The run is the durable product object. Workers and sandboxes are replaceable execution resources around it.

​
Why checkpoint after a successful turn

The completed response and workspace mutations form one durability promise. If Salambo marked the response complete before preserving required workspace changes, a replacement sandbox could continue the conversation with missing files. Checkpointing after each successful state-changing turn means Salambo can recreate the sandbox and restore the workspace before a durable follow-up.

​
Follow-up turn

For an existing run, Salambo restores session state, active model, thinking level, active tools, and the latest ready workspace generation before continuing.

​
Cancellation

Cancellation first stops or drains active model and extension work, then finalizes run state and sandbox cleanup. A cancelled response may have completed earlier responses; the final run outcome explains that distinction.

​
Deployment upgrade

With automatic workspace upgrades, Salambo checkpoints the current workspace, creates a sandbox from the new deployment, restores the run state, validates it, and switches authority only after the replacement is ready. See durable workspaces and run diagnostics for operational evidence.