Phase 1 MVP: synchronous OCR + regex header extraction

Implements the foundation of the OCR Sprint service:
- FastAPI app with /api/v1/health and /api/v1/documents (sync upload)
- Pydantic v2 schemas for documents, extraction result, personnel
- Pipeline: PDF/image ingest (PyMuPDF), preprocessing (resize, deskew,
  denoise, optional adaptive threshold), PaddleOCR wrapper, regex-based
  header extraction (nomor sprint, tanggal, satuan, perihal, dasar),
  signatory NRP, master-pangkat validation, confidence scoring + routing.
- Tests: 61 unit tests covering regex rules, validators, preprocess,
  ingest, confidence, and API contract (PaddleOCR mocked).
- Tooling: pyproject (setuptools), ruff, mypy strict, pytest, pre-commit,
  Dockerfile, docker-compose, Makefile.
- Docs: README + docs/architecture.md (full hybrid stack rationale and
  6-phase roadmap).

Co-authored-by: adrian kuman firmansah <adriancuman@gmail.com>

src/ocr_sprint/schemas/document.py

@@ -0,0 +1,57 @@
+"""Job-level schemas (request, response, status)."""
+
+from __future__ import annotations
+
+from datetime import datetime
+from enum import Enum
+from typing import Any
+from uuid import UUID, uuid4
+
+from pydantic import BaseModel, ConfigDict, Field
+
+from ocr_sprint.schemas.extraction import ExtractionResult
+
+
+class SourceKind(str, Enum):
+    """High-level type of the uploaded document."""
+
+    PDF = "pdf"
+    IMAGE = "image"
+    UNKNOWN = "unknown"
+
+
+class DocumentStatus(str, Enum):
+    """Lifecycle status of an OCR job."""
+
+    PENDING = "pending"
+    PROCESSING = "processing"
+    COMPLETED = "completed"
+    NEEDS_REVIEW = "needs_review"
+    FAILED = "failed"
+
+
+class DocumentJob(BaseModel):
+    """Internal representation of a job (Phase 1 holds it in-memory)."""
+
+    model_config = ConfigDict(use_enum_values=False)
+
+    job_id: UUID = Field(default_factory=uuid4)
+    source_kind: SourceKind = SourceKind.UNKNOWN
+    filename: str
+    status: DocumentStatus = DocumentStatus.PENDING
+    created_at: datetime = Field(default_factory=lambda: datetime.utcnow())
+    updated_at: datetime = Field(default_factory=lambda: datetime.utcnow())
+    error: str | None = None
+    result: ExtractionResult | None = None
+    debug: dict[str, Any] = Field(default_factory=dict)
+
+
+class DocumentResponse(BaseModel):
+    """Public response payload returned by the documents API."""
+
+    job_id: UUID
+    status: DocumentStatus
+    confidence: float | None = None
+    data: ExtractionResult | None = None
+    review_flags: list[str] = Field(default_factory=list)
+    error: str | None = None