Merge branch 'feature/store-sha256-checksums' into 'main'

Store SHA256 checksums with artifacts and add multiple hash support

Closes #25

See merge request esv/bsf/bsf-integration/orchard/orchard-mvp!16

CHANGELOG.md

@@ -6,6 +6,14 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## [Unreleased]
+### Added
+- Added integrity verification workflow design document (#24)
+- Added `sha256` field to API responses for clarity (alias of `id`) (#25)
+- Added `checksum_sha1` field to artifacts table for compatibility (#25)
+- Added `s3_etag` field to artifacts table for S3 verification (#25)
+- Compute and store MD5, SHA1, and S3 ETag alongside SHA256 during upload (#25)
+- Added `Dockerfile.local` and `docker-compose.local.yml` for local development (#25)
+- Added migration script `003_checksum_fields.sql` for existing databases (#25)
 
 ## [0.2.0] - 2025-12-15
 ### Changed

Dockerfile.local

@@ -0,0 +1,50 @@
+# Frontend build stage
+FROM node:20-alpine AS frontend-builder
+
+WORKDIR /app/frontend
+
+# Copy package files
+COPY frontend/package*.json ./
+RUN npm install
+
+# Copy frontend source
+COPY frontend/ ./
+
+# Build frontend
+RUN npm run build
+
+# Runtime stage
+FROM python:3.12-slim
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create non-root user
+RUN groupadd -g 1000 orchard && \
+    useradd -u 1000 -g orchard -s /bin/bash -m orchard
+
+WORKDIR /app
+
+# Copy requirements and install Python dependencies
+COPY backend/requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy backend source
+COPY backend/ ./backend/
+
+# Copy frontend build
+COPY --from=frontend-builder /app/frontend/dist ./frontend/dist
+
+# Set ownership
+RUN chown -R orchard:orchard /app
+
+USER orchard
+
+EXPOSE 8080
+
+HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:8080/health || exit 1
+
+CMD ["uvicorn", "backend.app.main:app", "--host", "0.0.0.0", "--port", "8080"]

backend/app/models.py

@@ -74,7 +74,9 @@ class Artifact(Base):
     content_type = Column(String(255))
     original_name = Column(String(1024))
     checksum_md5 = Column(String(32))  # MD5 hash for additional verification
-    metadata = Column(JSON, default=dict)  # Format-specific metadata
+    checksum_sha1 = Column(String(40))  # SHA1 hash for compatibility
+    s3_etag = Column(String(64))  # S3 ETag for verification
+    artifact_metadata = Column("metadata", JSON, default=dict)  # Format-specific metadata (column name is 'metadata')
     created_at = Column(DateTime(timezone=True), default=datetime.utcnow)
     created_by = Column(String(255), nullable=False)
     ref_count = Column(Integer, default=1)
@@ -83,6 +85,21 @@ class Artifact(Base):
     tags = relationship("Tag", back_populates="artifact")
     uploads = relationship("Upload", back_populates="artifact")
 
+    @property
+    def sha256(self) -> str:
+        """Alias for id - the SHA256 hash of the artifact content"""
+        return self.id
+
+    @property
+    def format_metadata(self):
+        """Alias for artifact_metadata - backward compatibility"""
+        return self.artifact_metadata
+
+    @format_metadata.setter
+    def format_metadata(self, value):
+        """Alias setter for artifact_metadata - backward compatibility"""
+        self.artifact_metadata = value
+
     __table_args__ = (
         Index("idx_artifacts_created_at", "created_at"),
         Index("idx_artifacts_created_by", "created_by"),

backend/app/routes.py

@@ -520,40 +520,51 @@ def upload_artifact(
         )
 
     # Store file (uses multipart for large files)
-    sha256_hash, size, s3_key = storage.store(file.file, content_length)
+    storage_result = storage.store(file.file, content_length)
 
     # Check if this is a deduplicated upload
     deduplicated = False
 
     # Create or update artifact record
-    artifact = db.query(Artifact).filter(Artifact.id == sha256_hash).first()
+    artifact = db.query(Artifact).filter(Artifact.id == storage_result.sha256).first()
     if artifact:
         artifact.ref_count += 1
         deduplicated = True
         # Merge metadata if new metadata was extracted
-        if file_metadata and artifact.format_metadata:
-            artifact.format_metadata = {**artifact.format_metadata, **file_metadata}
+        if file_metadata and artifact.artifact_metadata:
+            artifact.artifact_metadata = {**artifact.artifact_metadata, **file_metadata}
         elif file_metadata:
-            artifact.format_metadata = file_metadata
+            artifact.artifact_metadata = file_metadata
+        # Update checksums if not already set
+        if not artifact.checksum_md5 and storage_result.md5:
+            artifact.checksum_md5 = storage_result.md5
+        if not artifact.checksum_sha1 and storage_result.sha1:
+            artifact.checksum_sha1 = storage_result.sha1
+        if not artifact.s3_etag and storage_result.s3_etag:
+            artifact.s3_etag = storage_result.s3_etag
     else:
         artifact = Artifact(
-            id=sha256_hash,
-            size=size,
+            id=storage_result.sha256,
+            size=storage_result.size,
             content_type=file.content_type,
             original_name=file.filename,
+            checksum_md5=storage_result.md5,
+            checksum_sha1=storage_result.sha1,
+            s3_etag=storage_result.s3_etag,
             created_by=user_id,
-            s3_key=s3_key,
-            format_metadata=file_metadata or {},
+            s3_key=storage_result.s3_key,
+            artifact_metadata=file_metadata or {},
         )
         db.add(artifact)
 
     # Record upload
     upload = Upload(
-        artifact_id=sha256_hash,
+        artifact_id=storage_result.sha256,
         package_id=package.id,
         original_name=file.filename,
         uploaded_by=user_id,
         source_ip=request.client.host if request.client else None,
+        deduplicated=deduplicated,
     )
     db.add(upload)
 
@@ -561,13 +572,13 @@ def upload_artifact(
     if tag:
         existing_tag = db.query(Tag).filter(Tag.package_id == package.id, Tag.name == tag).first()
         if existing_tag:
-            existing_tag.artifact_id = sha256_hash
+            existing_tag.artifact_id = storage_result.sha256
             existing_tag.created_by = user_id
         else:
             new_tag = Tag(
                 package_id=package.id,
                 name=tag,
-                artifact_id=sha256_hash,
+                artifact_id=storage_result.sha256,
                 created_by=user_id,
             )
             db.add(new_tag)
@@ -575,12 +586,16 @@ def upload_artifact(
     db.commit()
 
     return UploadResponse(
-        artifact_id=sha256_hash,
-        size=size,
+        artifact_id=storage_result.sha256,
+        sha256=storage_result.sha256,
+        size=storage_result.size,
         project=project_name,
         package=package_name,
         tag=tag,
-        format_metadata=artifact.format_metadata,
+        checksum_md5=storage_result.md5,
+        checksum_sha1=storage_result.sha1,
+        s3_etag=storage_result.s3_etag,
+        format_metadata=artifact.artifact_metadata,
         deduplicated=deduplicated,
     )
 

backend/app/schemas.py

@@ -99,9 +99,13 @@ class PackageDetailResponse(BaseModel):
 # Artifact schemas
 class ArtifactResponse(BaseModel):
     id: str
+    sha256: str  # Explicit SHA256 field (same as id)
     size: int
     content_type: Optional[str]
     original_name: Optional[str]
+    checksum_md5: Optional[str] = None
+    checksum_sha1: Optional[str] = None
+    s3_etag: Optional[str] = None
     created_at: datetime
     created_by: str
     ref_count: int
@@ -173,9 +177,13 @@ class ArtifactTagInfo(BaseModel):
 class ArtifactDetailResponse(BaseModel):
     """Artifact with list of tags/packages referencing it"""
     id: str
+    sha256: str  # Explicit SHA256 field (same as id)
     size: int
     content_type: Optional[str]
     original_name: Optional[str]
+    checksum_md5: Optional[str] = None
+    checksum_sha1: Optional[str] = None
+    s3_etag: Optional[str] = None
     created_at: datetime
     created_by: str
     ref_count: int
@@ -189,9 +197,13 @@ class ArtifactDetailResponse(BaseModel):
 class PackageArtifactResponse(BaseModel):
     """Artifact with tags for package artifact listing"""
     id: str
+    sha256: str  # Explicit SHA256 field (same as id)
     size: int
     content_type: Optional[str]
     original_name: Optional[str]
+    checksum_md5: Optional[str] = None
+    checksum_sha1: Optional[str] = None
+    s3_etag: Optional[str] = None
     created_at: datetime
     created_by: str
     format_metadata: Optional[Dict[str, Any]] = None
@@ -204,10 +216,14 @@ class PackageArtifactResponse(BaseModel):
 # Upload response
 class UploadResponse(BaseModel):
     artifact_id: str
+    sha256: str  # Explicit SHA256 field (same as artifact_id)
     size: int
     project: str
     package: str
     tag: Optional[str]
+    checksum_md5: Optional[str] = None
+    checksum_sha1: Optional[str] = None
+    s3_etag: Optional[str] = None
     format_metadata: Optional[Dict[str, Any]] = None
     deduplicated: bool = False
 

backend/app/storage.py

@@ -1,6 +1,6 @@
 import hashlib
 import logging
-from typing import BinaryIO, Tuple, Optional, Dict, Any, Generator
+from typing import BinaryIO, Tuple, Optional, Dict, Any, Generator, NamedTuple
 import boto3
 from botocore.config import Config
 from botocore.exceptions import ClientError
@@ -18,6 +18,16 @@ MULTIPART_CHUNK_SIZE = 10 * 1024 * 1024
 HASH_CHUNK_SIZE = 8 * 1024 * 1024
 
 
+class StorageResult(NamedTuple):
+    """Result of storing a file with all computed checksums"""
+    sha256: str
+    size: int
+    s3_key: str
+    md5: Optional[str] = None
+    sha1: Optional[str] = None
+    s3_etag: Optional[str] = None
+
+
 class S3Storage:
     def __init__(self):
         config = Config(s3={"addressing_style": "path"} if settings.s3_use_path_style else {})
@@ -34,9 +44,9 @@ class S3Storage:
         # Store active multipart uploads for resumable support
         self._active_uploads: Dict[str, Dict[str, Any]] = {}
 
-    def store(self, file: BinaryIO, content_length: Optional[int] = None) -> Tuple[str, int, str]:
+    def store(self, file: BinaryIO, content_length: Optional[int] = None) -> StorageResult:
         """
-        Store a file and return its SHA256 hash, size, and s3_key.
+        Store a file and return StorageResult with all checksums.
         Content-addressable: if the file already exists, just return the hash.
         Uses multipart upload for files larger than MULTIPART_THRESHOLD.
         """
@@ -46,45 +56,76 @@ class S3Storage:
         else:
             return self._store_multipart(file, content_length)
 
-    def _store_simple(self, file: BinaryIO) -> Tuple[str, int, str]:
+    def _store_simple(self, file: BinaryIO) -> StorageResult:
         """Store a small file using simple put_object"""
-        # Read file and compute hash
+        # Read file and compute all hashes
         content = file.read()
         sha256_hash = hashlib.sha256(content).hexdigest()
+        md5_hash = hashlib.md5(content).hexdigest()
+        sha1_hash = hashlib.sha1(content).hexdigest()
         size = len(content)
 
         # Check if already exists
         s3_key = f"fruits/{sha256_hash[:2]}/{sha256_hash[2:4]}/{sha256_hash}"
+        s3_etag = None
 
         if not self._exists(s3_key):
-            self.client.put_object(
+            response = self.client.put_object(
                 Bucket=self.bucket,
                 Key=s3_key,
                 Body=content,
             )
+            s3_etag = response.get("ETag", "").strip('"')
+        else:
+            # Get existing ETag
+            obj_info = self.get_object_info(s3_key)
+            if obj_info:
+                s3_etag = obj_info.get("etag", "").strip('"')
 
-        return sha256_hash, size, s3_key
+        return StorageResult(
+            sha256=sha256_hash,
+            size=size,
+            s3_key=s3_key,
+            md5=md5_hash,
+            sha1=sha1_hash,
+            s3_etag=s3_etag,
+        )
 
-    def _store_multipart(self, file: BinaryIO, content_length: int) -> Tuple[str, int, str]:
+    def _store_multipart(self, file: BinaryIO, content_length: int) -> StorageResult:
         """Store a large file using S3 multipart upload with streaming hash computation"""
-        # First pass: compute hash by streaming through file
-        hasher = hashlib.sha256()
+        # First pass: compute all hashes by streaming through file
+        sha256_hasher = hashlib.sha256()
+        md5_hasher = hashlib.md5()
+        sha1_hasher = hashlib.sha1()
         size = 0
 
-        # Read file in chunks to compute hash
+        # Read file in chunks to compute hashes
         while True:
             chunk = file.read(HASH_CHUNK_SIZE)
             if not chunk:
                 break
-            hasher.update(chunk)
+            sha256_hasher.update(chunk)
+            md5_hasher.update(chunk)
+            sha1_hasher.update(chunk)
             size += len(chunk)
 
-        sha256_hash = hasher.hexdigest()
+        sha256_hash = sha256_hasher.hexdigest()
+        md5_hash = md5_hasher.hexdigest()
+        sha1_hash = sha1_hasher.hexdigest()
         s3_key = f"fruits/{sha256_hash[:2]}/{sha256_hash[2:4]}/{sha256_hash}"
 
         # Check if already exists (deduplication)
         if self._exists(s3_key):
-            return sha256_hash, size, s3_key
+            obj_info = self.get_object_info(s3_key)
+            s3_etag = obj_info.get("etag", "").strip('"') if obj_info else None
+            return StorageResult(
+                sha256=sha256_hash,
+                size=size,
+                s3_key=s3_key,
+                md5=md5_hash,
+                sha1=sha1_hash,
+                s3_etag=s3_etag,
+            )
 
         # Seek back to start for upload
         file.seek(0)
@@ -116,14 +157,22 @@ class S3Storage:
                 part_number += 1
 
             # Complete multipart upload
-            self.client.complete_multipart_upload(
+            complete_response = self.client.complete_multipart_upload(
                 Bucket=self.bucket,
                 Key=s3_key,
                 UploadId=upload_id,
                 MultipartUpload={"Parts": parts},
             )
+            s3_etag = complete_response.get("ETag", "").strip('"')
 
-            return sha256_hash, size, s3_key
+            return StorageResult(
+                sha256=sha256_hash,
+                size=size,
+                s3_key=s3_key,
+                md5=md5_hash,
+                sha1=sha1_hash,
+                s3_etag=s3_etag,
+            )
 
         except Exception as e:
             # Abort multipart upload on failure
@@ -135,33 +184,50 @@ class S3Storage:
             )
             raise
 
-    def store_streaming(self, chunks: Generator[bytes, None, None]) -> Tuple[str, int, str]:
+    def store_streaming(self, chunks: Generator[bytes, None, None]) -> StorageResult:
         """
         Store a file from a stream of chunks.
         First accumulates to compute hash, then uploads.
         For truly large files, consider using initiate_resumable_upload instead.
         """
-        # Accumulate chunks and compute hash
-        hasher = hashlib.sha256()
+        # Accumulate chunks and compute all hashes
+        sha256_hasher = hashlib.sha256()
+        md5_hasher = hashlib.md5()
+        sha1_hasher = hashlib.sha1()
         all_chunks = []
         size = 0
 
         for chunk in chunks:
-            hasher.update(chunk)
+            sha256_hasher.update(chunk)
+            md5_hasher.update(chunk)
+            sha1_hasher.update(chunk)
             all_chunks.append(chunk)
             size += len(chunk)
 
-        sha256_hash = hasher.hexdigest()
+        sha256_hash = sha256_hasher.hexdigest()
+        md5_hash = md5_hasher.hexdigest()
+        sha1_hash = sha1_hasher.hexdigest()
         s3_key = f"fruits/{sha256_hash[:2]}/{sha256_hash[2:4]}/{sha256_hash}"
+        s3_etag = None
 
         # Check if already exists
         if self._exists(s3_key):
-            return sha256_hash, size, s3_key
+            obj_info = self.get_object_info(s3_key)
+            s3_etag = obj_info.get("etag", "").strip('"') if obj_info else None
+            return StorageResult(
+                sha256=sha256_hash,
+                size=size,
+                s3_key=s3_key,
+                md5=md5_hash,
+                sha1=sha1_hash,
+                s3_etag=s3_etag,
+            )
 
         # Upload based on size
         if size < MULTIPART_THRESHOLD:
             content = b"".join(all_chunks)
-            self.client.put_object(Bucket=self.bucket, Key=s3_key, Body=content)
+            response = self.client.put_object(Bucket=self.bucket, Key=s3_key, Body=content)
+            s3_etag = response.get("ETag", "").strip('"')
         else:
             # Use multipart for large files
             mpu = self.client.create_multipart_upload(Bucket=self.bucket, Key=s3_key)
@@ -205,12 +271,13 @@ class S3Storage:
                         "ETag": response["ETag"],
                     })
 
-                self.client.complete_multipart_upload(
+                complete_response = self.client.complete_multipart_upload(
                     Bucket=self.bucket,
                     Key=s3_key,
                     UploadId=upload_id,
                     MultipartUpload={"Parts": parts},
                 )
+                s3_etag = complete_response.get("ETag", "").strip('"')
 
             except Exception as e:
                 logger.error(f"Streaming multipart upload failed: {e}")
@@ -221,7 +288,14 @@ class S3Storage:
                 )
                 raise
 
-        return sha256_hash, size, s3_key
+        return StorageResult(
+            sha256=sha256_hash,
+            size=size,
+            s3_key=s3_key,
+            md5=md5_hash,
+            sha1=sha1_hash,
+            s3_etag=s3_etag,
+        )
 
     def initiate_resumable_upload(self, expected_hash: str) -> Dict[str, Any]:
         """

docker-compose.local.yml

@@ -0,0 +1,122 @@
+version: '3.8'
+
+services:
+  orchard-server:
+    build:
+      context: .
+      dockerfile: Dockerfile.local
+    ports:
+      - "8080:8080"
+    environment:
+      - ORCHARD_SERVER_HOST=0.0.0.0
+      - ORCHARD_SERVER_PORT=8080
+      - ORCHARD_DATABASE_HOST=postgres
+      - ORCHARD_DATABASE_PORT=5432
+      - ORCHARD_DATABASE_USER=orchard
+      - ORCHARD_DATABASE_PASSWORD=orchard_secret
+      - ORCHARD_DATABASE_DBNAME=orchard
+      - ORCHARD_DATABASE_SSLMODE=disable
+      - ORCHARD_S3_ENDPOINT=http://minio:9000
+      - ORCHARD_S3_REGION=us-east-1
+      - ORCHARD_S3_BUCKET=orchard-artifacts
+      - ORCHARD_S3_ACCESS_KEY_ID=minioadmin
+      - ORCHARD_S3_SECRET_ACCESS_KEY=minioadmin
+      - ORCHARD_S3_USE_PATH_STYLE=true
+      - ORCHARD_REDIS_HOST=redis
+      - ORCHARD_REDIS_PORT=6379
+    depends_on:
+      postgres:
+        condition: service_healthy
+      minio:
+        condition: service_healthy
+      redis:
+        condition: service_healthy
+    networks:
+      - orchard-network
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
+      interval: 30s
+      timeout: 3s
+      start_period: 10s
+      retries: 3
+
+  postgres:
+    image: postgres:16-alpine
+    environment:
+      - POSTGRES_USER=orchard
+      - POSTGRES_PASSWORD=orchard_secret
+      - POSTGRES_DB=orchard
+    volumes:
+      - postgres-data-local:/var/lib/postgresql/data
+      - ./migrations:/docker-entrypoint-initdb.d:ro
+    ports:
+      - "5432:5432"
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U orchard -d orchard"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    networks:
+      - orchard-network
+    restart: unless-stopped
+
+  minio:
+    image: minio/minio:latest
+    command: server /data --console-address ":9001"
+    environment:
+      - MINIO_ROOT_USER=minioadmin
+      - MINIO_ROOT_PASSWORD=minioadmin
+    volumes:
+      - minio-data-local:/data
+    ports:
+      - "9000:9000"
+      - "9001:9001"
+    healthcheck:
+      test: ["CMD", "mc", "ready", "local"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    networks:
+      - orchard-network
+    restart: unless-stopped
+
+  minio-init:
+    image: minio/mc:latest
+    depends_on:
+      minio:
+        condition: service_healthy
+    entrypoint: >
+      /bin/sh -c "
+      mc alias set myminio http://minio:9000 minioadmin minioadmin;
+      mc mb myminio/orchard-artifacts --ignore-existing;
+      mc anonymous set download myminio/orchard-artifacts;
+      exit 0;
+      "
+    networks:
+      - orchard-network
+
+  redis:
+    image: redis:7-alpine
+    command: redis-server --appendonly yes
+    volumes:
+      - redis-data-local:/data
+    ports:
+      - "6379:6379"
+    healthcheck:
+      test: ["CMD", "redis-cli", "ping"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    networks:
+      - orchard-network
+    restart: unless-stopped
+
+volumes:
+  postgres-data-local:
+  minio-data-local:
+  redis-data-local:
+
+networks:
+  orchard-network:
+    driver: bridge

docs/design/integrity-verification.md

@@ -0,0 +1,504 @@
+# Integrity Verification Workflow Design
+
+This document defines the process for SHA256 checksum verification on artifact downloads, including failure handling and retry mechanisms.
+
+## Overview
+
+Orchard uses content-addressable storage where the artifact ID is the SHA256 hash of the content. This design leverages that property to provide configurable integrity verification during downloads.
+
+## Current State
+
+| Aspect | Status |
+|--------|--------|
+| Download streams content directly from S3 | ✅ Implemented |
+| Artifact ID is the SHA256 hash | ✅ Implemented |
+| S3 key derived from SHA256 hash | ✅ Implemented |
+| Verification during download | ❌ Not implemented |
+| Checksum headers in response | ❌ Not implemented |
+| Retry mechanism on failure | ❌ Not implemented |
+| Failure handling beyond S3 errors | ❌ Not implemented |
+
+## Verification Modes
+
+The verification mode is selected via query parameter `?verify=<mode>` or server-wide default via `ORCHARD_VERIFY_MODE`.
+
+| Mode | Performance | Integrity | Use Case |
+|------|-------------|-----------|----------|
+| `none` | ⚡ Fastest | Client-side | Trusted networks, high throughput |
+| `header` | ⚡ Fast | Client-side | Standard downloads, client verification |
+| `stream` | 🔄 Moderate | Post-hoc server | Logging/auditing, non-blocking |
+| `pre` | 🐢 Slower | Guaranteed | Critical downloads, untrusted storage |
+| `strict` | 🐢 Slower | Guaranteed + Alert | Security-sensitive, compliance |
+
+### Mode: None (Default)
+
+**Behavior:**
+- Stream content directly from S3 with no server-side processing
+- Maximum download performance
+- Client is responsible for verification
+
+**Headers Returned:**
+```
+X-Checksum-SHA256: <expected_hash>
+Content-Length: <expected_size>
+```
+
+**Flow:**
+```
+Client Request → Lookup Artifact → Stream from S3 → Client
+```
+
+### Mode: Header
+
+**Behavior:**
+- Stream content directly from S3
+- Include comprehensive checksum headers
+- Client performs verification using headers
+
+**Headers Returned:**
+```
+X-Checksum-SHA256: <expected_hash>
+Content-Length: <expected_size>
+Digest: sha-256=<base64_encoded_hash>
+ETag: "<sha256_hash>"
+X-Content-SHA256: <expected_hash>
+```
+
+**Flow:**
+```
+Client Request → Lookup Artifact → Add Headers → Stream from S3 → Client Verifies
+```
+
+**Client Verification Example:**
+```bash
+# Download and verify
+curl -OJ https://orchard/project/foo/bar/+/v1.0.0
+EXPECTED=$(curl -sI https://orchard/project/foo/bar/+/v1.0.0 | grep X-Checksum-SHA256 | cut -d' ' -f2)
+ACTUAL=$(sha256sum downloaded_file | cut -d' ' -f1)
+[ "$EXPECTED" = "$ACTUAL" ] && echo "OK" || echo "MISMATCH"
+```
+
+### Mode: Stream (Post-Hoc Verification)
+
+**Behavior:**
+- Wrap S3 stream with `HashingStreamWrapper`
+- Compute SHA256 incrementally while streaming to client
+- Verify hash after stream completes
+- Log verification result
+- Cannot reject content (already sent to client)
+
+**Headers Returned:**
+```
+X-Checksum-SHA256: <expected_hash>
+Content-Length: <expected_size>
+X-Verify-Mode: stream
+Trailer: X-Verified
+```
+
+**Trailers (if client supports):**
+```
+X-Verified: true|false
+X-Computed-SHA256: <computed_hash>
+```
+
+**Flow:**
+```
+Client Request → Lookup Artifact → Wrap Stream → Stream to Client
+                                       ↓
+                              Compute Hash Incrementally
+                                       ↓
+                              Verify After Complete → Log Result
+```
+
+**Implementation:**
+```python
+class HashingStreamWrapper:
+    def __init__(self, stream, expected_hash: str, on_complete: Callable):
+        self.stream = stream
+        self.hasher = hashlib.sha256()
+        self.expected_hash = expected_hash
+        self.on_complete = on_complete
+
+    def __iter__(self):
+        for chunk in self.stream:
+            self.hasher.update(chunk)
+            yield chunk
+        # Stream complete, verify
+        computed = self.hasher.hexdigest()
+        self.on_complete(computed == self.expected_hash, computed)
+```
+
+### Mode: Pre-Verify (Blocking)
+
+**Behavior:**
+- Download entire content from S3 to memory/temp file
+- Compute SHA256 hash before sending to client
+- On match: stream verified content to client
+- On mismatch: retry from S3 (up to N times)
+- If retries exhausted: return 500 error
+
+**Headers Returned:**
+```
+X-Checksum-SHA256: <expected_hash>
+Content-Length: <expected_size>
+X-Verify-Mode: pre
+X-Verified: true
+```
+
+**Flow:**
+```
+Client Request → Lookup Artifact → Download from S3 → Compute Hash
+                                                          ↓
+                                                    Hash Matches?
+                                                    ↓           ↓
+                                                   Yes          No
+                                                    ↓           ↓
+                                            Stream to Client   Retry?
+                                                                ↓
+                                                          Yes → Loop
+                                                          No  → 500 Error
+```
+
+**Memory Considerations:**
+- For files < `ORCHARD_VERIFY_MEMORY_LIMIT` (default 100MB): buffer in memory
+- For larger files: use temporary file with streaming hash computation
+- Cleanup temp files after response sent
+
+### Mode: Strict
+
+**Behavior:**
+- Same as pre-verify but with no retries
+- Fail immediately on any mismatch
+- Quarantine artifact on failure (mark as potentially corrupted)
+- Trigger alert/notification on failure
+- For security-critical downloads
+
+**Headers Returned (on success):**
+```
+X-Checksum-SHA256: <expected_hash>
+Content-Length: <expected_size>
+X-Verify-Mode: strict
+X-Verified: true
+```
+
+**Error Response (on failure):**
+```json
+{
+  "error": "integrity_verification_failed",
+  "message": "Artifact content does not match expected checksum",
+  "expected_hash": "<expected>",
+  "computed_hash": "<computed>",
+  "artifact_id": "<id>",
+  "action_taken": "quarantined"
+}
+```
+
+**Quarantine Process:**
+1. Mark artifact `status = 'quarantined'` in database
+2. Log security event to audit_logs
+3. Optionally notify via webhook/email
+4. Artifact becomes unavailable for download until resolved
+
+## Failure Detection
+
+### Failure Types
+
+| Failure Type | Detection Method | Severity |
+|--------------|------------------|----------|
+| Hash mismatch | Computed SHA256 ≠ Expected | Critical |
+| Size mismatch | Actual bytes ≠ `Content-Length` | High |
+| S3 read error | boto3 exception | Medium |
+| Truncated content | Stream ends early | High |
+| S3 object missing | `NoSuchKey` error | Critical |
+| ETag mismatch | S3 ETag ≠ expected | Medium |
+
+### Detection Implementation
+
+```python
+class VerificationResult:
+    success: bool
+    failure_type: Optional[str]  # hash_mismatch, size_mismatch, etc.
+    expected_hash: str
+    computed_hash: Optional[str]
+    expected_size: int
+    actual_size: Optional[int]
+    error_message: Optional[str]
+    retry_count: int
+```
+
+## Retry Mechanism
+
+### Configuration
+
+| Environment Variable | Default | Description |
+|---------------------|---------|-------------|
+| `ORCHARD_VERIFY_MAX_RETRIES` | 3 | Maximum retry attempts |
+| `ORCHARD_VERIFY_RETRY_DELAY_MS` | 100 | Base delay between retries |
+| `ORCHARD_VERIFY_RETRY_BACKOFF` | 2.0 | Exponential backoff multiplier |
+| `ORCHARD_VERIFY_RETRY_MAX_DELAY_MS` | 5000 | Maximum delay cap |
+
+### Backoff Formula
+
+```
+delay = min(base_delay * (backoff ^ attempt), max_delay)
+```
+
+Example with defaults:
+- Attempt 1: 100ms
+- Attempt 2: 200ms
+- Attempt 3: 400ms
+
+### Retry Flow
+
+```python
+async def download_with_retry(artifact, max_retries=3):
+    for attempt in range(max_retries + 1):
+        try:
+            content = await fetch_from_s3(artifact.s3_key)
+            computed_hash = compute_sha256(content)
+
+            if computed_hash == artifact.id:
+                return content  # Success
+
+            # Hash mismatch
+            log.warning(f"Verification failed, attempt {attempt + 1}/{max_retries + 1}")
+
+            if attempt < max_retries:
+                delay = calculate_backoff(attempt)
+                await asyncio.sleep(delay / 1000)
+            else:
+                raise IntegrityError("Max retries exceeded")
+
+        except S3Error as e:
+            if attempt < max_retries:
+                delay = calculate_backoff(attempt)
+                await asyncio.sleep(delay / 1000)
+            else:
+                raise
+```
+
+### Retryable vs Non-Retryable Failures
+
+**Retryable:**
+- S3 read timeout
+- S3 connection error
+- Hash mismatch (may be transient S3 issue)
+- Truncated content
+
+**Non-Retryable:**
+- S3 object not found (404)
+- S3 access denied (403)
+- Artifact not in database
+- Strict mode failures
+
+## Configuration Reference
+
+### Environment Variables
+
+```bash
+# Verification mode (none, header, stream, pre, strict)
+ORCHARD_VERIFY_MODE=none
+
+# Retry settings
+ORCHARD_VERIFY_MAX_RETRIES=3
+ORCHARD_VERIFY_RETRY_DELAY_MS=100
+ORCHARD_VERIFY_RETRY_BACKOFF=2.0
+ORCHARD_VERIFY_RETRY_MAX_DELAY_MS=5000
+
+# Memory limit for pre-verify buffering (bytes)
+ORCHARD_VERIFY_MEMORY_LIMIT=104857600  # 100MB
+
+# Strict mode settings
+ORCHARD_VERIFY_QUARANTINE_ON_FAILURE=true
+ORCHARD_VERIFY_ALERT_WEBHOOK=https://alerts.example.com/webhook
+
+# Allow per-request mode override
+ORCHARD_VERIFY_ALLOW_OVERRIDE=true
+```
+
+### Per-Request Override
+
+When `ORCHARD_VERIFY_ALLOW_OVERRIDE=true`, clients can specify verification mode:
+
+```
+GET /api/v1/project/foo/bar/+/v1.0.0?verify=pre
+GET /api/v1/project/foo/bar/+/v1.0.0?verify=none
+```
+
+## API Changes
+
+### Download Endpoint
+
+**Request:**
+```
+GET /api/v1/project/{project}/{package}/+/{ref}?verify={mode}
+```
+
+**New Query Parameters:**
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `verify` | string | from config | Verification mode |
+
+**New Response Headers:**
+| Header | Description |
+|--------|-------------|
+| `X-Checksum-SHA256` | Expected SHA256 hash |
+| `X-Verify-Mode` | Active verification mode |
+| `X-Verified` | `true` if server verified content |
+| `Digest` | RFC 3230 digest header |
+
+### New Endpoint: Verify Artifact
+
+**Request:**
+```
+POST /api/v1/project/{project}/{package}/+/{ref}/verify
+```
+
+**Response:**
+```json
+{
+  "artifact_id": "abc123...",
+  "verified": true,
+  "expected_hash": "abc123...",
+  "computed_hash": "abc123...",
+  "size_match": true,
+  "expected_size": 1048576,
+  "actual_size": 1048576,
+  "verification_time_ms": 45
+}
+```
+
+## Logging and Monitoring
+
+### Log Events
+
+| Event | Level | When |
+|-------|-------|------|
+| `verification.success` | INFO | Hash verified successfully |
+| `verification.failure` | ERROR | Hash mismatch detected |
+| `verification.retry` | WARN | Retry attempt initiated |
+| `verification.quarantine` | ERROR | Artifact quarantined |
+| `verification.skip` | DEBUG | Verification skipped (mode=none) |
+
+### Metrics
+
+| Metric | Type | Description |
+|--------|------|-------------|
+| `orchard_verification_total` | Counter | Total verification attempts |
+| `orchard_verification_failures` | Counter | Failed verifications |
+| `orchard_verification_retries` | Counter | Retry attempts |
+| `orchard_verification_duration_ms` | Histogram | Verification time |
+
+### Audit Log Entry
+
+```json
+{
+  "action": "artifact.download.verified",
+  "resource": "project/foo/package/bar/artifact/abc123",
+  "user_id": "user@example.com",
+  "details": {
+    "verification_mode": "pre",
+    "verified": true,
+    "retry_count": 0,
+    "duration_ms": 45
+  }
+}
+```
+
+## Security Considerations
+
+1. **Strict Mode for Sensitive Data**: Use strict mode for artifacts containing credentials, certificates, or security-critical code.
+
+2. **Quarantine Isolation**: Quarantined artifacts should be moved to a separate S3 prefix or bucket for forensic analysis.
+
+3. **Alert on Repeated Failures**: Multiple verification failures for the same artifact may indicate storage corruption or tampering.
+
+4. **Audit Trail**: All verification events should be logged for compliance and forensic purposes.
+
+5. **Client Trust**: In `none` and `header` modes, clients must implement their own verification for security guarantees.
+
+## Implementation Phases
+
+### Phase 1: Headers Only
+- Add `X-Checksum-SHA256` header to all downloads
+- Add `verify=header` mode support
+- Add configuration options
+
+### Phase 2: Stream Verification
+- Implement `HashingStreamWrapper`
+- Add `verify=stream` mode
+- Add verification logging
+
+### Phase 3: Pre-Verification
+- Implement buffered verification
+- Add retry mechanism
+- Add `verify=pre` mode
+
+### Phase 4: Strict Mode
+- Implement quarantine mechanism
+- Add alerting integration
+- Add `verify=strict` mode
+
+## Client Integration Examples
+
+### curl with Verification
+```bash
+#!/bin/bash
+URL="https://orchard.example.com/api/v1/project/myproject/mypackage/+/v1.0.0"
+
+# Get expected hash from headers
+EXPECTED=$(curl -sI "$URL" | grep -i "X-Checksum-SHA256" | tr -d '\r' | cut -d' ' -f2)
+
+# Download file
+curl -sO "$URL"
+FILENAME=$(basename "$URL")
+
+# Verify
+ACTUAL=$(sha256sum "$FILENAME" | cut -d' ' -f1)
+
+if [ "$EXPECTED" = "$ACTUAL" ]; then
+    echo "✓ Verification passed"
+else
+    echo "✗ Verification FAILED"
+    echo "  Expected: $EXPECTED"
+    echo "  Actual:   $ACTUAL"
+    exit 1
+fi
+```
+
+### Python Client
+```python
+import hashlib
+import requests
+
+def download_verified(url: str) -> bytes:
+    # Get headers first
+    head = requests.head(url)
+    expected_hash = head.headers.get('X-Checksum-SHA256')
+    expected_size = int(head.headers.get('Content-Length', 0))
+
+    # Download content
+    response = requests.get(url)
+    content = response.content
+
+    # Verify size
+    if len(content) != expected_size:
+        raise ValueError(f"Size mismatch: {len(content)} != {expected_size}")
+
+    # Verify hash
+    actual_hash = hashlib.sha256(content).hexdigest()
+    if actual_hash != expected_hash:
+        raise ValueError(f"Hash mismatch: {actual_hash} != {expected_hash}")
+
+    return content
+```
+
+### Server-Side Verification
+```bash
+# Force server to verify before sending
+curl -O "https://orchard.example.com/api/v1/project/myproject/mypackage/+/v1.0.0?verify=pre"
+
+# Check if verification was performed
+curl -I "https://orchard.example.com/api/v1/project/myproject/mypackage/+/v1.0.0?verify=pre" | grep X-Verified
+# X-Verified: true
+```

migrations/001_initial.sql

@@ -41,6 +41,8 @@ CREATE TABLE IF NOT EXISTS artifacts (
     content_type VARCHAR(255),
     original_name VARCHAR(1024),
     checksum_md5 VARCHAR(32),    -- MD5 hash for additional verification
+    checksum_sha1 VARCHAR(40),   -- SHA1 hash for compatibility
+    s3_etag VARCHAR(64),         -- S3 ETag for verification
     metadata JSONB,              -- format-specific metadata
     created_at TIMESTAMP WITH TIME ZONE DEFAULT NOW(),
     created_by VARCHAR(255) NOT NULL,
@@ -51,6 +53,8 @@ CREATE TABLE IF NOT EXISTS artifacts (
 CREATE INDEX idx_artifacts_created_at ON artifacts(created_at);
 CREATE INDEX idx_artifacts_created_by ON artifacts(created_by);
 CREATE INDEX idx_artifacts_metadata ON artifacts USING GIN (metadata);
+CREATE INDEX idx_artifacts_checksum_md5 ON artifacts(checksum_md5) WHERE checksum_md5 IS NOT NULL;
+CREATE INDEX idx_artifacts_checksum_sha1 ON artifacts(checksum_sha1) WHERE checksum_sha1 IS NOT NULL;
 
 -- Tags (Aliases pointing to artifacts)
 CREATE TABLE IF NOT EXISTS tags (

migrations/003_checksum_fields.sql

@@ -0,0 +1,12 @@
+-- Migration 003: Additional Checksum Fields
+-- Adds checksum_sha1 and s3_etag fields to artifacts table
+
+-- ============================================
+-- Artifacts: Add checksum_sha1 and s3_etag fields
+-- ============================================
+ALTER TABLE artifacts ADD COLUMN IF NOT EXISTS checksum_sha1 VARCHAR(40);
+ALTER TABLE artifacts ADD COLUMN IF NOT EXISTS s3_etag VARCHAR(64);
+
+-- Create indexes for checksum lookups (optional, for verification queries)
+CREATE INDEX IF NOT EXISTS idx_artifacts_checksum_md5 ON artifacts(checksum_md5) WHERE checksum_md5 IS NOT NULL;
+CREATE INDEX IF NOT EXISTS idx_artifacts_checksum_sha1 ON artifacts(checksum_sha1) WHERE checksum_sha1 IS NOT NULL;