feat: add internal committee decisions corpus (source_kind='internal_committee')

Three-layer separation: style learning (style_corpus), appeals-committee decisions
(internal_committee), and court rulings (external_upload).

- SCHEMA_V10: chair_name + district columns on case_law and cases, partial indexes
- create_internal_committee_decision() DB upsert function
- search_precedent_library_semantic() now accepts source_kind/district/chair_name params
- search_precedent_library_hybrid() passes through new params
- services/internal_decisions.py: ingest_internal_decision, migrate_from_style_corpus,
  migrate_from_external_corpus (identifies rows via source_type='appeals_committee')
- search_internal_decisions() MCP tool (server.py + tools/search.py)
- internal_decision_migrate() MCP admin tool
- Web endpoints: POST /api/internal-decisions/upload, POST /api/internal-decisions/migrate,
  GET /api/internal-decisions
- ingest_final_version auto-ingests finalized decisions into internal corpus
- SKILL.md updated: agents now search internal + external in parallel, present separately

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

mcp-server/src/legal_mcp/server.py

@@ -390,6 +390,35 @@ async def find_similar_cases(
     )
 
 
+@mcp.tool()
+async def search_internal_decisions(
+    query: str,
+    practice_area: str = "",
+    appeal_subtype: str = "",
+    district: str = "",
+    chair_name: str = "",
+    limit: int = 10,
+    include_halachot: bool = True,
+) -> str:
+    """חיפוש בהחלטות ועדות ערר לתכנון ובנייה (כל המחוזות).
+
+    מחזיר החלטות מהקורפוס הפנימי של ועדות הערר — נפרד מפסיקת בתי המשפט.
+    השתמש בו במקביל ל-search_precedent_library להצגת שתי שכבות נפרדות.
+
+    Args:
+        query: שאילתת חיפוש בעברית
+        practice_area: rishuy_uvniya / betterment_levy / compensation_197
+        appeal_subtype: סינון לפי תת-סוג ערר
+        district: מחוז — ירושלים / מרכז / תל אביב / צפון / דרום / ארצי. ריק = כל המחוזות
+        chair_name: שם יו"ר הוועדה לסינון. ריק = כל היו"רים
+        limit: מספר תוצאות מקסימלי
+        include_halachot: האם לכלול הלכות שחולצו
+    """
+    return await search.search_internal_decisions(
+        query, practice_area, appeal_subtype, district, chair_name, limit, include_halachot,
+    )
+
+
 # Drafting
 @mcp.tool()
 async def get_style_guide() -> str:
@@ -573,6 +602,28 @@ async def ingest_final_version(
     return await workflow.ingest_final_version(case_number, file_path, final_text)
 
 
+@mcp.tool()
+async def internal_decision_migrate(
+    source: str = "both",
+    dry_run: bool = True,
+) -> str:
+    """העברת החלטות ועדת ערר קיימות לקורפוס הפנימי (פעולת admin).
+
+    source: 'style_corpus' | 'external_corpus' | 'both'
+    dry_run: אם true — מציג מה יקרה ללא כתיבה
+    """
+    import json as _json
+    from legal_mcp.services import internal_decisions as int_svc
+    if source not in {"style_corpus", "external_corpus", "both"}:
+        return "source חייב להיות style_corpus / external_corpus / both"
+    results: dict = {}
+    if source in {"style_corpus", "both"}:
+        results["style_corpus"] = await int_svc.migrate_from_style_corpus(dry_run=dry_run)
+    if source in {"external_corpus", "both"}:
+        results["external_corpus"] = await int_svc.migrate_from_external_corpus(dry_run=dry_run)
+    return _json.dumps(results, ensure_ascii=False, indent=2)
+
+
 @mcp.tool()
 async def record_chair_feedback(
     case_number: str,

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

@@ -691,6 +691,16 @@ CREATE INDEX IF NOT EXISTS idx_prec_img_emb_case_law
 """
 
 
+SCHEMA_V10_SQL = """
+ALTER TABLE case_law ADD COLUMN IF NOT EXISTS chair_name TEXT DEFAULT '';
+ALTER TABLE case_law ADD COLUMN IF NOT EXISTS district TEXT DEFAULT '';
+ALTER TABLE cases ADD COLUMN IF NOT EXISTS chair_name TEXT DEFAULT '';
+CREATE INDEX IF NOT EXISTS idx_case_law_source_kind ON case_law(source_kind);
+CREATE INDEX IF NOT EXISTS idx_case_law_chair ON case_law(chair_name) WHERE chair_name <> '';
+CREATE INDEX IF NOT EXISTS idx_case_law_district ON case_law(district) WHERE district <> '';
+"""
+
+
 async def _run_schema_migrations(pool: asyncpg.Pool) -> None:
     async with pool.acquire() as conn:
         await conn.execute(SCHEMA_SQL)
@@ -703,7 +713,8 @@ async def _run_schema_migrations(pool: asyncpg.Pool) -> None:
         await conn.execute(SCHEMA_V7_SQL)
         await conn.execute(SCHEMA_V8_SQL)
         await conn.execute(SCHEMA_V9_SQL)
-    logger.info("Database schema initialized (v1-v9)")
+        await conn.execute(SCHEMA_V10_SQL)
+    logger.info("Database schema initialized (v1-v10)")
 
 
 async def init_schema() -> None:
@@ -1817,6 +1828,85 @@ async def create_external_case_law(
     return _row_to_case_law(row)
 
 
+async def create_internal_committee_decision(
+    case_number: str,
+    case_name: str,
+    full_text: str,
+    court: str = "",
+    decision_date: date | None = None,
+    chair_name: str = "",
+    district: str = "",
+    practice_area: str = "",
+    appeal_subtype: str = "",
+    subject_tags: list[str] | None = None,
+    summary: str = "",
+    is_binding: bool = True,
+    document_id: UUID | None = None,
+) -> dict:
+    """Upsert an appeals-committee decision as source_kind='internal_committee'.
+
+    If a row with this case_number already exists as cited_only, promotes it.
+    Idempotent: calling again updates metadata in-place.
+    """
+    pool = await get_pool()
+    tags_json = json.dumps(subject_tags or [], ensure_ascii=False)
+    async with pool.acquire() as conn:
+        existing = await conn.fetchrow(
+            "SELECT id FROM case_law WHERE case_number = $1",
+            case_number,
+        )
+        if existing:
+            row = await conn.fetchrow(
+                """
+                UPDATE case_law SET
+                    case_name = $2,
+                    court = COALESCE(NULLIF($3, ''), court),
+                    date = COALESCE($4, date),
+                    chair_name = COALESCE(NULLIF($5, ''), chair_name),
+                    district = COALESCE(NULLIF($6, ''), district),
+                    practice_area = $7,
+                    appeal_subtype = $8,
+                    subject_tags = $9,
+                    summary = COALESCE(NULLIF($10, ''), summary),
+                    full_text = $11,
+                    source_type = 'appeals_committee',
+                    source_kind = 'internal_committee',
+                    is_binding = $12,
+                    document_id = COALESCE($13, document_id),
+                    extraction_status = 'processing',
+                    halacha_extraction_status = 'pending'
+                WHERE id = $1
+                RETURNING *
+                """,
+                existing["id"], case_name, court, decision_date,
+                chair_name, district, practice_area, appeal_subtype,
+                tags_json, summary, full_text, is_binding, document_id,
+            )
+        else:
+            row = await conn.fetchrow(
+                """
+                INSERT INTO case_law (
+                    case_number, case_name, court, date, chair_name, district,
+                    subject_tags, summary, full_text,
+                    source_kind, source_type, document_id,
+                    extraction_status, halacha_extraction_status,
+                    practice_area, appeal_subtype, is_binding
+                ) VALUES (
+                    $1, $2, $3, $4, $5, $6,
+                    $7, $8, $9,
+                    'internal_committee', 'appeals_committee', $10,
+                    'processing', 'pending',
+                    $11, $12, $13
+                )
+                RETURNING *
+                """,
+                case_number, case_name, court, decision_date, chair_name, district,
+                tags_json, summary, full_text,
+                document_id, practice_area, appeal_subtype, is_binding,
+            )
+    return _row_to_case_law(row)
+
+
 async def update_case_law(case_law_id: UUID, **fields) -> dict | None:
     """Patch metadata fields on a case_law row.
 
@@ -2194,8 +2284,14 @@ async def search_precedent_library_semantic(
     subject_tag: str = "",
     limit: int = 10,
     include_halachot: bool = True,
+    source_kind: str = "external_upload",
+    district: str = "",
+    chair_name: str = "",
 ) -> list[dict]:
-    """Semantic search over chair-uploaded precedents.
+    """Semantic search over precedents filtered by source_kind.
+
+    source_kind='external_upload'  → court rulings (default)
+    source_kind='internal_committee' → appeals-committee decisions
 
     Returns merged halachot + chunks. Halachot are pre-distilled rules, so
     they get a small score boost. Only ``approved`` / ``published`` halachot
@@ -2204,7 +2300,7 @@ async def search_precedent_library_semantic(
     """
     pool = await get_pool()
     halacha_filters = ["h.review_status IN ('approved', 'published')"]
-    chunk_filters = ["cl.source_kind = 'external_upload'"]
+    chunk_filters = [f"cl.source_kind = '{source_kind}'"]
     h_params: list = [query_embedding, limit]
     c_params: list = [query_embedding, limit]
     h_idx = 3
@@ -2249,13 +2345,27 @@ async def search_precedent_library_semantic(
         halacha_filters.append(f"${h_idx} = ANY(h.subject_tags)")
         h_params.append(subject_tag)
         h_idx += 1
+    if district:
+        halacha_filters.append(f"cl.district = ${h_idx}")
+        h_params.append(district)
+        h_idx += 1
+        chunk_filters.append(f"cl.district = ${c_idx}")
+        c_params.append(district)
+        c_idx += 1
+    if chair_name:
+        halacha_filters.append(f"cl.chair_name = ${h_idx}")
+        h_params.append(chair_name)
+        h_idx += 1
+        chunk_filters.append(f"cl.chair_name = ${c_idx}")
+        c_params.append(chair_name)
+        c_idx += 1
 
     halacha_sql = f"""
         SELECT h.id AS halacha_id, h.case_law_id, h.rule_statement,
                h.reasoning_summary, h.supporting_quote, h.page_reference,
                h.practice_areas, h.subject_tags, h.confidence, h.rule_type,
                cl.case_number, cl.case_name, cl.court, cl.date AS decision_date,
-               cl.precedent_level,
+               cl.precedent_level, cl.chair_name, cl.district,
                1 - (h.embedding <=> $1) AS score
         FROM halachot h
         JOIN case_law cl ON cl.id = h.case_law_id
@@ -2269,7 +2379,7 @@ async def search_precedent_library_semantic(
         SELECT pc.id AS chunk_id, pc.case_law_id, pc.content,
                pc.section_type, pc.page_number,
                cl.case_number, cl.case_name, cl.court, cl.date AS decision_date,
-               cl.precedent_level, cl.practice_area,
+               cl.precedent_level, cl.practice_area, cl.chair_name, cl.district,
                1 - (pc.embedding <=> $1) AS score
         FROM precedent_chunks pc
         JOIN case_law cl ON cl.id = pc.case_law_id

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

@@ -88,8 +88,15 @@ async def search_precedent_library_hybrid(
     is_binding: bool | None = None,
     subject_tag: str = "",
     include_halachot: bool = True,
+    source_kind: str = "external_upload",
+    district: str = "",
+    chair_name: str = "",
 ) -> list[dict]:
-    """Hybrid wrapper for precedent-library search."""
+    """Hybrid wrapper for precedent-library search.
+
+    source_kind='external_upload'    → court rulings (default)
+    source_kind='internal_committee' → appeals-committee decisions
+    """
     fetch_k = max(limit, config.VOYAGE_RERANK_FETCH_K) if config.MULTIMODAL_ENABLED else limit
 
     async def _base(limit: int) -> list[dict]:
@@ -103,6 +110,9 @@ async def search_precedent_library_hybrid(
             subject_tag=subject_tag,
             limit=limit,
             include_halachot=include_halachot,
+            source_kind=source_kind,
+            district=district,
+            chair_name=chair_name,
         )
 
     text_results = await rerank.maybe_rerank(

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

@@ -0,0 +1,301 @@
+"""Orchestrator for the Internal Committee Decisions corpus.
+
+Ingest pipeline:
+    text/file → INSERT case_law (source_kind='internal_committee')
+        → chunk → embed → store precedent_chunks
+        → queue halacha extraction
+
+Migration helpers:
+    migrate_from_style_corpus()   — re-index style_corpus entries as searchable
+    migrate_from_external_corpus() — reclassify external appeals-committee rows
+
+All ועדות ערר (any district) belong here.
+Judicial decisions (Supreme Court, Administrative Court) stay in external_upload.
+"""
+
+from __future__ import annotations
+
+import logging
+import re
+import shutil
+from datetime import date
+from pathlib import Path
+from uuid import UUID, uuid4
+
+from legal_mcp import config
+from legal_mcp.services import chunker, db, embeddings, extractor
+
+logger = logging.getLogger(__name__)
+
+INTERNAL_DECISIONS_DIR = Path(config.DATA_DIR) / "internal-decisions"
+
+_VALID_DISTRICTS = {"", "ירושלים", "מרכז", "תל אביב", "צפון", "דרום", "ארצי"}
+
+_COURT_TO_DISTRICT = [
+    ("ירושלים", "ירושלים"),
+    ("תל אביב", "תל אביב"),
+    ('ת"א', "תל אביב"),
+    ("מרכז", "מרכז"),
+    ("חיפה", "צפון"),
+    ("צפון", "צפון"),
+    ("דרום", "דרום"),
+    ("ארצי", "ארצי"),
+    ("ארצית", "ארצי"),
+]
+
+
+def _coerce_date(value) -> date | None:
+    if value is None or value == "":
+        return None
+    if isinstance(value, date):
+        return value
+    if isinstance(value, str):
+        try:
+            return date.fromisoformat(value[:10])
+        except ValueError:
+            return None
+    return None
+
+
+def _safe_filename(name: str) -> str:
+    base = Path(name).name
+    return re.sub(r"[^\w.\-+א-ת ]", "_", base) or f"internal-{uuid4().hex[:8]}"
+
+
+def _district_from_court(court: str) -> str:
+    for keyword, district in _COURT_TO_DISTRICT:
+        if keyword in court:
+            return district
+    return ""
+
+
+async def ingest_internal_decision(
+    *,
+    case_number: str,
+    case_name: str = "",
+    court: str = "",
+    decision_date=None,
+    chair_name: str = "",
+    district: str = "",
+    practice_area: str = "",
+    appeal_subtype: str = "",
+    subject_tags: list[str] | None = None,
+    summary: str = "",
+    is_binding: bool = True,
+    file_path: str | Path | None = None,
+    text: str | None = None,
+    document_id: UUID | None = None,
+) -> dict:
+    """Ingest an appeals-committee decision into the internal corpus.
+
+    Either file_path or text must be provided.
+    If district is empty, it is inferred from court.
+    Returns: {"status": "completed", "case_law_id": "...", "chunks": N}
+    """
+    if not file_path and not text:
+        raise ValueError("either file_path or text is required")
+    if not case_number.strip():
+        raise ValueError("case_number is required")
+
+    resolved_district = district.strip() or _district_from_court(court)
+
+    if file_path:
+        src = Path(file_path)
+        if not src.is_file():
+            raise FileNotFoundError(f"file not found: {src}")
+        dest_dir = INTERNAL_DECISIONS_DIR / (resolved_district or "other")
+        dest_dir.mkdir(parents=True, exist_ok=True)
+        staged = dest_dir / f"{uuid4().hex[:8]}_{_safe_filename(src.name)}"
+        shutil.copy2(src, staged)
+        raw_text, page_count, page_offsets = await extractor.extract_text(str(staged))
+        raw_text = extractor.strip_nevo_preamble(raw_text or "").strip()
+        if not raw_text:
+            raise ValueError("no extractable text in file")
+    else:
+        raw_text = (text or "").strip()
+        if not raw_text:
+            raise ValueError("text is empty")
+        page_count = 0
+        page_offsets = None
+
+    record = await db.create_internal_committee_decision(
+        case_number=case_number.strip(),
+        case_name=(case_name.strip() or case_number.strip()),
+        full_text=raw_text,
+        court=court.strip(),
+        decision_date=_coerce_date(decision_date),
+        chair_name=chair_name.strip(),
+        district=resolved_district,
+        practice_area=practice_area,
+        appeal_subtype=appeal_subtype.strip(),
+        subject_tags=list(subject_tags or []),
+        summary=summary.strip(),
+        is_binding=is_binding,
+        document_id=document_id,
+    )
+    case_law_id = UUID(str(record["id"]))
+
+    try:
+        chunks = chunker.chunk_document(raw_text, page_offsets=page_offsets)
+        if not chunks:
+            await db.set_case_law_extraction_status(case_law_id, "completed")
+            await db.set_case_law_halacha_status(case_law_id, "completed")
+            return {"status": "completed", "case_law_id": str(case_law_id), "chunks": 0}
+
+        chunk_texts = [c.content for c in chunks]
+        chunk_vectors = await embeddings.embed_texts(chunk_texts, input_type="document")
+        chunk_dicts = [
+            {
+                "chunk_index": c.chunk_index,
+                "content": c.content,
+                "section_type": c.section_type,
+                "page_number": c.page_number,
+                "embedding": v,
+            }
+            for c, v in zip(chunks, chunk_vectors)
+        ]
+        stored = await db.store_precedent_chunks(case_law_id, chunk_dicts)
+
+        await db.set_case_law_extraction_status(case_law_id, "completed")
+        await db.set_case_law_halacha_status(case_law_id, "pending")
+        await db.request_halacha_extraction(case_law_id)
+
+        return {
+            "status": "completed",
+            "case_law_id": str(case_law_id),
+            "chunks": stored,
+            "halachot_pending": True,
+        }
+
+    except Exception:
+        logger.exception("ingest_internal_decision failed for %s", case_number)
+        await db.set_case_law_extraction_status(case_law_id, "failed")
+        raise
+
+
+async def migrate_from_style_corpus(dry_run: bool = False) -> dict:
+    """Re-index all style_corpus entries as searchable internal committee decisions.
+
+    Does NOT delete style_corpus rows — they remain for style analysis.
+    Skips entries that already exist in case_law as internal_committee.
+    """
+    pool = await db.get_pool()
+    async with pool.acquire() as conn:
+        rows = await conn.fetch(
+            """SELECT decision_number, decision_date, full_text,
+                      practice_area, appeal_subtype, subject_categories
+               FROM style_corpus
+               ORDER BY decision_date NULLS LAST"""
+        )
+
+    results = {"total": len(rows), "ingested": 0, "skipped": 0, "failed": 0, "dry_run": dry_run}
+
+    for row in rows:
+        case_number = (row["decision_number"] or "").strip()
+        if not case_number:
+            results["skipped"] += 1
+            continue
+
+        if not dry_run:
+            existing = await pool.fetchval(
+                "SELECT id FROM case_law WHERE case_number = $1 AND source_kind = 'internal_committee'",
+                case_number,
+            )
+            if existing:
+                results["skipped"] += 1
+                continue
+
+        if dry_run:
+            results["ingested"] += 1
+            continue
+
+        try:
+            subject_tags = list(row["subject_categories"] or [])
+            await ingest_internal_decision(
+                case_number=case_number,
+                court="ועדת הערר לתכנון ובנייה — מחוז ירושלים",
+                decision_date=row["decision_date"],
+                chair_name="דפנה תמיר",
+                district="ירושלים",
+                practice_area=row["practice_area"] or "",
+                appeal_subtype=row["appeal_subtype"] or "",
+                subject_tags=subject_tags,
+                text=row["full_text"],
+            )
+            results["ingested"] += 1
+            logger.info("Migrated style_corpus entry: %s", case_number)
+        except Exception as e:
+            logger.error("Failed to migrate %s: %s", case_number, e)
+            results["failed"] += 1
+
+    return results
+
+
+async def migrate_from_external_corpus(dry_run: bool = False) -> dict:
+    """Reclassify external appeals-committee decisions to source_kind='internal_committee'.
+
+    Identifies rows by source_type='appeals_committee' and updates source_kind + district.
+    Existing precedent_chunks remain — no re-embedding needed.
+    """
+    pool = await db.get_pool()
+    async with pool.acquire() as conn:
+        rows = await conn.fetch(
+            """SELECT id, case_number, court
+               FROM case_law
+               WHERE source_kind = 'external_upload'
+                 AND source_type = 'appeals_committee'"""
+        )
+
+    results = {"total": len(rows), "updated": 0, "dry_run": dry_run}
+
+    if dry_run:
+        results["updated"] = len(rows)
+        results["preview"] = [
+            {"case_number": r["case_number"], "court": r["court"], "district": _district_from_court(r["court"] or "")}
+            for r in rows
+        ]
+        return results
+
+    async with pool.acquire() as conn:
+        for row in rows:
+            district = _district_from_court(row["court"] or "")
+            await conn.execute(
+                """UPDATE case_law
+                   SET source_kind = 'internal_committee',
+                       district = CASE WHEN $2 <> '' THEN $2 ELSE district END
+                   WHERE id = $1""",
+                row["id"], district,
+            )
+        results["updated"] = len(rows)
+
+    logger.info("Migrated %d external appeals-committee rows to internal_committee", len(rows))
+    return results
+
+
+async def search_internal(
+    query: str,
+    *,
+    practice_area: str = "",
+    appeal_subtype: str = "",
+    district: str = "",
+    chair_name: str = "",
+    limit: int = 10,
+    include_halachot: bool = True,
+) -> list[dict]:
+    """Semantic search over internal committee decisions."""
+    from legal_mcp.services import hybrid_search
+
+    if not query.strip():
+        return []
+    query_vec = await embeddings.embed_query(query)
+    return await hybrid_search.search_precedent_library_hybrid(
+        query=query,
+        query_text_embedding=query_vec,
+        limit=limit,
+        practice_area=practice_area,
+        appeal_subtype=appeal_subtype,
+        include_halachot=include_halachot,
+        source_kind="internal_committee",
+        district=district,
+        chair_name=chair_name,
+    )

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

@@ -179,3 +179,63 @@ async def find_similar_cases(
         })
 
     return json.dumps(formatted, ensure_ascii=False, indent=2)
+
+
+async def search_internal_decisions(
+    query: str,
+    practice_area: str = "",
+    appeal_subtype: str = "",
+    district: str = "",
+    chair_name: str = "",
+    limit: int = 10,
+    include_halachot: bool = True,
+) -> str:
+    """חיפוש בהחלטות ועדות ערר לתכנון ובנייה (כל המחוזות).
+
+    Args:
+        query: שאילתת חיפוש בעברית
+        practice_area: rishuy_uvniya / betterment_levy / compensation_197
+        appeal_subtype: סינון לפי תת-סוג ערר
+        district: מחוז — ירושלים / מרכז / תל אביב / צפון / דרום / ארצי. ריק = כל המחוזות
+        chair_name: שם יו"ר הוועדה לסינון. ריק = כל היו"רים
+        limit: מספר תוצאות מקסימלי
+        include_halachot: האם לכלול הלכות שחולצו
+    """
+    from legal_mcp.services import internal_decisions as int_svc
+
+    results = await int_svc.search_internal(
+        query,
+        practice_area=practice_area,
+        appeal_subtype=appeal_subtype,
+        district=district,
+        chair_name=chair_name,
+        limit=limit,
+        include_halachot=include_halachot,
+    )
+
+    if not results:
+        return "לא נמצאו החלטות ועדת ערר רלוונטיות."
+
+    formatted = []
+    for r in results:
+        entry = {
+            "score": round(float(r["score"]), 4),
+            "type": r.get("type", "passage"),
+            "case_number": r.get("case_number"),
+            "case_name": r.get("case_name"),
+            "court": r.get("court"),
+            "district": r.get("district"),
+            "chair_name": r.get("chair_name"),
+            "decision_date": r.get("decision_date"),
+        }
+        if r.get("type") == "halacha":
+            entry["rule"] = r.get("rule_statement")
+            entry["quote"] = r.get("supporting_quote")
+            entry["rule_type"] = r.get("rule_type")
+        else:
+            entry["content"] = r.get("content", "")
+            entry["section"] = r.get("section_type")
+            entry["page"] = r.get("page_number")
+        formatted.append(entry)
+
+    return json.dumps(formatted, ensure_ascii=False, indent=2)

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

@@ -3,10 +3,13 @@
 from __future__ import annotations
 
 import json
+import logging
 from uuid import UUID
 
 from legal_mcp.services import db
 
+logger = logging.getLogger(__name__)
+
 
 async def workflow_status(case_number: str) -> str:
     """סטטוס תהליך עבודה מלא לתיק - מסמכים, עיבוד, טיוטות.
@@ -315,10 +318,29 @@ async def ingest_final_version(
 
     try:
         result = await learning_loop.process_final_version(case_id, final_text)
-        return json.dumps(result, default=str, ensure_ascii=False, indent=2)
     except ValueError as e:
         return json.dumps({"status": "error", "message": str(e)}, ensure_ascii=False, indent=2)
 
+    # Auto-ingest into internal committee decisions corpus (best-effort).
+    try:
+        from legal_mcp.services import internal_decisions as int_svc
+        await int_svc.ingest_internal_decision(
+            case_number=case_number,
+            case_name=case.get("title", ""),
+            decision_date=case.get("decision_date"),
+            chair_name=case.get("chair_name", ""),
+            district="ירושלים",
+            practice_area=case.get("practice_area", ""),
+            appeal_subtype=case.get("appeal_subtype", ""),
+            text=final_text,
+        )
+        result["internal_corpus_ingested"] = True
+    except Exception as e:
+        logger.warning("ingest_final_version: internal corpus ingestion failed (non-fatal): %s", e)
+        result["internal_corpus_ingested"] = False
+
+    return json.dumps(result, default=str, ensure_ascii=False, indent=2)
+
 
 # ── Chair feedback tools ──────────────────────────────────────────
 

skills/decision/SKILL.md

@@ -293,18 +293,25 @@ description: This skill should be used when writing legal decisions (החלטו
 
 ### 7.5 שלושה מקורות פסיקה — אל תבלבל
 
-המערכת מפרידה בין שלושה קורפוסי פסיקה. כל אחד מהם משמש למטרה אחרת ויש כלי MCP נפרד לחיפוש בו:
+המערכת מפרידה בין **ארבעה** קורפוסי פסיקה. כל אחד מהם משמש למטרה אחרת ויש כלי MCP נפרד לחיפוש בו:
 
 | קורפוס | טבלה | כלי חיפוש | תפקיד |
 |---|---|---|---|
-| תקדימי דפנה (סגנון) | `style_corpus` + `paragraph_embeddings` | `search_decisions` | החלטות שדפנה עצמה כתבה. מקור לסגנון, ניסוחים, ג'וריספרודנציה אישית. |
+| לימוד סגנון | `style_corpus` | (לא לחיפוש תוכן) | ממשק /training — ניתוח "הקול" של היו"ר: טון, ביטויי מעבר, מבנה פסקאות. **אין לחפש כאן תוכן משפטי.** |
-| ספריית הפסיקה הסמכותית | `case_law` (`source_kind='external_upload'`) + `halachot` | `search_precedent_library` | פסיקה חיצונית מחייבת — עליון, מנהלי, ועדות ערר אחרות — עם הלכות שאושרו ע"י דפנה. **המקור היחיד לציטוטים בבלוק י לפי CREAC.** |
+| החלטות ועדות ערר | `case_law` (`source_kind='internal_committee'`) + `halachot` | `search_internal_decisions` | **כל** ועדות הערר לתכנון ובנייה (כל המחוזות). מסונן לפי `district` ו-`chair_name`. מקור לעקביות פנימית ופרקטיקה ארצית. |
-| ציטוטים שצורפו ידנית | `case_precedents` | `precedent_search_library` | quotes שדפנה צירפה לתיק ספציפי בעבר. דומה לקורפוס סמכותי אך פר-תיק, ידני, לא עוברת חילוץ הלכות. |
+| פסיקת בתי משפט | `case_law` (`source_kind='external_upload'`) + `halachot` | `search_precedent_library` | בתי משפט: עליון, מנהלי, בג"ץ. **המקור היחיד לציטוטים מחייבים בבלוק י לפי CREAC.** |
+| ציטוטים ידניים | `case_precedents` | `precedent_search_library` | quotes שצורפו לתיק ספציפי בעבר. פר-תיק, ידני. |
 
-**הזרימה הסטנדרטית בבלוק י:**
+**הזרימה הסטנדרטית בבלוק י — חפש במקביל:**
-1. `search_decisions` קודם — בדוק אם דפנה כבר הכריעה בסוגיה דומה (חיסכון דוקטרינרי / הבחנה).
+1. `search_internal_decisions(district="ירושלים")` — האם ועדת ערר ירושלים הכריעה בסוגיה? (עקביות פנימית)
-2. `search_precedent_library` — חפש את הכלל המחייב והציטוט התומך לפסקת CREAC.
+   - אם יש תוצאה רלוונטית: הצג תחת **"החלטות ועדת ערר ירושלים"** והתייחס לה בניתוח.
-3. אם הצדדים הפנו לפסיקה שלא בקורפוס — דפנה מעלה אותה דרך `/precedents` ב-UI; חילוץ ההלכות אוטומטי וההלכות מחכות לאישורה.
+2. `search_internal_decisions()` (ריק = כל המחוזות) — פרקטיקה ארצית של ועדות אחרות.
+   - הצג תחת **"החלטות ועדות ערר אחרות"** — כמשל/השוואה, לא כמחייב.
+3. `search_precedent_library` — כלל מחייב מבית משפט לפסקת CREAC.
+   - הצג תחת **"פסיקת בתי משפט"** — זה המקור לציטוט מחייב.
+4. אם הצדדים הפנו לפסיקה שלא בקורפוס — דפנה מעלה אותה דרך `/precedents` ב-UI.
+
+**חשוב:** החלטות ועדת ערר הן פרקטיקה, לא מחייב. ציטוט מחייב בבלוק י מגיע רק מ-`search_precedent_library`.
 
 **איסור על המצאת ציטוטים** — ציטוט פסיקה חייב להגיע מאחד מהקורפוסים. אם אין הלכה מאושרת תומכת בנקודה — אל תמציא; ציין שהנושא דורש הוספת פסיקה לקורפוס.
 

web/app.py

@@ -4395,6 +4395,148 @@ async def precedent_queue_pending(kind: str = "metadata", limit: int = 20):
     return {"items": items, "count": len(items)}
 
 
+from legal_mcp.services import internal_decisions as int_decisions_service  # noqa: E402
+
+
+@app.post("/api/internal-decisions/upload")
+async def internal_decisions_upload(
+    file: UploadFile = File(...),
+    case_number: str = Form(...),
+    case_name: str = Form(""),
+    court: str = Form(""),
+    decision_date: str = Form(""),
+    chair_name: str = Form(""),
+    district: str = Form(""),
+    practice_area: str = Form(""),
+    appeal_subtype: str = Form(""),
+    subject_tags: str = Form("[]"),
+    is_binding: bool = Form(True),
+    summary: str = Form(""),
+):
+    """Upload a planning appeals-committee decision to the internal corpus."""
+    if practice_area and practice_area not in _PRACTICE_AREAS:
+        raise HTTPException(400, "practice_area לא תקין")
+    if not case_number.strip():
+        raise HTTPException(400, "case_number חובה")
+
+    suffix = Path(file.filename or "").suffix.lower()
+    if suffix not in ALLOWED_EXTENSIONS:
+        raise HTTPException(400, f"סוג קובץ לא נתמך: {suffix}")
+
+    UPLOAD_DIR.mkdir(parents=True, exist_ok=True)
+    staged = UPLOAD_DIR / f"int_{uuid4().hex[:8]}_{file.filename}"
+    size = 0
+    with staged.open("wb") as out:
+        while chunk := await file.read(1024 * 1024):
+            size += len(chunk)
+            if size > MAX_FILE_SIZE:
+                staged.unlink(missing_ok=True)
+                raise HTTPException(413, "קובץ גדול מדי")
+            out.write(chunk)
+
+    try:
+        tags = json.loads(subject_tags) if subject_tags else []
+        if not isinstance(tags, list):
+            tags = []
+    except json.JSONDecodeError:
+        tags = []
+
+    task_id = str(uuid4())
+    await _progress.set(task_id, {
+        "status": "queued", "filename": file.filename or "",
+        "stage": "queued", "percent": 0,
+    })
+
+    async def _run():
+        try:
+            await int_decisions_service.ingest_internal_decision(
+                case_number=case_number.strip(),
+                case_name=case_name.strip(),
+                court=court.strip(),
+                decision_date=decision_date or None,
+                chair_name=chair_name.strip(),
+                district=district.strip(),
+                practice_area=practice_area,
+                appeal_subtype=appeal_subtype.strip(),
+                subject_tags=tags,
+                is_binding=is_binding,
+                summary=summary.strip(),
+                file_path=staged,
+            )
+            await _progress.set(task_id, {"status": "completed", "percent": 100})
+        except Exception as e:
+            logger.exception("internal-decisions upload failed")
+            await _progress.set(task_id, {"status": "failed", "error": str(e)})
+        finally:
+            staged.unlink(missing_ok=True)
+
+    asyncio.create_task(_run())
+    return {"task_id": task_id}
+
+
+@app.post("/api/internal-decisions/migrate")
+async def internal_decisions_migrate(
+    source: str = "both",
+    dry_run: bool = True,
+):
+    """Migrate existing data to the internal committee corpus.
+
+    source: 'style_corpus' | 'external_corpus' | 'both'
+    dry_run: if true, only report what would be done (no writes)
+    """
+    if source not in {"style_corpus", "external_corpus", "both"}:
+        raise HTTPException(400, "source חייב להיות style_corpus / external_corpus / both")
+
+    results: dict = {}
+    if source in {"style_corpus", "both"}:
+        results["style_corpus"] = await int_decisions_service.migrate_from_style_corpus(dry_run=dry_run)
+    if source in {"external_corpus", "both"}:
+        results["external_corpus"] = await int_decisions_service.migrate_from_external_corpus(dry_run=dry_run)
+    return results
+
+
+@app.get("/api/internal-decisions")
+async def internal_decisions_list(
+    district: str = "",
+    chair_name: str = "",
+    practice_area: str = "",
+    limit: int = 100,
+):
+    """List internal committee decisions with optional filters."""
+    pool = await db.get_pool()
+    async with pool.acquire() as conn:
+        conditions = ["source_kind = 'internal_committee'"]
+        params: list = []
+        idx = 1
+        if district:
+            conditions.append(f"district = ${idx}")
+            params.append(district)
+            idx += 1
+        if chair_name:
+            conditions.append(f"chair_name = ${idx}")
+            params.append(chair_name)
+            idx += 1
+        if practice_area:
+            conditions.append(f"practice_area = ${idx}")
+            params.append(practice_area)
+            idx += 1
+        params.append(limit)
+        where = " AND ".join(conditions)
+        rows = await conn.fetch(
+            f"SELECT id, case_number, case_name, court, district, chair_name, "
+            f"date, practice_area, appeal_subtype, extraction_status, halacha_extraction_status "
+            f"FROM case_law WHERE {where} ORDER BY date DESC NULLS LAST LIMIT ${idx}",
+            *params,
+        )
+        total = await conn.fetchval(
+            "SELECT COUNT(*) FROM case_law WHERE source_kind = 'internal_committee'"
+        )
+    return {
+        "total": total,
+        "items": [dict(r) for r in rows],
+    }
+
+
 @app.get("/api/halachot")
 async def halachot_list(
     case_law_id: str = "",