arcade-mcp/toolkits/code_sandbox/arcade_code_sandbox/tools/e2b.py
Sam Partee b6b4cd0a4c
🏗️ Restructure: Multi-Package Architecture + uv Migration (#412)
### Overview
Major restructuring from monolithic `arcade-ai` package to modular
library architecture with standardized uv-based dependency management.

![arcade-ai Monorepo
(2)](https://github.com/user-attachments/assets/25f102b0-bb87-4a04-9701-d227d05664b1)

### New Package Structure
- **`arcade-tdk`** - Lightweight toolkit development kit (core
decorators, auth)
- **`arcade-core`** - Core execution engine and catalog functionality  
- **`arcade-serve`** - FastAPI/MCP server components
- **`arcade-ai`** - Meta package that includes CLI functionality.
Optionally include evals via the `evals` extra. Optionally include all
packages via the `all` extra.

### Key Benefits
- **Lighter Dependencies**: Toolkits now depend only on `arcade-tdk` (~2
deps) vs full `arcade-ai` (~30+ deps)
- **Faster Builds**: uv provides 10-100x faster dependency resolution
and installation
- **Better Modularity**: Clear separation of concerns, consumers import
only what they need
- **Standard Tooling**: Eliminates custom poetry scripts, uses standard
Python packaging

### Migration Impact
- All 20 toolkits converted from poetry → uv with `arcade-tdk`
dependencies plus `arcade-ai[evals]` and `arcade-serve` dev
dependencies. When developing locally, devs should install toolkits via
`make install-local`.
- Modern Python 3.10+ type hints throughout
- Standardized build system with hatchling backend
- Enhanced Makefile with robust toolkit management commands
- Removed `arcade dev` CLI command
- Reduce the number of files created by `arcade new` and add an option
to not generate a tests and evals folder.

This foundation enables faster development cycles and cleaner dependency
chains for the growing toolkit ecosystem.

### Todo After this PR is merged
- [ ] Post-merge workflow(s) (release & publish containers, etc)
- [ ] Release order plan. @EricGustin suggests releasing in the
following order:
    1. `arcade-core` version 0.1.0
    2. `arcade-serve` version 0.1.0 and `arcade-tdk` version 0.1.0
    3. `arcade-ai` version 2.0.0
4. Patch release for all toolkits (all changes in toolkits are internal
refactors)
- [ ] [Update docs](https://github.com/ArcadeAI/docs/pull/318)

---------

Co-authored-by: Eric Gustin <eric@arcade.dev>
Co-authored-by: Eric Gustin <34000337+EricGustin@users.noreply.github.com>
2025-06-11 16:48:17 -07:00

52 lines
1.6 KiB
Python

from typing import Annotated
from arcade_tdk import ToolContext, tool
from e2b_code_interpreter import Sandbox
from arcade_code_sandbox.tools.models import E2BSupportedLanguage
# See https://e2b.dev/docs to learn more about E2B
@tool(requires_secrets=["E2B_API_KEY"])
def run_code(
context: ToolContext,
code: Annotated[str, "The code to run"],
language: Annotated[
E2BSupportedLanguage, "The language of the code"
] = E2BSupportedLanguage.PYTHON,
) -> Annotated[str, "The sandbox execution as a JSON string"]:
"""
Run code in a sandbox and return the output.
"""
api_key = context.get_secret("E2B_API_KEY")
with Sandbox(api_key=api_key) as sbx:
execution = sbx.run_code(code=code, language=language)
return str(execution.to_json())
# Note: Not recommended to use tool_choice='generate' with this tool
# since it contains base64 encoded image.
@tool(requires_secrets=["E2B_API_KEY"])
def create_static_matplotlib_chart(
context: ToolContext,
code: Annotated[str, "The Python code to run"],
) -> Annotated[dict, "A dictionary with the following keys: base64_image, logs, error"]:
"""
Run the provided Python code to generate a static matplotlib chart.
The resulting chart is returned as a base64 encoded image.
"""
api_key = context.get_secret("E2B_API_KEY")
with Sandbox(api_key=api_key) as sbx:
execution = sbx.run_code(code=code)
result = {
"base64_image": execution.results[0].png if execution.results else None,
"logs": execution.logs.to_json(),
"error": execution.error.to_json() if execution.error else None,
}
return result