Initial commit: MCP server + web upload interface

Ezer Mishpati - AI legal decision drafting system with:
- MCP server (FastMCP) with document processing pipeline
- Web upload interface (FastAPI) for file upload and classification
- pgvector-based semantic search
- Hebrew legal document chunking and embedding

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

@@ -0,0 +1,118 @@
+"""MCP tools for workflow status tracking."""
+
+from __future__ import annotations
+
+import json
+from uuid import UUID
+
+from legal_mcp.services import db
+
+
+async def workflow_status(case_number: str) -> str:
+    """סטטוס תהליך עבודה מלא לתיק - מסמכים, עיבוד, טיוטות.
+
+    Args:
+        case_number: מספר תיק הערר
+    """
+    case = await db.get_case_by_number(case_number)
+    if not case:
+        return f"תיק {case_number} לא נמצא."
+
+    case_id = UUID(case["id"])
+    docs = await db.list_documents(case_id)
+
+    # Count chunks per document
+    pool = await db.get_pool()
+    async with pool.acquire() as conn:
+        chunk_counts = await conn.fetch(
+            "SELECT document_id, COUNT(*) as count FROM document_chunks WHERE case_id = $1 GROUP BY document_id",
+            case_id,
+        )
+    chunk_map = {str(r["document_id"]): r["count"] for r in chunk_counts}
+
+    doc_status = []
+    for doc in docs:
+        doc_status.append({
+            "title": doc["title"],
+            "type": doc["doc_type"],
+            "extraction": doc["extraction_status"],
+            "chunks": chunk_map.get(doc["id"], 0),
+            "pages": doc.get("page_count"),
+        })
+
+    # Check draft status
+    from pathlib import Path
+    from legal_mcp import config
+
+    case_dir = config.CASES_DIR / case_number
+    draft_path = case_dir / "drafts" / "decision.md"
+    has_draft = draft_path.exists()
+    draft_size = draft_path.stat().st_size if has_draft else 0
+
+    status = {
+        "case_number": case["case_number"],
+        "title": case["title"],
+        "status": case["status"],
+        "documents": doc_status,
+        "total_documents": len(docs),
+        "total_chunks": sum(chunk_map.values()),
+        "has_draft": has_draft,
+        "draft_size_bytes": draft_size,
+        "next_steps": _suggest_next_steps(case, docs, has_draft),
+    }
+
+    return json.dumps(status, ensure_ascii=False, indent=2)
+
+
+def _suggest_next_steps(case: dict, docs: list, has_draft: bool) -> list[str]:
+    """Suggest next steps based on case state."""
+    steps = []
+    doc_types = {d["doc_type"] for d in docs}
+
+    if not docs:
+        steps.append("העלה מסמכים לתיק (כתב ערר, תשובת ועדה)")
+    else:
+        if "appeal" not in doc_types:
+            steps.append("העלה כתב ערר")
+        if "response" not in doc_types:
+            steps.append("העלה תשובת ועדה/משיבים")
+
+    pending = [d for d in docs if d["extraction_status"] == "pending"]
+    if pending:
+        steps.append(f"עיבוד {len(pending)} מסמכים ממתינים")
+
+    if docs and not has_draft:
+        steps.append("התחל ניסוח טיוטת החלטה (/draft-decision)")
+    elif has_draft and case["status"] in ("new", "in_progress"):
+        steps.append("סקור ועדכן את הטיוטה")
+        steps.append("עדכן סטטוס ל-drafted")
+
+    if case["status"] == "drafted":
+        steps.append("סקירה סופית ועדכון סטטוס ל-reviewed")
+    elif case["status"] == "reviewed":
+        steps.append("אישור סופי ועדכון סטטוס ל-final")
+
+    return steps
+
+
+async def processing_status() -> str:
+    """סטטוס כללי - מספר תיקים, מסמכים ממתינים לעיבוד."""
+    pool = await db.get_pool()
+    async with pool.acquire() as conn:
+        case_count = await conn.fetchval("SELECT COUNT(*) FROM cases")
+        doc_count = await conn.fetchval("SELECT COUNT(*) FROM documents")
+        pending_count = await conn.fetchval(
+            "SELECT COUNT(*) FROM documents WHERE extraction_status = 'pending'"
+        )
+        chunk_count = await conn.fetchval("SELECT COUNT(*) FROM document_chunks")
+        corpus_count = await conn.fetchval("SELECT COUNT(*) FROM style_corpus")
+        pattern_count = await conn.fetchval("SELECT COUNT(*) FROM style_patterns")
+
+    return json.dumps({
+        "cases": case_count,
+        "documents": doc_count,
+        "pending_processing": pending_count,
+        "chunks": chunk_count,
+        "style_corpus_entries": corpus_count,
+        "style_patterns": pattern_count,
+    }, ensure_ascii=False, indent=2)