> The script runs in the Code Execution tool (a sandboxed environment), pausing when it needs results from your tools. When you return tool results via the API, they're processed by the script rather than consumed by the model. The script continues executing, and Claude only sees the final output.

Anyone knows how they would have implemented the pause/resume functionality in the code execution sandbox? I can think of these: unikernels / Temporal / custom implementation of serializable continuations. Anything else?

▲

vanviegen 18 hours ago | parent [-]

Presumably, a tool call is just a library call in the script. The implementation would need to ask the environment outside the sandbox (through a socket?) to take some action on its behalf.

	▲	emilsoman 15 hours ago \| parent [-]
		That's cool, but they say the code execution would wait till the tool call is done. Would they be just keeping the code execution process alive? That seems like a bad idea given tool calls can take an unknown amount of time to finish. I am guessing they would be putting the python orchestrator code to sleep when the tool call starts and restoring the state when the tool call is done.