RunsMerge check · 6 November 2026, 16:18 UTC
The scenario suite
Do the scripted scenarios still pass on this version of the code?
6/6 passed2 h 25 min
Setup
- Chains
- Satsuma lab chain
- RoleHome
- KeptLab, not retained
- RoleProving
- KeptLab, not retained
- Users
- UsersSynthetic
- Model
- No model: scripted answers
- ModeScripted
- Operator seat
- SeatBy delegate
- Unattended
- Yes: nobody was watching to step in
- Time
- 2 h 25 min · ended 18:43 UTC
Checklist 6 items
Every item, unless its row says otherwise
- ChainLab
- UsersSynthetic
- DecisionsScripted
Stopping and restarting a product
1/1 passed
Fixing by redeploying
1/1 passed
Fixing by an in-place upgrade
2/2 passed
Stolen-key safety
1/1 passed
Defending against market manipulation
1/1 passed
What this proves
- The scenarios that ran still reach their expected end on this version of the code, from saved chain states, with scripted model answers.
What it does not
- Anything about the model's own judgment: every model answer in these scenarios is scripted.
- Anything about a scenario that was not selected for this check.
What broke, what was fixed
The record of this run does not say whether a person stepped in, so it does not count as a run without repairs.
Cost in tokens
Not recorded: this run has no chain-derived scorecard.
Archived evidence
The lab chains this run used were reset afterwards and are not retained, so nothing here links to an explorer. The record below is the archived copy.
- Scorecard
- None archived.
- Loop
- 872c8908d0ab211f4106f59c543f5f0096baf080
- Harness
- 00f0708125cf0895489430358676e67dfd9f38aa