fix: Prevent binary file data loss on storage failure

- Log at WARNING level instead of DEBUG
- Fall back to storing data URI in content field for binary files
  if workspace storage fails, preventing permanent data loss

.devcontainer/platform/README.md

@@ -1,206 +0,0 @@
-# GitHub Codespaces for AutoGPT Platform
-
-This dev container provides a complete development environment for the AutoGPT Platform, optimized for PR reviews.
-
-## 🚀 Quick Start
-
-1. **Open in Codespaces:**
-   - Go to the repository on GitHub
-   - Click **Code** → **Codespaces** → **Create codespace on dev**
-   - Or click the badge: [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/Significant-Gravitas/AutoGPT?quickstart=1)
-
-2. **Wait for setup** (~60 seconds with prebuild, ~5-10 min without)
-
-3. **Start the servers:**
-   ```bash
-   # Terminal 1
-   make run-backend
-
-   # Terminal 2  
-   make run-frontend
-   ```
-
-4. **Start developing!**
-   - Frontend: `http://localhost:3000`
-   - Login with: `test123@gmail.com` / `testpassword123`
-
-## 🏗️ Architecture
-
-**Dependencies run in Docker** (cached by prebuild):
-- PostgreSQL, Redis, RabbitMQ, Supabase Auth
-
-**Backend & Frontend run natively** (not cached):
-- This ensures you're always running the current branch's code
-- Enables hot-reload during development
-- VS Code debugger can attach directly
-
-## 📍 Available Services
-
-| Service | URL | Notes |
-|---------|-----|-------|
-| Frontend | http://localhost:3000 | Next.js app |
-| REST API | http://localhost:8006 | FastAPI backend |
-| WebSocket | ws://localhost:8001 | Real-time updates |
-| Supabase | http://localhost:8000 | Auth & API gateway |
-| Supabase Studio | http://localhost:5555 | Database admin |
-| RabbitMQ | http://localhost:15672 | Queue management |
-
-## 🔑 Test Accounts
-
-| Email | Password | Role |
-|-------|----------|------|
-| test123@gmail.com | testpassword123 | Featured Creator |
-
-The test account has:
-- Pre-created agents and workflows
-- Published store listings
-- Active agent executions
-- Reviews and ratings
-
-## 🛠️ Development Commands
-
-```bash
-# Navigate to platform directory (terminal starts here by default)
-cd autogpt_platform
-
-# Start all services
-docker compose up -d
-
-# Or just core services (DB, Redis, RabbitMQ)
-make start-core
-
-# Run backend in dev mode (hot reload)
-make run-backend
-
-# Run frontend in dev mode (hot reload)
-make run-frontend
-
-# Run both backend and frontend
-# (Use VS Code's "Full Stack" launch config for debugging)
-
-# Format code
-make format
-
-# Run tests
-make test-data        # Regenerate test data
-poetry run test       # Backend tests (from backend/)
-pnpm test:e2e         # E2E tests (from frontend/)
-```
-
-## 🐛 Debugging
-
-### VS Code Launch Configs
-
-> **Note:** Launch and task configs are in `.devcontainer/vscode-templates/`. 
-> To use them locally, copy to `.vscode/`:
-> ```bash
-> cp .devcontainer/vscode-templates/*.json .vscode/
-> ```
-> In Codespaces, core settings are auto-applied via devcontainer.json.
-
-Press `F5` or use the Run and Debug panel:
-
-- **Backend: Debug FastAPI** - Debug the REST API server
-- **Backend: Debug Executor** - Debug the agent executor
-- **Frontend: Debug Next.js** - Debug with browser DevTools
-- **Full Stack: Backend + Frontend** - Debug both simultaneously
-- **Tests: Run E2E Tests** - Run Playwright tests
-
-### VS Code Tasks
-
-Press `Ctrl+Shift+P` → "Tasks: Run Task":
-
-- Start/Stop All Services
-- Run Migrations
-- Seed Test Data
-- View Docker Logs
-- Reset Database
-
-## 📁 Project Structure
-
-```text
-autogpt_platform/           # This folder
-├── .devcontainer/          # Codespaces/devcontainer config
-├── .vscode/                # VS Code settings
-├── backend/                # Python FastAPI backend
-│   ├── backend/            # Application code
-│   ├── test/               # Test files + data seeders
-│   └── migrations/         # Prisma migrations
-├── frontend/               # Next.js frontend
-│   ├── src/                # Application code
-│   └── e2e/                # Playwright E2E tests
-├── db/                     # Supabase configuration
-├── docker-compose.yml      # Service orchestration
-└── Makefile                # Common commands
-```
-
-## 🔧 Troubleshooting
-
-### Services not starting?
-```bash
-# Check service status
-docker compose ps
-
-# View logs
-docker compose logs -f
-
-# Restart everything
-docker compose down && docker compose up -d
-```
-
-### Database issues?
-```bash
-# Reset database (destroys all data)
-make reset-db
-
-# Re-run migrations
-make migrate
-
-# Re-seed test data
-make test-data
-```
-
-### Port already in use?
-```bash
-# Check what's using the port
-lsof -i :3000
-
-# Kill process (if safe)
-kill -9 <PID>
-```
-
-### Can't login?
-- Ensure all services are running: `docker compose ps`
-- Check auth service: `docker compose logs auth`
-- Try seeding data again: `make test-data`
-
-## 📝 Making Changes
-
-### Backend Changes
-1. Edit files in `backend/backend/`
-2. If using `make run-backend`, changes auto-reload
-3. Run `poetry run format` before committing
-
-### Frontend Changes
-1. Edit files in `frontend/src/`
-2. If using `make run-frontend`, changes auto-reload
-3. Run `pnpm format` before committing
-
-### Database Schema Changes
-1. Edit `backend/schema.prisma`
-2. Run `poetry run prisma migrate dev --name your_migration`
-3. Run `poetry run prisma generate`
-
-## 🔒 Environment Variables
-
-Default environment variables are configured for local development. For production secrets, use GitHub Codespaces Secrets:
-
-1. Go to GitHub Settings → Codespaces → Secrets
-2. Add secrets with names matching `.env` variables
-3. They'll be automatically available in your codespace
-
-## 📚 More Resources
-
-- [AutoGPT Platform Docs](https://docs.agpt.co)
-- [Codespaces Documentation](https://docs.github.com/en/codespaces)
-- [Dev Containers Spec](https://containers.dev)

.devcontainer/platform/devcontainer.json

@@ -1,152 +0,0 @@
-{
-  "name": "AutoGPT Platform",
-  "dockerComposeFile": "docker-compose.devcontainer.yml",
-  "service": "devcontainer",
-  "workspaceFolder": "/workspaces/AutoGPT/autogpt_platform",
-  "shutdownAction": "stopCompose",
-
-  // Features - Docker-in-Docker for full compose support
-  "features": {
-    "ghcr.io/devcontainers/features/docker-in-docker:2": {
-      "dockerDashComposeVersion": "v2"
-    },
-    "ghcr.io/devcontainers/features/github-cli:1": {},
-    "ghcr.io/devcontainers/features/node:1": {
-      "version": "22",
-      "nodeGypDependencies": true
-    },
-    "ghcr.io/devcontainers/features/python:1": {
-      "version": "3.13",
-      "installTools": true,
-      "toolsToInstall": "flake8,autopep8,black,mypy,pytest,poetry"
-    }
-  },
-
-  // Lifecycle scripts - paths relative to repo root
-  "onCreateCommand": "bash .devcontainer/platform/scripts/oncreate.sh",
-  "postCreateCommand": "bash .devcontainer/platform/scripts/postcreate.sh",
-  "postStartCommand": "bash .devcontainer/platform/scripts/poststart.sh",
-
-  // Port forwarding
-  "forwardPorts": [
-    3000,   // Frontend
-    8006,   // REST API
-    8001,   // WebSocket
-    8000,   // Supabase Kong
-    5432,   // PostgreSQL
-    6379,   // Redis
-    15672,  // RabbitMQ Management
-    5555    // Supabase Studio
-  ],
-
-  "portsAttributes": {
-    "3000": { "label": "Frontend", "onAutoForward": "openBrowser" },
-    "8006": { "label": "REST API", "onAutoForward": "notify" },
-    "8001": { "label": "WebSocket", "onAutoForward": "silent" },
-    "8000": { "label": "Supabase", "onAutoForward": "silent" },
-    "5432": { "label": "PostgreSQL", "onAutoForward": "silent" },
-    "6379": { "label": "Redis", "onAutoForward": "silent" },
-    "15672": { "label": "RabbitMQ", "onAutoForward": "silent" },
-    "5555": { "label": "Supabase Studio", "onAutoForward": "silent" }
-  },
-
-  // VS Code customizations
-  "customizations": {
-    "vscode": {
-      "settings": {
-        // Python
-        "python.defaultInterpreterPath": "${workspaceFolder}/backend/.venv/bin/python",
-        "python.analysis.typeCheckingMode": "basic",
-        "python.testing.pytestEnabled": true,
-        "python.testing.pytestArgs": ["backend"],
-        
-        // Formatting
-        "[python]": {
-          "editor.defaultFormatter": "ms-python.black-formatter",
-          "editor.formatOnSave": true
-        },
-        "[typescript]": {
-          "editor.defaultFormatter": "esbenp.prettier-vscode",
-          "editor.formatOnSave": true
-        },
-        "[typescriptreact]": {
-          "editor.defaultFormatter": "esbenp.prettier-vscode",
-          "editor.formatOnSave": true
-        },
-        "[javascript]": {
-          "editor.defaultFormatter": "esbenp.prettier-vscode",
-          "editor.formatOnSave": true
-        },
-        
-        // Editor
-        "editor.rulers": [88, 120],
-        "editor.tabSize": 2,
-        "files.trimTrailingWhitespace": true,
-        
-        // Terminal
-        "terminal.integrated.defaultProfile.linux": "bash",
-        "terminal.integrated.cwd": "${workspaceFolder}",
-        
-        // Git
-        "git.autofetch": true,
-        "git.enableSmartCommit": true,
-        "git.openRepositoryInParentFolders": "always",
-        
-        // Prisma
-        "prisma.showPrismaDataPlatformNotification": false
-      },
-      
-      "extensions": [
-        // Python
-        "ms-python.python",
-        "ms-python.vscode-pylance",
-        "ms-python.black-formatter",
-        "ms-python.isort",
-        
-        // JavaScript/TypeScript
-        "dbaeumer.vscode-eslint",
-        "esbenp.prettier-vscode",
-        "bradlc.vscode-tailwindcss",
-        
-        // Database
-        "Prisma.prisma",
-        
-        // Testing
-        "ms-playwright.playwright",
-        
-        // GitHub
-        "GitHub.vscode-pull-request-github",
-        "GitHub.copilot",
-        "github.vscode-github-actions",
-        
-        // Utilities
-        "eamodio.gitlens",
-        "usernamehw.errorlens",
-        "christian-kohler.path-intellisense",
-        "mikestead.dotenv"
-      ]
-    },
-    
-    "codespaces": {
-      "openFiles": [
-        "README.md"
-      ]
-    }
-  },
-
-  // Environment variables
-  "containerEnv": {
-    "CODESPACES": "true",
-    "POETRY_VIRTUALENVS_IN_PROJECT": "true"
-  },
-
-  // Run as non-root for security
-  "remoteUser": "vscode",
-  
-  // Host requirements for performance
-  "hostRequirements": {
-    "cpus": 4,
-    "memory": "8gb",
-    "storage": "32gb"
-  }
-}

.devcontainer/platform/docker-compose.devcontainer.yml

@@ -1,21 +0,0 @@
-# Standalone devcontainer service
-# The platform services (db, redis, etc.) are started from within
-# the container using docker compose commands in the lifecycle scripts.
-
-services:
-  devcontainer:
-    image: mcr.microsoft.com/devcontainers/base:ubuntu-24.04
-    volumes:
-      # Mount the entire AutoGPT repo
-      - ../..:/workspaces/AutoGPT:cached
-    
-    # Keep container running
-    command: sleep infinity
-    
-    # Environment for development
-    environment:
-      - CODESPACES=true
-      - POETRY_VIRTUALENVS_IN_PROJECT=true
-      - POETRY_NO_INTERACTION=1
-      - NEXT_TELEMETRY_DISABLED=1
-      - DO_NOT_TRACK=1

.devcontainer/platform/scripts/oncreate.sh

@@ -1,142 +0,0 @@
-#!/bin/bash
-# =============================================================================
-# ONCREATE SCRIPT - Runs during prebuild
-# =============================================================================
-# This script runs during the prebuild phase (GitHub Actions).
-# It caches everything that's safe to cache:
-#   ✅ Dependency Docker images (postgres, redis, rabbitmq, etc.)
-#   ✅ Python packages (poetry install)
-#   ✅ Node packages (pnpm install)
-#
-# It does NOT build backend/frontend Docker images because those would
-# contain stale code from the prebuild branch, not the PR being reviewed.
-# =============================================================================
-
-set -e  # Exit on error
-set -x  # Print commands for debugging
-
-echo "🚀 Starting prebuild setup..."
-
-# =============================================================================
-# Setup PATH for tools installed by devcontainer features
-# =============================================================================
-# Python feature installs pipx at /usr/local/py-utils/bin
-# Node feature installs nvm, node, pnpm at various locations
-export PATH="/usr/local/py-utils/bin:$PATH"
-
-# Source nvm if available (Node feature uses nvm)
-export NVM_DIR="${NVM_DIR:-/usr/local/share/nvm}"
-if [ -s "$NVM_DIR/nvm.sh" ]; then
-    . "$NVM_DIR/nvm.sh"
-fi
-
-# =============================================================================
-# Verify and Install Poetry
-# =============================================================================
-echo "📦 Setting up Poetry..."
-
-if command -v poetry &> /dev/null; then
-    echo "  Poetry already installed: $(poetry --version)"
-else
-    echo "  Installing Poetry via pipx..."
-    if command -v pipx &> /dev/null; then
-        pipx install poetry
-    else
-        echo "  pipx not found, installing poetry via pip..."
-        pip install --user poetry
-        export PATH="$HOME/.local/bin:$PATH"
-    fi
-fi
-
-poetry --version || { echo "❌ Poetry installation failed"; exit 1; }
-
-# =============================================================================
-# Verify and Install pnpm
-# =============================================================================
-echo "📦 Setting up pnpm..."
-
-if command -v pnpm &> /dev/null; then
-    echo "  pnpm already installed: $(pnpm --version)"
-else
-    echo "  Installing pnpm via npm..."
-    npm install -g pnpm
-fi
-
-pnpm --version || { echo "❌ pnpm installation failed"; exit 1; }
-
-# =============================================================================
-# Navigate to workspace
-# =============================================================================
-cd /workspaces/AutoGPT/autogpt_platform
-
-# =============================================================================
-# Install Backend Dependencies
-# =============================================================================
-echo "📦 Installing backend dependencies..."
-
-cd backend
-poetry install --no-interaction --no-ansi
-
-# Generate Prisma client (schema only, no DB needed)
-echo "🔧 Generating Prisma client..."
-poetry run prisma generate || true
-poetry run gen-prisma-stub || true
-
-cd ..
-
-# =============================================================================
-# Install Frontend Dependencies
-# =============================================================================
-echo "📦 Installing frontend dependencies..."
-
-cd frontend
-pnpm install --frozen-lockfile
-cd ..
-
-# =============================================================================
-# Pull Dependency Docker Images
-# =============================================================================
-# Use docker compose pull to get exact versions from compose files
-# (single source of truth, no version drift)
-# =============================================================================
-echo "🐳 Pulling dependency Docker images..."
-
-# Start Docker daemon if using docker-in-docker
-if [ -e /var/run/docker-host.sock ]; then
-    sudo ln -sf /var/run/docker-host.sock /var/run/docker.sock || true
-fi
-
-# Check if Docker is available
-if command -v docker &> /dev/null && docker info &> /dev/null; then
-    # Pull images defined in docker-compose.yml (single source of truth)
-    docker compose pull db redis rabbitmq kong auth || echo "⚠️ Some images may not have pulled"
-    echo "✅ Dependency images pulled"
-else
-    echo "⚠️ Docker not available during prebuild, images will be pulled on first start"
-fi
-
-# =============================================================================
-# Copy environment files
-# =============================================================================
-echo "📄 Setting up environment files..."
-
-cd /workspaces/AutoGPT/autogpt_platform
-
-[ ! -f backend/.env ] && cp backend/.env.default backend/.env
-[ ! -f frontend/.env ] && cp frontend/.env.default frontend/.env
-[ ! -f .env ] && cp .env.default .env
-
-# =============================================================================
-# Done!
-# =============================================================================
-echo ""
-echo "=============================================="
-echo "✅ PREBUILD COMPLETE"
-echo "=============================================="
-echo ""
-echo "Cached:"
-echo "  ✅ Poetry $(poetry --version 2>/dev/null || echo '(check path)')"
-echo "  ✅ pnpm $(pnpm --version 2>/dev/null || echo '(check path)')"
-echo "  ✅ Python packages"
-echo "  ✅ Node packages"
-echo ""

.devcontainer/platform/scripts/postcreate.sh

@@ -1,131 +0,0 @@
-#!/bin/bash
-# =============================================================================
-# POSTCREATE SCRIPT - Runs after container creation
-# =============================================================================
-# This script runs once when a codespace is first created. It starts the
-# dependency services and prepares the environment for development.
-#
-# NOTE: Backend and Frontend run NATIVELY (not in Docker) to ensure you're
-# always running the current branch's code, not stale prebuild code.
-# =============================================================================
-
-set -e  # Exit on error
-
-echo "🚀 Setting up your development environment..."
-
-# Ensure PATH includes pipx binaries (where poetry is installed)
-export PATH="/usr/local/py-utils/bin:$PATH"
-
-cd /workspaces/AutoGPT/autogpt_platform
-
-# =============================================================================
-# Ensure Docker is available
-# =============================================================================
-if [ -e /var/run/docker-host.sock ]; then
-    sudo ln -sf /var/run/docker-host.sock /var/run/docker.sock 2>/dev/null || true
-fi
-
-# Wait for Docker to be ready
-echo "⏳ Waiting for Docker..."
-timeout 60 bash -c 'until docker info &>/dev/null; do sleep 1; done'
-echo "✅ Docker is ready"
-
-# =============================================================================
-# Start Dependency Services ONLY
-# =============================================================================
-# We only start infrastructure deps in Docker.
-# Backend/Frontend run natively to use the current branch's code.
-# =============================================================================
-echo "🐳 Starting dependency services..."
-
-# Start core dependencies (DB, Auth, Redis, RabbitMQ)
-docker compose up -d db redis rabbitmq kong auth
-
-# Wait for PostgreSQL to be healthy
-echo "⏳ Waiting for PostgreSQL..."
-timeout 120 bash -c '
-until docker compose exec -T db pg_isready -U postgres &>/dev/null; do
-    sleep 2
-    echo "  Waiting for database..."
-done
-'
-echo "✅ PostgreSQL is ready"
-
-# Wait for Redis
-echo "⏳ Waiting for Redis..."
-timeout 60 bash -c 'until docker compose exec -T redis redis-cli ping &>/dev/null; do sleep 1; done'
-echo "✅ Redis is ready"
-
-# Wait for RabbitMQ
-echo "⏳ Waiting for RabbitMQ..."
-timeout 90 bash -c 'until docker compose exec -T rabbitmq rabbitmq-diagnostics -q ping &>/dev/null; do sleep 2; done'
-echo "✅ RabbitMQ is ready"
-
-# =============================================================================
-# Run Database Migrations
-# =============================================================================
-echo "🔄 Running database migrations..."
-
-cd backend
-
-# Run migrations
-poetry run prisma migrate deploy
-poetry run prisma generate
-poetry run gen-prisma-stub || true
-
-cd ..
-
-# =============================================================================
-# Seed Test Data (Minimal)
-# =============================================================================
-echo "🌱 Checking test data..."
-
-cd backend
-
-# Check if test data already exists (idempotent)
-if poetry run python -c "
-import asyncio
-from backend.data.db import prisma
-
-async def check():
-    await prisma.connect()
-    count = await prisma.user.count()
-    await prisma.disconnect()
-    return count > 0
-
-print('exists' if asyncio.run(check()) else 'empty')
-" 2>/dev/null | grep -q "exists"; then
-    echo "  Test data already exists, skipping seed"
-else
-    echo "  Running E2E test data creator..."
-    poetry run python test/e2e_test_data.py || echo "⚠️ Test data seeding had issues (may be partial)"
-fi
-
-cd ..
-
-# =============================================================================
-# Print Welcome Message
-# =============================================================================
-echo ""
-echo "=============================================="
-echo "🎉 CODESPACE READY!"
-echo "=============================================="
-echo ""
-echo "📍 Services Running (Docker):"
-echo "   PostgreSQL:  localhost:5432"
-echo "   Redis:       localhost:6379"
-echo "   RabbitMQ:    localhost:5672 (mgmt: 15672)"
-echo "   Supabase:    localhost:8000"
-echo ""
-echo "🚀 Start Development:"
-echo "   make run-backend   # Start backend (localhost:8006)"
-echo "   make run-frontend  # Start frontend (localhost:3000)"
-echo ""
-echo "   Or run both in separate terminals!"
-echo ""
-echo "🔑 Test Account:"
-echo "   Email:    test123@gmail.com"
-echo "   Password: testpassword123"
-echo ""
-echo "📚 Full docs: .devcontainer/platform/README.md"
-echo ""

.devcontainer/platform/scripts/poststart.sh

@@ -1,44 +0,0 @@
-#!/bin/bash
-# =============================================================================
-# POSTSTART SCRIPT - Runs every time the codespace starts
-# =============================================================================
-# This script runs when:
-# 1. Codespace is first created (after postcreate)
-# 2. Codespace resumes from stopped state
-# 3. Codespace rebuilds
-#
-# It ensures dependency services are running. Backend/Frontend are run
-# manually by the developer for hot-reload during development.
-# =============================================================================
-
-echo "🔄 Starting dependency services..."
-
-cd /workspaces/AutoGPT/autogpt_platform || { echo "❌ Failed to cd to workspace"; exit 1; }
-
-# Ensure Docker socket is available
-if [ -e /var/run/docker-host.sock ]; then
-    sudo ln -sf /var/run/docker-host.sock /var/run/docker.sock 2>/dev/null || true
-fi
-
-# Wait for Docker
-timeout 30 bash -c 'until docker info &>/dev/null; do sleep 1; done' || {
-    echo "⚠️ Docker not available, services may need manual start"
-    exit 0
-}
-
-# Start only dependency services (not backend/frontend)
-docker compose up -d db redis rabbitmq kong auth
-
-# Quick health check
-echo "⏳ Waiting for services..."
-sleep 5
-
-if docker compose ps | grep -q "running"; then
-    echo "✅ Dependency services are running"
-    echo ""
-    echo "🚀 Start development with:"
-    echo "   make run-backend   # Terminal 1"
-    echo "   make run-frontend  # Terminal 2"
-else
-    echo "⚠️ Some services may not be running. Try: docker compose up -d"
-fi

.devcontainer/platform/vscode-templates/launch.json

@@ -1,110 +0,0 @@
-{
-  "version": "0.2.0",
-  "configurations": [
-    {
-      "name": "Backend: Debug FastAPI",
-      "type": "debugpy",
-      "request": "launch",
-      "module": "uvicorn",
-      "args": [
-        "backend.rest:app",
-        "--reload",
-        "--host", "0.0.0.0",
-        "--port", "8006"
-      ],
-      "cwd": "${workspaceFolder}/backend",
-      "env": {
-        "PYTHONPATH": "${workspaceFolder}/backend"
-      },
-      "console": "integratedTerminal",
-      "justMyCode": false
-    },
-    {
-      "name": "Backend: Debug Executor",
-      "type": "debugpy",
-      "request": "launch",
-      "module": "backend.exec",
-      "cwd": "${workspaceFolder}/backend",
-      "env": {
-        "PYTHONPATH": "${workspaceFolder}/backend"
-      },
-      "console": "integratedTerminal",
-      "justMyCode": false
-    },
-    {
-      "name": "Backend: Debug WebSocket",
-      "type": "debugpy",
-      "request": "launch",
-      "module": "backend.ws",
-      "cwd": "${workspaceFolder}/backend",
-      "env": {
-        "PYTHONPATH": "${workspaceFolder}/backend"
-      },
-      "console": "integratedTerminal",
-      "justMyCode": false
-    },
-    {
-      "name": "Frontend: Debug Next.js",
-      "type": "node",
-      "request": "launch",
-      "runtimeExecutable": "pnpm",
-      "runtimeArgs": ["dev"],
-      "cwd": "${workspaceFolder}/frontend",
-      "console": "integratedTerminal",
-      "serverReadyAction": {
-        "pattern": "- Local:.+(https?://\\S+)",
-        "uriFormat": "%s",
-        "action": "openExternally"
-      }
-    },
-    {
-      "name": "Frontend: Debug Next.js (Server-side)",
-      "type": "node",
-      "request": "launch",
-      "runtimeExecutable": "pnpm",
-      "runtimeArgs": ["dev"],
-      "cwd": "${workspaceFolder}/frontend",
-      "env": {
-        "NODE_OPTIONS": "--inspect"
-      },
-      "console": "integratedTerminal"
-    },
-    {
-      "name": "Tests: Run Backend Tests",
-      "type": "debugpy",
-      "request": "launch",
-      "module": "pytest",
-      "args": ["-v", "--tb=short"],
-      "cwd": "${workspaceFolder}/backend",
-      "console": "integratedTerminal",
-      "justMyCode": false
-    },
-    {
-      "name": "Tests: Run E2E Tests (Playwright)",
-      "type": "node",
-      "request": "launch",
-      "runtimeExecutable": "pnpm",
-      "runtimeArgs": ["test:e2e"],
-      "cwd": "${workspaceFolder}/frontend",
-      "console": "integratedTerminal"
-    },
-    {
-      "name": "Scripts: Seed Test Data",
-      "type": "debugpy",
-      "request": "launch",
-      "program": "${workspaceFolder}/backend/test/e2e_test_data.py",
-      "cwd": "${workspaceFolder}/backend",
-      "env": {
-        "PYTHONPATH": "${workspaceFolder}/backend"
-      },
-      "console": "integratedTerminal"
-    }
-  ],
-  "compounds": [
-    {
-      "name": "Full Stack: Backend + Frontend",
-      "configurations": ["Backend: Debug FastAPI", "Frontend: Debug Next.js"],
-      "stopAll": true
-    }
-  ]
-}

.devcontainer/platform/vscode-templates/tasks.json

@@ -1,147 +0,0 @@
-{
-  "version": "2.0.0",
-  "tasks": [
-    {
-      "label": "Start All Services",
-      "type": "shell",
-      "command": "docker compose up -d",
-      "options": {
-        "cwd": "${workspaceFolder}"
-      },
-      "problemMatcher": [],
-      "group": "build"
-    },
-    {
-      "label": "Stop All Services",
-      "type": "shell",
-      "command": "docker compose stop",
-      "options": {
-        "cwd": "${workspaceFolder}"
-      },
-      "problemMatcher": []
-    },
-    {
-      "label": "Start Core Services",
-      "type": "shell",
-      "command": "make start-core",
-      "options": {
-        "cwd": "${workspaceFolder}"
-      },
-      "problemMatcher": [],
-      "group": "build"
-    },
-    {
-      "label": "Run Backend (Dev Mode)",
-      "type": "shell",
-      "command": "poetry run app",
-      "options": {
-        "cwd": "${workspaceFolder}/backend"
-      },
-      "problemMatcher": [],
-      "isBackground": true,
-      "group": {
-        "kind": "build",
-        "isDefault": false
-      }
-    },
-    {
-      "label": "Run Frontend (Dev Mode)",
-      "type": "shell",
-      "command": "pnpm dev",
-      "options": {
-        "cwd": "${workspaceFolder}/frontend"
-      },
-      "problemMatcher": [],
-      "isBackground": true,
-      "group": {
-        "kind": "build",
-        "isDefault": true
-      }
-    },
-    {
-      "label": "Run Migrations",
-      "type": "shell",
-      "command": "make migrate",
-      "options": {
-        "cwd": "${workspaceFolder}"
-      },
-      "problemMatcher": []
-    },
-    {
-      "label": "Seed Test Data",
-      "type": "shell",
-      "command": "make test-data",
-      "options": {
-        "cwd": "${workspaceFolder}"
-      },
-      "problemMatcher": []
-    },
-    {
-      "label": "Format Code",
-      "type": "shell",
-      "command": "make format",
-      "options": {
-        "cwd": "${workspaceFolder}"
-      },
-      "problemMatcher": []
-    },
-    {
-      "label": "Backend: Run Tests",
-      "type": "shell",
-      "command": "poetry run test",
-      "options": {
-        "cwd": "${workspaceFolder}/backend"
-      },
-      "problemMatcher": [],
-      "group": "test"
-    },
-    {
-      "label": "Frontend: Run Tests",
-      "type": "shell",
-      "command": "pnpm test",
-      "options": {
-        "cwd": "${workspaceFolder}/frontend"
-      },
-      "problemMatcher": [],
-      "group": "test"
-    },
-    {
-      "label": "Frontend: Run E2E Tests",
-      "type": "shell",
-      "command": "pnpm test:e2e",
-      "options": {
-        "cwd": "${workspaceFolder}/frontend"
-      },
-      "problemMatcher": [],
-      "group": "test"
-    },
-    {
-      "label": "Generate API Client",
-      "type": "shell",
-      "command": "pnpm generate:api",
-      "options": {
-        "cwd": "${workspaceFolder}/frontend"
-      },
-      "problemMatcher": []
-    },
-    {
-      "label": "View Docker Logs",
-      "type": "shell",
-      "command": "docker compose logs -f",
-      "options": {
-        "cwd": "${workspaceFolder}"
-      },
-      "problemMatcher": [],
-      "isBackground": true
-    },
-    {
-      "label": "Reset Database",
-      "type": "shell",
-      "command": "make reset-db",
-      "options": {
-        "cwd": "${workspaceFolder}"
-      },
-      "problemMatcher": []
-    }
-  ]
-}

autogpt_platform/backend/backend/blocks/claude_code.py

@@ -1,10 +1,10 @@
 import json
 import shlex
 import uuid
-from typing import Literal, Optional
+from typing import TYPE_CHECKING, Literal, Optional
 
 from e2b import AsyncSandbox as BaseAsyncSandbox
-from pydantic import BaseModel, SecretStr
+from pydantic import SecretStr
 
 from backend.data.block import (
     Block,
@@ -20,6 +20,13 @@ from backend.data.model import (
     SchemaField,
 )
 from backend.integrations.providers import ProviderName
+from backend.util.sandbox_files import (
+    SandboxFileOutput,
+    extract_and_store_sandbox_files,
+)
+
+if TYPE_CHECKING:
+    from backend.executor.utils import ExecutionContext
 
 
 class ClaudeCodeExecutionError(Exception):
@@ -174,22 +181,15 @@ class ClaudeCodeBlock(Block):
             advanced=True,
         )
 
-    class FileOutput(BaseModel):
-        """A file extracted from the sandbox."""
-
-        path: str
-        relative_path: str  # Path relative to working directory (for GitHub, etc.)
-        name: str
-        content: str
-
     class Output(BlockSchemaOutput):
         response: str = SchemaField(
             description="The output/response from Claude Code execution"
         )
-        files: list["ClaudeCodeBlock.FileOutput"] = SchemaField(
+        files: list[SandboxFileOutput] = SchemaField(
             description=(
                 "List of text files created/modified by Claude Code during this execution. "
-                "Each file has 'path', 'relative_path', 'name', and 'content' fields."
+                "Each file has 'path', 'relative_path', 'name', 'content', and 'workspace_ref' fields. "
+                "workspace_ref contains a workspace:// URI if the file was stored to workspace."
             )
         )
         conversation_history: str = SchemaField(
@@ -252,6 +252,7 @@ class ClaudeCodeBlock(Block):
                             "relative_path": "index.html",
                             "name": "index.html",
                             "content": "<html>Hello World</html>",
+                            "workspace_ref": None,
                         }
                     ],
                 ),
@@ -267,11 +268,12 @@ class ClaudeCodeBlock(Block):
                 "execute_claude_code": lambda *args, **kwargs: (
                     "Created index.html with hello world content",  # response
                     [
-                        ClaudeCodeBlock.FileOutput(
+                        SandboxFileOutput(
                             path="/home/user/index.html",
                             relative_path="index.html",
                             name="index.html",
                             content="<html>Hello World</html>",
+                            workspace_ref=None,
                         )
                     ],  # files
                     "User: Create a hello world HTML file\n"
@@ -294,7 +296,8 @@ class ClaudeCodeBlock(Block):
         existing_sandbox_id: str,
         conversation_history: str,
         dispose_sandbox: bool,
-    ) -> tuple[str, list["ClaudeCodeBlock.FileOutput"], str, str, str]:
+        execution_context: "ExecutionContext",
+    ) -> tuple[str, list[SandboxFileOutput], str, str, str]:
         """
         Execute Claude Code in an E2B sandbox.
 
@@ -449,14 +452,18 @@ class ClaudeCodeBlock(Block):
                 else:
                     new_conversation_history = turn_entry
 
-            # Extract files created/modified during this run
-            files = await self._extract_files(
-                sandbox, working_directory, start_timestamp
+            # Extract files created/modified during this run and store to workspace
+            sandbox_files = await extract_and_store_sandbox_files(
+                sandbox=sandbox,
+                working_directory=working_directory,
+                execution_context=execution_context,
+                since_timestamp=start_timestamp,
+                text_only=True,
             )
 
             return (
                 response,
-                files,
+                sandbox_files,  # Already SandboxFileOutput objects
                 new_conversation_history,
                 current_session_id,
                 sandbox_id,
@@ -471,140 +478,6 @@ class ClaudeCodeBlock(Block):
             if dispose_sandbox and sandbox:
                 await sandbox.kill()
 
-    async def _extract_files(
-        self,
-        sandbox: BaseAsyncSandbox,
-        working_directory: str,
-        since_timestamp: str | None = None,
-    ) -> list["ClaudeCodeBlock.FileOutput"]:
-        """
-        Extract text files created/modified during this Claude Code execution.
-
-        Args:
-            sandbox: The E2B sandbox instance
-            working_directory: Directory to search for files
-            since_timestamp: ISO timestamp - only return files modified after this time
-
-        Returns:
-            List of FileOutput objects with path, relative_path, name, and content
-        """
-        files: list[ClaudeCodeBlock.FileOutput] = []
-
-        # Text file extensions we can safely read as text
-        text_extensions = {
-            ".txt",
-            ".md",
-            ".html",
-            ".htm",
-            ".css",
-            ".js",
-            ".ts",
-            ".jsx",
-            ".tsx",
-            ".json",
-            ".xml",
-            ".yaml",
-            ".yml",
-            ".toml",
-            ".ini",
-            ".cfg",
-            ".conf",
-            ".py",
-            ".rb",
-            ".php",
-            ".java",
-            ".c",
-            ".cpp",
-            ".h",
-            ".hpp",
-            ".cs",
-            ".go",
-            ".rs",
-            ".swift",
-            ".kt",
-            ".scala",
-            ".sh",
-            ".bash",
-            ".zsh",
-            ".sql",
-            ".graphql",
-            ".env",
-            ".gitignore",
-            ".dockerfile",
-            "Dockerfile",
-            ".vue",
-            ".svelte",
-            ".astro",
-            ".mdx",
-            ".rst",
-            ".tex",
-            ".csv",
-            ".log",
-        }
-
-        try:
-            # List files recursively using find command
-            # Exclude node_modules and .git directories, but allow hidden files
-            # like .env and .gitignore (they're filtered by text_extensions later)
-            # Filter by timestamp to only get files created/modified during this run
-            safe_working_dir = shlex.quote(working_directory)
-            timestamp_filter = ""
-            if since_timestamp:
-                timestamp_filter = f"-newermt {shlex.quote(since_timestamp)} "
-            find_result = await sandbox.commands.run(
-                f"find {safe_working_dir} -type f "
-                f"{timestamp_filter}"
-                f"-not -path '*/node_modules/*' "
-                f"-not -path '*/.git/*' "
-                f"2>/dev/null"
-            )
-
-            if find_result.stdout:
-                for file_path in find_result.stdout.strip().split("\n"):
-                    if not file_path:
-                        continue
-
-                    # Check if it's a text file we can read
-                    is_text = any(
-                        file_path.endswith(ext) for ext in text_extensions
-                    ) or file_path.endswith("Dockerfile")
-
-                    if is_text:
-                        try:
-                            content = await sandbox.files.read(file_path)
-                            # Handle bytes or string
-                            if isinstance(content, bytes):
-                                content = content.decode("utf-8", errors="replace")
-
-                            # Extract filename from path
-                            file_name = file_path.split("/")[-1]
-
-                            # Calculate relative path by stripping working directory
-                            relative_path = file_path
-                            if file_path.startswith(working_directory):
-                                relative_path = file_path[len(working_directory) :]
-                                # Remove leading slash if present
-                                if relative_path.startswith("/"):
-                                    relative_path = relative_path[1:]
-
-                            files.append(
-                                ClaudeCodeBlock.FileOutput(
-                                    path=file_path,
-                                    relative_path=relative_path,
-                                    name=file_name,
-                                    content=content,
-                                )
-                            )
-                        except Exception:
-                            # Skip files that can't be read
-                            pass
-
-        except Exception:
-            # If file extraction fails, return empty results
-            pass
-
-        return files
-
     def _escape_prompt(self, prompt: str) -> str:
         """Escape the prompt for safe shell execution."""
         # Use single quotes and escape any single quotes in the prompt
@@ -617,6 +490,7 @@ class ClaudeCodeBlock(Block):
         *,
         e2b_credentials: APIKeyCredentials,
         anthropic_credentials: APIKeyCredentials,
+        execution_context: "ExecutionContext",
         **kwargs,
     ) -> BlockOutput:
         try:
@@ -637,6 +511,7 @@ class ClaudeCodeBlock(Block):
                 existing_sandbox_id=input_data.sandbox_id,
                 conversation_history=input_data.conversation_history,
                 dispose_sandbox=input_data.dispose_sandbox,
+                execution_context=execution_context,
             )
 
             yield "response", response

autogpt_platform/backend/backend/blocks/code_executor.py

@@ -1,5 +1,5 @@
 from enum import Enum
-from typing import Any, Literal, Optional
+from typing import TYPE_CHECKING, Any, Literal, Optional
 
 from e2b_code_interpreter import AsyncSandbox
 from e2b_code_interpreter import Result as E2BExecutionResult
@@ -20,6 +20,13 @@ from backend.data.model import (
     SchemaField,
 )
 from backend.integrations.providers import ProviderName
+from backend.util.sandbox_files import (
+    SandboxFileOutput,
+    extract_and_store_sandbox_files,
+)
+
+if TYPE_CHECKING:
+    from backend.executor.utils import ExecutionContext
 
 TEST_CREDENTIALS = APIKeyCredentials(
     id="01234567-89ab-cdef-0123-456789abcdef",
@@ -85,6 +92,9 @@ class CodeExecutionResult(MainCodeExecutionResult):
 class BaseE2BExecutorMixin:
     """Shared implementation methods for E2B executor blocks."""
 
+    # Default output directory for file extraction
+    OUTPUT_DIR = "/output"
+
     async def execute_code(
         self,
         api_key: str,
@@ -95,14 +105,21 @@ class BaseE2BExecutorMixin:
         timeout: Optional[int] = None,
         sandbox_id: Optional[str] = None,
         dispose_sandbox: bool = False,
+        execution_context: Optional["ExecutionContext"] = None,
+        extract_files: bool = False,
     ):
         """
         Unified code execution method that handles all three use cases:
         1. Create new sandbox and execute (ExecuteCodeBlock)
         2. Create new sandbox, execute, and return sandbox_id (InstantiateCodeSandboxBlock)
         3. Connect to existing sandbox and execute (ExecuteCodeStepBlock)
+
+        Args:
+            extract_files: If True and execution_context provided, extract files from
+                           /output directory and store to workspace.
         """  # noqa
         sandbox = None
+        files: list[SandboxFileOutput] = []
         try:
             if sandbox_id:
                 # Connect to existing sandbox (ExecuteCodeStepBlock case)
@@ -114,6 +131,9 @@ class BaseE2BExecutorMixin:
                 sandbox = await AsyncSandbox.create(
                     api_key=api_key, template=template_id, timeout=timeout
                 )
+                # Create /output directory for file extraction
+                if extract_files:
+                    await sandbox.commands.run(f"mkdir -p {self.OUTPUT_DIR}")
                 if setup_commands:
                     for cmd in setup_commands:
                         await sandbox.commands.run(cmd)
@@ -133,7 +153,24 @@ class BaseE2BExecutorMixin:
             stdout_logs = "".join(execution.logs.stdout)
             stderr_logs = "".join(execution.logs.stderr)
 
-            return results, text_output, stdout_logs, stderr_logs, sandbox.sandbox_id
+            # Extract files from /output if requested
+            if extract_files and execution_context:
+                files = await extract_and_store_sandbox_files(
+                    sandbox=sandbox,
+                    working_directory=self.OUTPUT_DIR,
+                    execution_context=execution_context,
+                    since_timestamp=None,  # Get all files in /output
+                    text_only=False,  # Include binary files too
+                )
+
+            return (
+                results,
+                text_output,
+                stdout_logs,
+                stderr_logs,
+                sandbox.sandbox_id,
+                files,
+            )
         finally:
             # Dispose of sandbox if requested to reduce usage costs
             if dispose_sandbox and sandbox:
@@ -238,6 +275,12 @@ class ExecuteCodeBlock(Block, BaseE2BExecutorMixin):
             description="Standard output logs from execution"
         )
         stderr_logs: str = SchemaField(description="Standard error logs from execution")
+        files: list[SandboxFileOutput] = SchemaField(
+            description=(
+                "Files written to /output directory during execution. "
+                "Each file has path, name, content, and workspace_ref (if stored)."
+            ),
+        )
 
     def __init__(self):
         super().__init__(
@@ -259,23 +302,30 @@ class ExecuteCodeBlock(Block, BaseE2BExecutorMixin):
                 ("results", []),
                 ("response", "Hello World"),
                 ("stdout_logs", "Hello World\n"),
+                ("files", []),
             ],
             test_mock={
-                "execute_code": lambda api_key, code, language, template_id, setup_commands, timeout, dispose_sandbox: (  # noqa
+                "execute_code": lambda api_key, code, language, template_id, setup_commands, timeout, dispose_sandbox, execution_context, extract_files: (  # noqa
                     [],  # results
                     "Hello World",  # text_output
                     "Hello World\n",  # stdout_logs
                     "",  # stderr_logs
                     "sandbox_id",  # sandbox_id
+                    [],  # files
                 ),
             },
         )
 
     async def run(
-        self, input_data: Input, *, credentials: APIKeyCredentials, **kwargs
+        self,
+        input_data: Input,
+        *,
+        credentials: APIKeyCredentials,
+        execution_context: "ExecutionContext",
+        **kwargs,
     ) -> BlockOutput:
         try:
-            results, text_output, stdout, stderr, _ = await self.execute_code(
+            results, text_output, stdout, stderr, _, files = await self.execute_code(
                 api_key=credentials.api_key.get_secret_value(),
                 code=input_data.code,
                 language=input_data.language,
@@ -283,6 +333,8 @@ class ExecuteCodeBlock(Block, BaseE2BExecutorMixin):
                 setup_commands=input_data.setup_commands,
                 timeout=input_data.timeout,
                 dispose_sandbox=input_data.dispose_sandbox,
+                execution_context=execution_context,
+                extract_files=True,
             )
 
             # Determine result object shape & filter out empty formats
@@ -296,6 +348,8 @@ class ExecuteCodeBlock(Block, BaseE2BExecutorMixin):
                 yield "stdout_logs", stdout
             if stderr:
                 yield "stderr_logs", stderr
+            # Always yield files (empty list if none)
+            yield "files", [f.model_dump() for f in files]
         except Exception as e:
             yield "error", str(e)
 
@@ -393,6 +447,7 @@ class InstantiateCodeSandboxBlock(Block, BaseE2BExecutorMixin):
                     "Hello World\n",  # stdout_logs
                     "",  # stderr_logs
                     "sandbox_id",  # sandbox_id
+                    [],  # files
                 ),
             },
         )
@@ -401,7 +456,7 @@ class InstantiateCodeSandboxBlock(Block, BaseE2BExecutorMixin):
         self, input_data: Input, *, credentials: APIKeyCredentials, **kwargs
     ) -> BlockOutput:
         try:
-            _, text_output, stdout, stderr, sandbox_id = await self.execute_code(
+            _, text_output, stdout, stderr, sandbox_id, _ = await self.execute_code(
                 api_key=credentials.api_key.get_secret_value(),
                 code=input_data.setup_code,
                 language=input_data.language,
@@ -500,6 +555,7 @@ class ExecuteCodeStepBlock(Block, BaseE2BExecutorMixin):
                     "Hello World\n",  # stdout_logs
                     "",  # stderr_logs
                     sandbox_id,  # sandbox_id
+                    [],  # files
                 ),
             },
         )
@@ -508,7 +564,7 @@ class ExecuteCodeStepBlock(Block, BaseE2BExecutorMixin):
         self, input_data: Input, *, credentials: APIKeyCredentials, **kwargs
     ) -> BlockOutput:
         try:
-            results, text_output, stdout, stderr, _ = await self.execute_code(
+            results, text_output, stdout, stderr, _, _ = await self.execute_code(
                 api_key=credentials.api_key.get_secret_value(),
                 code=input_data.step_code,
                 language=input_data.language,

autogpt_platform/backend/backend/util/sandbox_files.py

@@ -0,0 +1,288 @@
+"""
+Shared utilities for extracting and storing files from E2B sandboxes.
+
+This module provides common file extraction and workspace storage functionality
+for blocks that run code in E2B sandboxes (Claude Code, Code Executor, etc.).
+"""
+
+import logging
+import shlex
+from dataclasses import dataclass
+from typing import TYPE_CHECKING
+
+from pydantic import BaseModel
+
+from backend.util.file import store_media_file
+from backend.util.type import MediaFileType
+
+if TYPE_CHECKING:
+    from e2b import AsyncSandbox as BaseAsyncSandbox
+
+    from backend.executor.utils import ExecutionContext
+
+logger = logging.getLogger(__name__)
+
+# Text file extensions that can be safely read and stored as text
+TEXT_EXTENSIONS = {
+    ".txt",
+    ".md",
+    ".html",
+    ".htm",
+    ".css",
+    ".js",
+    ".ts",
+    ".jsx",
+    ".tsx",
+    ".json",
+    ".xml",
+    ".yaml",
+    ".yml",
+    ".toml",
+    ".ini",
+    ".cfg",
+    ".conf",
+    ".py",
+    ".rb",
+    ".php",
+    ".java",
+    ".c",
+    ".cpp",
+    ".h",
+    ".hpp",
+    ".cs",
+    ".go",
+    ".rs",
+    ".swift",
+    ".kt",
+    ".scala",
+    ".sh",
+    ".bash",
+    ".zsh",
+    ".sql",
+    ".graphql",
+    ".env",
+    ".gitignore",
+    ".dockerfile",
+    "Dockerfile",
+    ".vue",
+    ".svelte",
+    ".astro",
+    ".mdx",
+    ".rst",
+    ".tex",
+    ".csv",
+    ".log",
+}
+
+
+class SandboxFileOutput(BaseModel):
+    """A file extracted from a sandbox and optionally stored in workspace."""
+
+    path: str
+    """Full path in the sandbox."""
+
+    relative_path: str
+    """Path relative to the working directory."""
+
+    name: str
+    """Filename only."""
+
+    content: str
+    """File content as text (for backward compatibility)."""
+
+    workspace_ref: str | None = None
+    """Workspace reference (workspace://{id}#mime) if stored, None otherwise."""
+
+
+@dataclass
+class ExtractedFile:
+    """Internal representation of an extracted file before storage."""
+
+    path: str
+    relative_path: str
+    name: str
+    content: bytes
+    is_text: bool
+
+
+async def extract_sandbox_files(
+    sandbox: "BaseAsyncSandbox",
+    working_directory: str,
+    since_timestamp: str | None = None,
+    text_only: bool = True,
+) -> list[ExtractedFile]:
+    """
+    Extract files from an E2B sandbox.
+
+    Args:
+        sandbox: The E2B sandbox instance
+        working_directory: Directory to search for files
+        since_timestamp: ISO timestamp - only return files modified after this time
+        text_only: If True, only extract text files (default). If False, extract all files.
+
+    Returns:
+        List of ExtractedFile objects with path, content, and metadata
+    """
+    files: list[ExtractedFile] = []
+
+    try:
+        # Build find command
+        safe_working_dir = shlex.quote(working_directory)
+        timestamp_filter = ""
+        if since_timestamp:
+            timestamp_filter = f"-newermt {shlex.quote(since_timestamp)} "
+
+        find_result = await sandbox.commands.run(
+            f"find {safe_working_dir} -type f "
+            f"{timestamp_filter}"
+            f"-not -path '*/node_modules/*' "
+            f"-not -path '*/.git/*' "
+            f"2>/dev/null"
+        )
+
+        if not find_result.stdout:
+            return files
+
+        for file_path in find_result.stdout.strip().split("\n"):
+            if not file_path:
+                continue
+
+            # Check if it's a text file
+            is_text = any(file_path.endswith(ext) for ext in TEXT_EXTENSIONS)
+
+            # Skip non-text files if text_only mode
+            if text_only and not is_text:
+                continue
+
+            try:
+                # Read file content as bytes
+                content = await sandbox.files.read(file_path, format="bytes")
+                if isinstance(content, str):
+                    content = content.encode("utf-8")
+                elif isinstance(content, bytearray):
+                    content = bytes(content)
+
+                # Extract filename from path
+                file_name = file_path.split("/")[-1]
+
+                # Calculate relative path
+                relative_path = file_path
+                if file_path.startswith(working_directory):
+                    relative_path = file_path[len(working_directory) :]
+                    if relative_path.startswith("/"):
+                        relative_path = relative_path[1:]
+
+                files.append(
+                    ExtractedFile(
+                        path=file_path,
+                        relative_path=relative_path,
+                        name=file_name,
+                        content=content,
+                        is_text=is_text,
+                    )
+                )
+            except Exception as e:
+                logger.debug(f"Failed to read file {file_path}: {e}")
+                continue
+
+    except Exception as e:
+        logger.warning(f"File extraction failed: {e}")
+
+    return files
+
+
+async def store_sandbox_files(
+    extracted_files: list[ExtractedFile],
+    execution_context: "ExecutionContext",
+) -> list[SandboxFileOutput]:
+    """
+    Store extracted sandbox files to workspace and return output objects.
+
+    Args:
+        extracted_files: List of files extracted from sandbox
+        execution_context: Execution context for workspace storage
+
+    Returns:
+        List of SandboxFileOutput objects with workspace refs
+    """
+    outputs: list[SandboxFileOutput] = []
+
+    for file in extracted_files:
+        # Decode content for text files (for backward compat content field)
+        if file.is_text:
+            try:
+                content_str = file.content.decode("utf-8", errors="replace")
+            except Exception:
+                content_str = ""
+        else:
+            content_str = f"[Binary file: {len(file.content)} bytes]"
+
+        # Try to store in workspace
+        workspace_ref: str | None = None
+        try:
+            # Convert bytes to data URI for store_media_file
+            import base64
+            import mimetypes
+
+            mime_type = mimetypes.guess_type(file.name)[0] or "application/octet-stream"
+            data_uri = (
+                f"data:{mime_type};base64,{base64.b64encode(file.content).decode()}"
+            )
+
+            result = await store_media_file(
+                file=MediaFileType(data_uri),
+                execution_context=execution_context,
+                return_format="for_block_output",
+            )
+            # Result is workspace://... or data:... depending on context
+            if result.startswith("workspace://"):
+                workspace_ref = result
+        except Exception as e:
+            logger.warning(f"Failed to store file {file.name} to workspace: {e}")
+            # For binary files, fall back to data URI to prevent data loss
+            if not file.is_text:
+                content_str = data_uri
+
+        outputs.append(
+            SandboxFileOutput(
+                path=file.path,
+                relative_path=file.relative_path,
+                name=file.name,
+                content=content_str,
+                workspace_ref=workspace_ref,
+            )
+        )
+
+    return outputs
+
+
+async def extract_and_store_sandbox_files(
+    sandbox: "BaseAsyncSandbox",
+    working_directory: str,
+    execution_context: "ExecutionContext",
+    since_timestamp: str | None = None,
+    text_only: bool = True,
+) -> list[SandboxFileOutput]:
+    """
+    Extract files from sandbox and store them in workspace.
+
+    This is the main entry point combining extraction and storage.
+
+    Args:
+        sandbox: The E2B sandbox instance
+        working_directory: Directory to search for files
+        execution_context: Execution context for workspace storage
+        since_timestamp: ISO timestamp - only return files modified after this time
+        text_only: If True, only extract text files
+
+    Returns:
+        List of SandboxFileOutput objects with content and workspace refs
+    """
+    extracted = await extract_sandbox_files(
+        sandbox=sandbox,
+        working_directory=working_directory,
+        since_timestamp=since_timestamp,
+        text_only=text_only,
+    )
+
+    return await store_sandbox_files(extracted, execution_context)

docs/integrations/block-integrations/llm.md

@@ -563,7 +563,7 @@ The block supports conversation continuation through three mechanisms:
 |--------|-------------|------|
 | error | Error message if execution failed | str |
 | response | The output/response from Claude Code execution | str |
-| files | List of text files created/modified by Claude Code during this execution. Each file has 'path', 'relative_path', 'name', and 'content' fields. | List[FileOutput] |
+| files | List of text files created/modified by Claude Code during this execution. Each file has 'path', 'relative_path', 'name', 'content', and 'workspace_ref' fields. workspace_ref contains a workspace:// URI if the file was stored to workspace. | List[SandboxFileOutput] |
 | conversation_history | Full conversation history including this turn. Pass this to conversation_history input to continue on a fresh sandbox if the previous sandbox timed out. | str |
 | session_id | Session ID for this conversation. Pass this back along with sandbox_id to continue the conversation. | str |
 | sandbox_id | ID of the sandbox instance. Pass this back along with session_id to continue the conversation. This is None if dispose_sandbox was True (sandbox was disposed). | str |

docs/integrations/block-integrations/misc.md

@@ -215,6 +215,7 @@ The sandbox includes pip and npm pre-installed. Set timeout to limit execution t
 | response | Text output (if any) of the main execution result | str |
 | stdout_logs | Standard output logs from execution | str |
 | stderr_logs | Standard error logs from execution | str |
+| files | Files written to /output directory during execution. Each file has path, name, content, and workspace_ref (if stored). | List[SandboxFileOutput] |
 
 ### Possible use case
 <!-- MANUAL: use_case -->