פרוטוקול ועדה
+    "block-zayin": None,                      # claims_context is sufficient
+    "block-chet":  ["protocol"],              # פרוטוקול + השלמות טיעון
+    "block-tet":   ["appraisal"],             # שומות בלבד
+    # block-yod, block-yod-alef, block-he etc. default → all docs
+}
+
+
 async def _build_source_context(case_id: UUID, block_id: str) -> str:
-    """Get full document texts for the block.
+    """Get document texts for the block, filtered by relevance.
 
     Per Anthropic best practices: send full source documents, not truncated excerpts.
-    Place documents at the TOP of the prompt (before instructions) for 30% better recall.
+    Per-block filtering prevents context overflow on large cases (9+ docs).
-    For grounding: instruct Claude to cite word-for-word from these documents.
     """
+    allowed = _BLOCK_DOC_TYPES.get(block_id, [])  # [] sentinel = not in map → all docs
+    if allowed is None:
+        return ""  # this block doesn't need raw source docs
+
     docs = await db.list_documents(case_id)
     context_parts = []
     for doc in docs:
+        if allowed and doc["doc_type"] not in allowed:
+            continue
         text = await db.get_document_text(UUID(doc["id"]))
         if text:
             context_parts.append(f"--- מסמך: {doc['title']} ({doc['doc_type']}) ---\n{text}")

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

@@ -72,6 +72,9 @@ async def query(
     """
     full_prompt = f"{system}\n\n{prompt}" if system else prompt
 
+    if len(full_prompt) > 150_000:
+        logger.warning("Large prompt: %d chars — may hit context limits", len(full_prompt))
+
     cmd = [
         "claude", "-p",
         "--output-format", "json",
@@ -110,7 +113,8 @@ async def query(
 
     if proc.returncode != 0:
         stderr = stderr_b.decode("utf-8", errors="replace").strip()[:500] or "unknown error"
-        raise RuntimeError(f"Claude CLI failed (exit {proc.returncode}): {stderr}")
+        size_info = f"; prompt_len={len(full_prompt):,} chars" if len(full_prompt) > 100_000 else ""
+        raise RuntimeError(f"Claude CLI failed (exit {proc.returncode}): {stderr}{size_info}")
 
     stdout = stdout_b.decode("utf-8", errors="replace").strip()
     if not stdout:

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

@@ -700,6 +700,20 @@ CREATE INDEX IF NOT EXISTS idx_case_law_chair ON case_law(chair_name) WHERE chai
 CREATE INDEX IF NOT EXISTS idx_case_law_district ON case_law(district) WHERE district <> '';
 """
 
+SCHEMA_V11_SQL = """
+CREATE TABLE IF NOT EXISTS case_law_relations (
+    id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    case_law_id UUID NOT NULL REFERENCES case_law(id) ON DELETE CASCADE,
+    related_id   UUID NOT NULL REFERENCES case_law(id) ON DELETE CASCADE,
+    relation_type TEXT NOT NULL DEFAULT 'same_case_chain',
+    created_at TIMESTAMPTZ DEFAULT now(),
+    UNIQUE(case_law_id, related_id),
+    CHECK (case_law_id <> related_id)
+);
+CREATE INDEX IF NOT EXISTS idx_clr_a ON case_law_relations(case_law_id);
+CREATE INDEX IF NOT EXISTS idx_clr_b ON case_law_relations(related_id);
+"""
+
 
 async def _run_schema_migrations(pool: asyncpg.Pool) -> None:
     async with pool.acquire() as conn:
@@ -714,7 +728,8 @@ async def _run_schema_migrations(pool: asyncpg.Pool) -> None:
         await conn.execute(SCHEMA_V8_SQL)
         await conn.execute(SCHEMA_V9_SQL)
         await conn.execute(SCHEMA_V10_SQL)
-    logger.info("Database schema initialized (v1-v10)")
+        await conn.execute(SCHEMA_V11_SQL)
+    logger.info("Database schema initialized (v1-v11)")
 
 
 async def init_schema() -> None:
@@ -1735,6 +1750,59 @@ async def get_case_law(case_law_id: UUID) -> dict | None:
     return _row_to_case_law(row) if row else None
 
 
+async def add_case_law_relation(
+    a_id: UUID, b_id: UUID, relation_type: str = "same_case_chain"
+) -> None:
+    """Link two case_law records bidirectionally. Idempotent (ON CONFLICT DO NOTHING)."""
+    pool = await get_pool()
+    async with pool.acquire() as conn:
+        await conn.executemany(
+            """
+            INSERT INTO case_law_relations(case_law_id, related_id, relation_type)
+            VALUES($1, $2, $3)
+            ON CONFLICT (case_law_id, related_id) DO NOTHING
+            """,
+            [(a_id, b_id, relation_type), (b_id, a_id, relation_type)],
+        )
+
+
+async def remove_case_law_relation(a_id: UUID, b_id: UUID) -> None:
+    """Remove a bidirectional link between two case_law records."""
+    pool = await get_pool()
+    await pool.execute(
+        """
+        DELETE FROM case_law_relations
+        WHERE (case_law_id = $1 AND related_id = $2)
+           OR (case_law_id = $2 AND related_id = $1)
+        """,
+        a_id,
+        b_id,
+    )
+
+
+async def get_case_law_relations(case_law_id: UUID) -> list[dict]:
+    """Return all case_law records linked to case_law_id, ordered by date asc."""
+    pool = await get_pool()
+    rows = await pool.fetch(
+        """
+        SELECT cl.*, r.relation_type
+        FROM case_law_relations r
+        JOIN case_law cl ON cl.id = r.related_id
+        WHERE r.case_law_id = $1
+        ORDER BY cl.date ASC NULLS LAST
+        """,
+        case_law_id,
+    )
+    results = []
+    for row in rows:
+        d = dict(row)
+        relation_type = d.pop("relation_type")
+        normalized = _row_to_case_law(d)
+        normalized["relation_type"] = relation_type
+        results.append(normalized)
+    return results
+
+
 async def get_case_law_by_citation(case_number: str) -> dict | None:
     pool = await get_pool()
     row = await pool.fetchrow(
@@ -1984,9 +2052,19 @@ async def list_external_case_law(
     offset: int = 0,
     source_kind: str = "external_upload",
 ) -> list[dict]:
-    """List chair-uploaded precedents, with simple filters."""
+    """List chair-uploaded precedents, with simple filters.
+
+    source_kind="all_committees" expands to: source_kind='internal_committee'
+    OR (source_kind='external_upload' AND source_type='appeals_committee').
+    """
     pool = await get_pool()
-    conditions = [f"source_kind = '{source_kind}'"]
+    if source_kind == "all_committees":
+        conditions = [
+            "(source_kind = 'internal_committee' OR "
+            "(source_kind = 'external_upload' AND source_type = 'appeals_committee'))"
+        ]
+    else:
+        conditions = [f"source_kind = '{source_kind}'"]
     params: list = []
     idx = 1
     if practice_area:
@@ -2420,19 +2498,17 @@ async def precedent_library_stats() -> dict:
     pool = await get_pool()
     async with pool.acquire() as conn:
         total = await conn.fetchval(
-            "SELECT COUNT(*) FROM case_law WHERE source_kind = 'external_upload'"
+            "SELECT COUNT(*) FROM case_law"
         )
         by_practice = await conn.fetch(
             """SELECT practice_area, COUNT(*) AS n
                FROM case_law
-               WHERE source_kind = 'external_upload'
                GROUP BY practice_area
                ORDER BY n DESC"""
         )
         by_level = await conn.fetch(
             """SELECT precedent_level, COUNT(*) AS n
                FROM case_law
-               WHERE source_kind = 'external_upload'
                GROUP BY precedent_level
                ORDER BY n DESC"""
         )

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

@@ -123,7 +123,7 @@ SUMMARY_STRATEGIES = {
 
 DISCUSSION_RULES: dict[str, list[str]] = {
     "universal": [
-        "פרק הדיון = אסה רציפה. אין כותרות משנה (H2/H3). מעברים רק עם ביטויי מעבר טקסטואליים.",
+        "פרק הדיון = מאסה רציפה. אין כותרות משנה (H2/H3). מעברים רק עם ביטויי מעבר טקסטואליים.",
         "חריג יחיד לכותרות משנה: נושאים נפרדים לחלוטין (למשל: הקלה בגובה + התייחסות לטענות נוספות).",
         "טווח אורך סעיפים: 20 עד 600+ מילים. סעיף עם ציטוט מקיף = בלוק אחד שלם, לא שבירה לסעיפים קצרים.",
     ],

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

@@ -438,13 +438,14 @@ async def delete_precedent(case_law_id: UUID | str) -> bool:
 
 
 async def get_precedent(case_law_id: UUID | str) -> dict | None:
-    """Get a precedent with its halachot attached."""
+    """Get a precedent with its halachot and related cases attached."""
     if isinstance(case_law_id, str):
         case_law_id = UUID(case_law_id)
     record = await db.get_case_law(case_law_id)
     if not record:
         return None
     record["halachot"] = await db.list_halachot(case_law_id=case_law_id, limit=500)
+    record["related_cases"] = await db.get_case_law_relations(case_law_id)
     return record
 
 

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

@@ -116,6 +116,54 @@ async def precedent_library_get(case_law_id: str) -> str:
     return _ok(record)
 
 
+async def precedent_link_cases(
+    case_law_id_a: str,
+    case_law_id_b: str,
+    relation_type: str = "same_case_chain",
+) -> str:
+    """קישור שתי פסיקות כקשורות זו לזו (דו-כיווני). idempotent.
+
+    Args:
+        case_law_id_a: UUID של פסיקה ראשונה.
+        case_law_id_b: UUID של פסיקה שנייה.
+        relation_type: same_case_chain | overruled_by | distinguished
+    """
+    try:
+        a = UUID(case_law_id_a)
+        b = UUID(case_law_id_b)
+    except ValueError:
+        return _err("case_law_id לא תקין")
+    rec_a = await db.get_case_law(a)
+    rec_b = await db.get_case_law(b)
+    if not rec_a:
+        return _err(f"פסיקה {case_law_id_a} לא נמצאה")
+    if not rec_b:
+        return _err(f"פסיקה {case_law_id_b} לא נמצאה")
+    await db.add_case_law_relation(a, b, relation_type)
+    return _ok({
+        "linked": True,
+        "relation_type": relation_type,
+        "a": {"id": case_law_id_a, "case_number": rec_a.get("case_number"), "court": rec_a.get("court")},
+        "b": {"id": case_law_id_b, "case_number": rec_b.get("case_number"), "court": rec_b.get("court")},
+    })
+
+
+async def precedent_unlink_cases(case_law_id_a: str, case_law_id_b: str) -> str:
+    """הסרת קישור בין שתי פסיקות (דו-כיווני).
+
+    Args:
+        case_law_id_a: UUID של פסיקה ראשונה.
+        case_law_id_b: UUID של פסיקה שנייה.
+    """
+    try:
+        a = UUID(case_law_id_a)
+        b = UUID(case_law_id_b)
+    except ValueError:
+        return _err("case_law_id לא תקין")
+    await db.remove_case_law_relation(a, b)
+    return _ok({"unlinked": True, "a": case_law_id_a, "b": case_law_id_b})
+
+
 async def precedent_library_delete(case_law_id: str) -> str:
     """מחיקת פסיקה מהקורפוס. cascade: chunks + halachot."""
     try:

scripts/sync_agents_across_companies.py

@@ -259,6 +259,14 @@ async def apply_diff(mirror_id: str, agent_name: str, diff: dict) -> list[str]:
     if "runtime_config" in diff:
         patch_body["runtimeConfig"] = diff["runtime_config"]["to"]
 
+    # Stamp claude_md_mtime + last_synced into metadata
+    mtime = diff.get("_claude_md_mtime")
+    if mtime:
+        current_meta = dict(patch_body.get("metadata") or {})
+        current_meta["claude_md_mtime"] = mtime
+        current_meta["claude_md_last_synced"] = datetime.now(timezone.utc).isoformat()
+        patch_body["metadata"] = current_meta
+
     if patch_body:
         status, data = await call_patch(mirror_id, patch_body)
         if status >= 400:
@@ -278,12 +286,73 @@ async def apply_diff(mirror_id: str, agent_name: str, diff: dict) -> list[str]:
     return errors
 
 
+def get_claude_md_mtime(adapter_config: dict) -> str | None:
+    """Return Unix mtime of the agent's instructionsFilePath, or None if file missing."""
+    path = adapter_config.get("instructionsFilePath", "")
+    if not path or not os.path.exists(path):
+        return None
+    return str(int(os.path.getmtime(path)))
+
+
+async def check_instructions(agents: list[dict]) -> bool:
+    """Print a report of all agents' instruction files. Returns True if all OK."""
+    from datetime import datetime
+
+    all_ok = True
+    print(f"\n{'Agent':<30} {'File':<55} {'Status':<12} {'Size':>7} {'Modified'}")
+    print("-" * 115)
+
+    for agent in agents:
+        name = (agent.get("name") or agent.get("id") or "?")[:29]
+
+        try:
+            adapter_cfg = agent.get("adapter_config") or {}
+            if isinstance(adapter_cfg, str):
+                adapter_cfg = json.loads(adapter_cfg)
+        except (json.JSONDecodeError, TypeError):
+            print(f"{name:<30} {'(malformed adapter_config in DB)':<55} {'⚠ ERROR':<12}")
+            continue
+
+        file_path = adapter_cfg.get("instructionsFilePath", "")
+
+        if not file_path:
+            print(f"{name:<30} {'(none)':<55} {'⚠ NOT SET':<12}")
+            continue
+
+        if not os.path.exists(file_path):
+            print(f"{name:<30} {file_path[-54:]:<55} {'❌ MISSING':<12}")
+            all_ok = False
+            continue
+
+        stat = os.stat(file_path)
+        size_kb = stat.st_size // 1024
+        mtime = datetime.fromtimestamp(stat.st_mtime).strftime("%Y-%m-%d %H:%M")
+
+        # Check for drift vs DB metadata
+        try:
+            metadata = agent.get("metadata") or {}
+            if isinstance(metadata, str):
+                metadata = json.loads(metadata)
+        except (json.JSONDecodeError, TypeError):
+            metadata = {}
+        db_mtime = metadata.get("claude_md_mtime", "")
+        actual_mtime = str(int(stat.st_mtime))
+        drift = " ⚠ DRIFT" if db_mtime and db_mtime != actual_mtime else ""
+
+        print(f"{name:<30} {file_path[-54:]:<55} {'✅ OK':<12} {size_kb:>5}KB  {mtime}{drift}")
+
+    print()
+    return all_ok
+
+
 async def main() -> None:
     p = argparse.ArgumentParser()
     g = p.add_mutually_exclusive_group(required=True)
     g.add_argument("--verify", action="store_true", help="Show current drift, no changes")
     g.add_argument("--dry-run", action="store_true", help="Show what would change")
     g.add_argument("--apply", action="store_true", help="Backup + apply changes")
+    g.add_argument("--check-instructions", action="store_true",
+                   help="Scan all agents' instructionsFilePath and report missing/outdated files")
     p.add_argument("--only", help="Sync only the named agent (e.g., 'עוזר משפטי')")
     args = p.parse_args()
 
@@ -295,6 +364,11 @@ async def main() -> None:
     finally:
         await conn.close()
 
+    if args.check_instructions:
+        all_agents = master_agents + mirror_agents
+        all_ok = await check_instructions(all_agents)
+        sys.exit(0 if all_ok else 1)
+
     mirror_by_name = {a["name"]: a for a in mirror_agents}
 
     print(f"\n=== Master (CMP, 1xxx): {len(master_agents)} agents ===")
@@ -332,6 +406,14 @@ async def main() -> None:
         return
 
     # APPLY
+    # Pre-flight: abort if any master agent is missing its instructions file
+    print("🔍 Pre-flight: checking instruction files...")
+    all_ok = await check_instructions(master_agents)
+    if not all_ok:
+        print("❌ Abort: one or more instruction files are missing. Fix before --apply.")
+        sys.exit(1)
+    print("✅ Pre-flight passed.\n")
+
     print(f"\n=== Backup ===")
     backup_path = backup_agents_table()
     print(f"  ✓ {backup_path}")
@@ -340,6 +422,11 @@ async def main() -> None:
     all_errors: list[str] = []
     for master, mirror, diff in plan:
         print(f"\n  → {master['name']} ({mirror['id']})")
+        # Inject mtime into diff so apply_diff can stamp metadata
+        master_ac = master.get("adapter_config") or {}
+        mtime = get_claude_md_mtime(master_ac)
+        if mtime:
+            diff["_claude_md_mtime"] = mtime
         errors = await apply_diff(mirror["id"], master["name"], diff)
         if errors:
             for e in errors:

web-ui/src/app/precedents/[id]/page.tsx

@@ -11,6 +11,7 @@ import { Skeleton } from "@/components/ui/skeleton";
 import { usePrecedent } from "@/lib/api/precedent-library";
 import { PrecedentEditSheet } from "@/components/precedents/precedent-edit-sheet";
 import { ExtractedHalachotSection } from "@/components/precedents/extracted-halachot";
+import { RelatedCasesSection } from "@/components/precedents/link-related-dialog";
 
 const PRACTICE_AREA_LABELS: Record<string, string> = {
   rishuy_uvniya: "רישוי ובנייה",
@@ -152,6 +153,15 @@ export default function PrecedentDetailPage({
               </CardContent>
             </Card>
 
+            <Card className="bg-surface border-rule shadow-sm">
+              <CardContent className="px-6 py-5">
+                <RelatedCasesSection
+                  caseId={id}
+                  related={data.related_cases ?? []}
+                />
+              </CardContent>
+            </Card>
+
             <Card className="bg-surface border-rule shadow-sm">
               <CardContent className="px-6 py-5">
                 <ExtractedHalachotSection halachot={data.halachot ?? []} />

web-ui/src/components/precedents/library-list-panel.tsx

@@ -1,6 +1,7 @@
 "use client";
 
 import { useState } from "react";
+import Link from "next/link";
 import { Trash2, Plus, Pencil, Wand2 } from "lucide-react";
 import { toast } from "sonner";
 import {
@@ -151,7 +152,9 @@ function CourtRow({ p, onEdit }: { p: Precedent; onEdit: (id: string) => void })
         className="font-semibold text-navy text-right whitespace-normal break-words min-w-[280px] max-w-[420px] py-3"
         dir="rtl"
       >
-        <span dir="auto">{cleanCitation(p.case_number)}</span>
+        <Link href={`/precedents/${p.id}`} className="hover:underline hover:text-gold-deep" dir="auto">
+          {cleanCitation(p.case_number)}
+        </Link>
       </TableCell>
       <TableCell className="text-ink whitespace-normal break-words max-w-[260px] py-3">
         <div className="font-medium">{cleanCitation(p.case_name)}</div>
@@ -233,7 +236,9 @@ function CommitteeRow({ p, onEdit }: { p: Precedent; onEdit: (id: string) => voi
         className="font-semibold text-navy text-right whitespace-normal break-words min-w-[200px] max-w-[320px] py-3"
         dir="rtl"
       >
-        <span dir="auto">{cleanCitation(p.case_number)}</span>
+        <Link href={`/precedents/${p.id}`} className="hover:underline hover:text-gold-deep" dir="auto">
+          {cleanCitation(p.case_number)}
+        </Link>
       </TableCell>
       <TableCell className="text-ink whitespace-normal break-words max-w-[220px] py-3">
         <div className="font-medium">{cleanCitation(p.case_name)}</div>
@@ -308,8 +313,8 @@ export function LibraryListPanel() {
     limit: 200,
   };
 
-  const courts = usePrecedents({ ...sharedFilters, sourceKind: "external_upload" });
+  const courts = usePrecedents({ ...sharedFilters, sourceKind: "external_upload", sourceType: "court_ruling" });
-  const committee = usePrecedents({ ...sharedFilters, sourceKind: "internal_committee" });
+  const committee = usePrecedents({ ...sharedFilters, sourceKind: "all_committees" });
 
   return (
     <div className="space-y-8">

web-ui/src/components/precedents/link-related-dialog.tsx

@@ -0,0 +1,222 @@
+"use client";
+
+import { useState } from "react";
+import { Link2, Loader2, X } from "lucide-react";
+import { toast } from "sonner";
+import {
+  Dialog,
+  DialogContent,
+  DialogHeader,
+  DialogTitle,
+} from "@/components/ui/dialog";
+import { Button } from "@/components/ui/button";
+import { Input } from "@/components/ui/input";
+import { Badge } from "@/components/ui/badge";
+import {
+  usePrecedents,
+  useLinkRelatedCase,
+  useUnlinkRelatedCase,
+  RelatedCase,
+} from "@/lib/api/precedent-library";
+
+const LEVEL_LABELS: Record<string, string> = {
+  "עליון": "עליון",
+  "מנהלי": "מנהלי",
+  "ועדת_ערר_ארצית": "ארצי",
+  "ועדת_ערר_מחוזית": "מחוזי",
+};
+
+const LEVEL_COLORS: Record<string, string> = {
+  "עליון": "bg-red-50 text-red-700 border-red-200",
+  "מנהלי": "bg-orange-50 text-orange-700 border-orange-200",
+  "ועדת_ערר_ארצית": "bg-blue-50 text-blue-700 border-blue-200",
+  "ועדת_ערר_מחוזית": "bg-green-50 text-green-700 border-green-200",
+};
+
+// ── Search Dialog ────────────────────────────────────────────────────
+
+type DialogProps = {
+  caseId: string;
+  currentRelated: RelatedCase[];
+  open: boolean;
+  onOpenChange: (open: boolean) => void;
+};
+
+function LinkDialog({ caseId, currentRelated, open, onOpenChange }: DialogProps) {
+  const [query, setQuery] = useState("");
+  const { mutateAsync: linkCase, isPending } = useLinkRelatedCase(caseId);
+  const alreadyLinkedIds = new Set([...currentRelated.map((r) => r.id), caseId]);
+
+  const { data, isPending: searching } = usePrecedents(
+    query.length >= 2 ? { search: query, limit: 10 } : {},
+  );
+
+  const candidates = (data?.items ?? []).filter((p) => !alreadyLinkedIds.has(p.id));
+
+  async function handleLink(relatedId: string) {
+    try {
+      await linkCase({ relatedId });
+      toast.success("הפסיקות קושרו");
+      setQuery("");
+    } catch {
+      toast.error("שגיאה בקישור");
+    }
+  }
+
+  return (
+    <Dialog open={open} onOpenChange={onOpenChange}>
+      <DialogContent className="max-w-lg" dir="rtl">
+        <DialogHeader>
+          <DialogTitle className="text-navy">קשר החלטה קשורה</DialogTitle>
+        </DialogHeader>
+
+        <div className="space-y-3">
+          <Input
+            placeholder="חפש לפי מספר תיק, שם, ערכאה..."
+            value={query}
+            onChange={(e) => setQuery(e.target.value)}
+            autoFocus
+            dir="rtl"
+          />
+
+          {query.length >= 2 && (
+            <div className="space-y-1 max-h-72 overflow-y-auto">
+              {searching ? (
+                <div className="flex items-center gap-2 text-ink-muted text-sm py-3">
+                  <Loader2 className="w-3.5 h-3.5 animate-spin" /> מחפש...
+                </div>
+              ) : candidates.length === 0 ? (
+                <p className="text-ink-muted text-sm py-3 text-center">לא נמצאו תוצאות</p>
+              ) : (
+                candidates.map((p) => (
+                  <button
+                    key={p.id}
+                    onClick={() => handleLink(p.id)}
+                    disabled={isPending}
+                    className="w-full text-right flex items-center justify-between gap-3 px-3 py-2.5 rounded-lg border border-rule hover:bg-surface/60 transition-colors disabled:opacity-50"
+                  >
+                    <div className="min-w-0 flex-1">
+                      <div className="text-sm font-medium text-navy truncate">
+                        {p.case_name || p.case_number}
+                      </div>
+                      <div className="text-[0.72rem] text-ink-muted font-mono" dir="ltr">
+                        {p.case_number}
+                      </div>
+                    </div>
+                    {p.precedent_level && (
+                      <Badge
+                        variant="outline"
+                        className={`text-[0.62rem] shrink-0 ${LEVEL_COLORS[p.precedent_level] ?? ""}`}
+                      >
+                        {LEVEL_LABELS[p.precedent_level] ?? p.precedent_level}
+                      </Badge>
+                    )}
+                  </button>
+                ))
+              )}
+            </div>
+          )}
+
+          {query.length > 0 && query.length < 2 && (
+            <p className="text-ink-muted text-xs">הקלד לפחות 2 תווים</p>
+          )}
+        </div>
+      </DialogContent>
+    </Dialog>
+  );
+}
+
+// ── Related Case Card ────────────────────────────────────────────────
+
+function RelatedCaseCard({ caseId, related }: { caseId: string; related: RelatedCase }) {
+  const { mutateAsync: unlinkCase, isPending } = useUnlinkRelatedCase(caseId);
+
+  async function handleUnlink() {
+    try {
+      await unlinkCase(related.id);
+      toast.success("הקישור הוסר");
+    } catch {
+      toast.error("שגיאה בהסרת הקישור");
+    }
+  }
+
+  return (
+    <div className="flex items-center justify-between gap-3 px-3 py-2.5 rounded-lg border border-rule bg-surface">
+      <a
+        href={`/precedents/${related.id}`}
+        className="min-w-0 flex-1 hover:opacity-80 transition-opacity"
+      >
+        <div className="text-sm font-medium text-navy truncate">
+          {related.case_name || related.case_number}
+        </div>
+        <div className="flex items-center gap-2 mt-0.5 flex-wrap">
+          {related.precedent_level && (
+            <Badge
+              variant="outline"
+              className={`text-[0.62rem] ${LEVEL_COLORS[related.precedent_level] ?? ""}`}
+            >
+              {LEVEL_LABELS[related.precedent_level] ?? related.precedent_level}
+            </Badge>
+          )}
+          {related.court && (
+            <span className="text-[0.7rem] text-ink-muted truncate">{related.court}</span>
+          )}
+          {related.date && (
+            <span className="text-[0.7rem] text-ink-muted tabular-nums" dir="ltr">
+              {related.date.slice(0, 10)}
+            </span>
+          )}
+        </div>
+      </a>
+      <button
+        onClick={handleUnlink}
+        disabled={isPending}
+        className="p-1 rounded hover:bg-danger-bg hover:text-danger transition-colors text-ink-muted disabled:opacity-40 shrink-0"
+        title="הסר קישור"
+      >
+        <X className="w-3.5 h-3.5" />
+      </button>
+    </div>
+  );
+}
+
+// ── Public section component ─────────────────────────────────────────
+
+type SectionProps = {
+  caseId: string;
+  related: RelatedCase[];
+};
+
+export function RelatedCasesSection({ caseId, related }: SectionProps) {
+  const [dialogOpen, setDialogOpen] = useState(false);
+
+  return (
+    <div className="space-y-3">
+      <div className="flex items-center justify-between">
+        <h3 className="text-navy text-sm font-semibold">
+          החלטות קשורות{related.length > 0 ? ` (${related.length})` : ""}
+        </h3>
+        <Button variant="outline" size="sm" onClick={() => setDialogOpen(true)}>
+          <Link2 className="w-3.5 h-3.5 me-1" /> קשר החלטה
+        </Button>
+      </div>
+
+      {related.length === 0 ? (
+        <p className="text-ink-muted text-sm">אין החלטות קשורות עדיין</p>
+      ) : (
+        <div className="space-y-1.5">
+          {related.map((r) => (
+            <RelatedCaseCard key={r.id} caseId={caseId} related={r} />
+          ))}
+        </div>
+      )}
+
+      <LinkDialog
+        caseId={caseId}
+        currentRelated={related}
+        open={dialogOpen}
+        onOpenChange={setDialogOpen}
+      />
+    </div>
+  );
+}

web-ui/src/components/precedents/precedent-edit-sheet.tsx

@@ -1,6 +1,6 @@
 "use client";
 
-import { useEffect, useState } from "react";
+import { useState } from "react";
 import { Save, Sparkles } from "lucide-react";
 import { toast } from "sonner";
 import {
@@ -65,10 +65,12 @@ export function PrecedentEditSheet({ caseLawId, onOpenChange }: Props) {
 
   const [form, setForm] = useState<FormState>(EMPTY);
 
-  // Hydrate form when the record loads.
+  // React-approved derived-state pattern: sync form whenever a different
-  useEffect(() => {
+  // record arrives (including after save+refetch). Using setState during
-    if (!record) return;
+  // render avoids the one-frame flash that useEffect would produce.
-    // eslint-disable-next-line react-hooks/set-state-in-effect
+  const [syncedRecordId, setSyncedRecordId] = useState<string | null>(null);
+  if (record && record.id !== syncedRecordId) {
+    setSyncedRecordId(record.id as string);
     setForm({
       citation: record.case_number || "",
       case_name: record.case_name || "",
@@ -84,7 +86,7 @@ export function PrecedentEditSheet({ caseLawId, onOpenChange }: Props) {
       headnote: record.headnote || "",
       key_quote: (record as { key_quote?: string }).key_quote || "",
     });
-  }, [record]);
+  }
 
   const onSubmit = async (e: React.FormEvent) => {
     e.preventDefault();

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

@@ -84,9 +84,20 @@ export type Halacha = {
   precedent_level?: string;
 };
 
+export type RelatedCase = {
+  id: string;
+  case_number: string;
+  case_name: string;
+  court: string;
+  precedent_level: string;
+  date: string | null;
+  relation_type: string;
+};
+
 export type PrecedentDetail = Precedent & {
   full_text: string;
   halachot: Halacha[];
+  related_cases: RelatedCase[];
 };
 
 export type SearchHit =
@@ -357,6 +368,40 @@ export function useDeletePrecedent() {
   });
 }
 
+export function useLinkRelatedCase(caseId: string) {
+  const qc = useQueryClient();
+  return useMutation({
+    mutationFn: (vars: { relatedId: string; relationType?: string }) =>
+      apiRequest<{ linked: boolean }>(
+        `/api/precedent-library/${encodeURIComponent(caseId)}/relations`,
+        {
+          method: "POST",
+          body: {
+            related_id: vars.relatedId,
+            relation_type: vars.relationType ?? "same_case_chain",
+          },
+        },
+      ),
+    onSuccess: () => {
+      qc.invalidateQueries({ queryKey: libraryKeys.detail(caseId) });
+    },
+  });
+}
+
+export function useUnlinkRelatedCase(caseId: string) {
+  const qc = useQueryClient();
+  return useMutation({
+    mutationFn: (relatedId: string) =>
+      apiRequest<{ unlinked: boolean }>(
+        `/api/precedent-library/${encodeURIComponent(caseId)}/relations/${encodeURIComponent(relatedId)}`,
+        { method: "DELETE" },
+      ),
+    onSuccess: () => {
+      qc.invalidateQueries({ queryKey: libraryKeys.detail(caseId) });
+    },
+  });
+}
+
 export type PrecedentPatch = Partial<{
   case_name: string;
   court: string;

web/app.py

@@ -20,7 +20,7 @@ sys.path.insert(0, str(Path(__file__).resolve().parent.parent / "mcp-server" / "
 
 import zipfile
 
-from fastapi import FastAPI, File, Form, HTTPException, UploadFile
+from fastapi import BackgroundTasks, FastAPI, File, Form, HTTPException, UploadFile
 from fastapi.responses import FileResponse, StreamingResponse
 from typing import Any, Literal
 from pydantic import BaseModel
@@ -44,7 +44,7 @@ from web.mcp_env_catalog import (
     normalize_for_compare,
 )
 from web.progress_store import ProgressStore
-from web.paperclip_api import pc_request
+from web.paperclip_api import emit_case_status_webhook, pc_request
 from web.paperclip_client import (
     COMPANIES as PAPERCLIP_COMPANIES,
     accept_interaction as pc_accept_interaction,
@@ -1135,6 +1135,36 @@ async def list_cases(
     return result
 
 
+@app.get("/api/cases/stale")
+async def api_stale_cases(days: int = 3):
+    """Return cases that haven't been updated in N days and are not in 'final' or 'new' status."""
+    if days <= 0:
+        return {"cases": [], "total": 0}
+    pool = await db.get_pool()
+    async with pool.acquire() as conn:
+        rows = await conn.fetch(
+            """
+            SELECT case_number, title, status,
+                   EXTRACT(DAY FROM (now() - updated_at))::int AS days_stale
+            FROM cases
+            WHERE status NOT IN ('final', 'new')
+              AND updated_at < now() - make_interval(days => $1)
+            ORDER BY updated_at ASC  -- oldest stale first (longest overdue = highest priority)
+            """,
+            days,
+        )
+    cases = [
+        {
+            "case_number": r["case_number"],
+            "title": r["title"],
+            "status": r["status"],
+            "days_stale": r["days_stale"],
+        }
+        for r in rows
+    ]
+    return {"cases": cases, "total": len(cases)}
+
+
 @app.post("/api/cases/{case_number}/archive")
 async def api_archive_case(case_number: str):
     """Move a case to the archive. Also archives the matching Paperclip project."""
@@ -1337,8 +1367,12 @@ async def api_case_get(case_number: str):
 
 
 @app.put("/api/cases/{case_number}")
-async def api_case_update(case_number: str, req: CaseUpdateRequest):
+async def api_case_update(case_number: str, req: CaseUpdateRequest, background_tasks: BackgroundTasks):
     """Update case details."""
+    # Capture old status before the update so we can detect changes.
+    existing = await db.get_case_by_number(case_number)
+    old_status = (existing or {}).get("status", "")
+
     result = await cases_tools.case_update(
         case_number=case_number,
         status=req.status,
@@ -1351,10 +1385,30 @@ async def api_case_update(case_number: str, req: CaseUpdateRequest):
         expected_outcome=req.expected_outcome,
     )
     try:
-        return json.loads(result)
+        parsed = json.loads(result)
     except json.JSONDecodeError:
         raise HTTPException(404, result)
 
+    # Emit webhook when status changes (fire-and-forget via BackgroundTasks).
+    new_status = req.status
+    if new_status and old_status != new_status:
+        prefix = case_number[:1]
+        company_id = (
+            PAPERCLIP_COMPANIES["licensing"] if prefix == "1"
+            else PAPERCLIP_COMPANIES["betterment"] if prefix in ("8", "9")
+            else None
+        )
+        background_tasks.add_task(
+            emit_case_status_webhook,
+            case_number=case_number,
+            old_status=old_status,
+            new_status=new_status,
+            company_id=company_id,  # None is safe — plugin handles unknown company gracefully
+        )
+        logger.debug("webhook scheduled: case %s %s → %s", case_number, old_status, new_status)
+
+    return parsed
+
 
 @app.delete("/api/cases")
 async def api_case_delete(case_number: str, remove_files: bool = False):
@@ -3057,8 +3111,16 @@ async def api_get_methodology(category: str):
     items = {}
     for key, default_val in defaults.items():
         if key in overrides:
+            raw = overrides[key]["rule_value"]
+            # asyncpg returns JSONB as a raw JSON string when no codec is registered.
+            # Parse it back to a Python object so the frontend receives the correct type.
+            if isinstance(raw, str):
+                try:
+                    raw = json.loads(raw)
+                except (json.JSONDecodeError, TypeError):
+                    pass
             items[key] = {
-                "value": overrides[key]["rule_value"],
+                "value": raw,
                 "is_override": True,
                 "updated_at": overrides[key]["created_at"].isoformat() if overrides[key]["created_at"] else None,
             }
@@ -3095,10 +3157,14 @@ async def api_update_methodology(category: str, key: str, req: MethodologyUpdate
             raise HTTPException(422, "content_checklists value must be a non-empty string")
 
     pool = await db.get_pool()
+    # json.dumps → text, then PostgreSQL casts text→jsonb.
+    # Passing a Python list directly causes "expected str, got list" in asyncpg;
+    # passing a str with ::jsonb causes double-encoding (stored as JSONB string).
+    # ::text::jsonb bypasses asyncpg's codec and lets PostgreSQL parse the JSON.
     await pool.execute(
         "INSERT INTO appeal_type_rules (id, appeal_type, rule_category, rule_key, rule_value) "
-        "VALUES (gen_random_uuid(), '_global', $1, $2, $3::jsonb) "
+        "VALUES (gen_random_uuid(), '_global', $1, $2, $3::text::jsonb) "
-        "ON CONFLICT (appeal_type, rule_category, rule_key) DO UPDATE SET rule_value = $3::jsonb",
+        "ON CONFLICT (appeal_type, rule_category, rule_key) DO UPDATE SET rule_value = $3::text::jsonb",
         category, key, json.dumps(req.value, ensure_ascii=False),
     )
 
@@ -3979,6 +4045,34 @@ async def api_resolve_feedback(feedback_id: str, body: dict):
     return {"status": "resolved"}
 
 
+@app.get("/api/chair-feedback/weekly-summary")
+async def api_chair_feedback_weekly_summary(days: int = 7, limit: int = 100):
+    """Return chair feedback from the last N days as a text summary for the CEO agent."""
+    if days <= 0:
+        return {"summary": "", "entry_count": 0}
+    pool = await db.get_pool()
+    async with pool.acquire() as conn:
+        rows = await conn.fetch(
+            """
+            SELECT cf.feedback_text, c.case_number, c.title
+            FROM chair_feedback cf
+            LEFT JOIN cases c ON c.id = cf.case_id
+            WHERE cf.created_at >= now() - make_interval(days => $1)
+            ORDER BY cf.created_at DESC
+            LIMIT $2
+            """,
+            days,
+            limit,
+        )
+    if not rows:
+        return {"summary": "", "entry_count": 0}
+    lines = [
+        f"- תיק {r['case_number'] or '—'} ({r['title'] or '—'}): {r['feedback_text']}"
+        for r in rows
+    ]
+    return {"summary": "\n".join(lines), "entry_count": len(rows)}
+
+
 # ── Background Processing ─────────────────────────────────────────
 
 
@@ -4380,6 +4474,37 @@ async def precedent_library_delete(case_law_id: str):
     return {"deleted": True, "case_law_id": case_law_id}
 
 
+class PrecedentRelationRequest(BaseModel):
+    related_id: str
+    relation_type: str = "same_case_chain"
+
+
+@app.post("/api/precedent-library/{case_law_id}/relations")
+async def precedent_add_relation(case_law_id: str, req: PrecedentRelationRequest):
+    try:
+        a = UUID(case_law_id)
+        b = UUID(req.related_id)
+    except ValueError:
+        raise HTTPException(400, "case_law_id לא תקין")
+    if not await db.get_case_law(a):
+        raise HTTPException(404, "פסיקה לא נמצאה")
+    if not await db.get_case_law(b):
+        raise HTTPException(404, f"פסיקה קשורה {req.related_id} לא נמצאה")
+    await db.add_case_law_relation(a, b, req.relation_type)
+    return {"linked": True, "case_law_id": case_law_id, "related_id": req.related_id}
+
+
+@app.delete("/api/precedent-library/{case_law_id}/relations/{related_id}")
+async def precedent_remove_relation(case_law_id: str, related_id: str):
+    try:
+        a = UUID(case_law_id)
+        b = UUID(related_id)
+    except ValueError:
+        raise HTTPException(400, "case_law_id לא תקין")
+    await db.remove_case_law_relation(a, b)
+    return {"unlinked": True, "case_law_id": case_law_id, "related_id": related_id}
+
+
 # Halacha and metadata extraction are LLM-driven and rely on the local
 # `claude` CLI via mcp-server/services/claude_session.py — they CANNOT run
 # from this container (no CLI, no claude.ai session). The endpoints below

web/paperclip_api.py

@@ -19,6 +19,7 @@ from __future__ import annotations
 
 import logging
 import os
+from datetime import datetime, timezone
 from typing import Any
 
 import httpx
@@ -81,3 +82,35 @@ async def pc_request(
     if raise_on_error:
         resp.raise_for_status()
     return resp
+
+
+async def emit_case_status_webhook(
+    case_number: str,
+    old_status: str,
+    new_status: str,
+    company_id: str | None = None,
+    run_id: str | None = None,
+) -> None:
+    """Notify the Paperclip plugin that a case status changed.
+
+    Fire-and-forget: logs errors but never raises, so callers aren't blocked.
+    """
+    try:
+        await pc_request(
+            "POST",
+            "/api/plugins/marcusgroup.legal-ai/webhooks/case-status",
+            json={
+                "caseNumber": case_number,
+                "oldStatus": old_status,
+                "newStatus": new_status,
+                "companyId": company_id,
+                "timestamp": datetime.now(timezone.utc).isoformat(),
+            },
+            run_id=run_id,
+            timeout=5.0,
+        )
+    except Exception as exc:
+        logger.warning(
+            "emit_case_status_webhook failed for case %s (%s → %s): %s",
+            case_number, old_status, new_status, exc,
+        )