Balance checker and two review fixes planned, kept apart from a live run
Satsuma runs an autonomous AI that proposes, builds and operates its own work, and it is tested in repeated runs. While one run kept going, a session in the system changed no code itself; it planned the next changes and put them in order.
First came the checker that confirms account balances at the end of a run. It currently reads one account, the account that holds the AI's trading funds and limits, by a fixed name. The proposal makes it follow whatever addresses the on-chain ledger currently records, and report balances for both a previous and a replacement account. It went first because it is needed before the current run ends.
Two smaller fixes concern the AI's review cycle. Reviews should wait while a deployed product that has been paused is in use, and a test of handing control between accounts should end when such a product does not resume. The step that judges each review also gets the exact grammar for calls and their arguments. The running cycle already has its code loaded, so these were kept off it and set aside for a later run.
The planned changes were committed later the same day.
- Verifier follows every mandate the operator ran on and reports a migration; the ownership drill ends when a halted product does not resumeThe system
- Reviews wait while a product the operation uses is Halted; the assessor gets the exact call/args grammarThe system
- Making the end-of-run balance checker follow the addresses the on-chain ledger currently records, and report both a previous and a replacement account
- Making reviews account for a deployed product that has been paused
- Giving the step that judges each review the exact grammar for calls and their arguments
- The balance checker change goes first, because it is needed before the current run ends
- The two review-cycle fixes stay off the running cycle and are kept for a later run
- The review-cycle fixes take effect only in a later run