Reserve a distinct r0.3 A01 evaluation entry
ci / vet-and-test (pull_request) Successful in 45s

Why: A future separately approved model trial must not reuse the consumed r0.2 label or overwrite its raw result.

Evidence: New label/output and 30000-token guard tests failed before implementation, then selected live-tag tests and Backend full Go suite passed.

Impact: Zero-paid evaluation entry only; its name does not grant resource approval or issue provider requests.

Refs: Dev task feature/fast-slow-u2-u3-plan; r0.3 plan Task 5
This commit is contained in:
2026-10-13 17:59:26 +00:00
parent 5f53f804e6
commit 5f834544b0
3 changed files with 7 additions and 1 deletions
+5
View File
@@ -36,6 +36,9 @@ func checkpointEvalOutputName(filter, authorization string) (string, bool) {
if filter == "A01" && authorization == "approved-r02-20261013" {
return "candidate-r02-a01", true
}
if filter == "A01" && authorization == "approved-r03-20261013" {
return "candidate-r03-a01", true
}
if filter == "A02,A04" {
return "candidate-remaining", true
}
@@ -86,6 +89,8 @@ func TestFollowupA01KeepsItsOwnOneShotResult(t *testing.T) {
{"A01", "approved-20261013", "candidate-extra-a01", true},
{"A01", "approved-followup-20261013", "candidate-followup-a01", true},
{"A01", "approved-r02-20261013", "candidate-r02-a01", true},
{"A01", "approved-r03-20261013", "candidate-r03-a01", true},
{"A02,A04", "approved-r03-20261013", "candidate-remaining", true},
{"A01", "", "", false},
{"A01", "unknown", "", false},
{"A02,A04", "", "candidate-remaining", true},
@@ -161,6 +161,7 @@ func TestFollowupA01UsesNewBoundedAuthorization(t *testing.T) {
{"approved-20261013", 20000, true},
{"approved-followup-20261013", 30000, true},
{"approved-r02-20261013", 30000, true},
{"approved-r03-20261013", 30000, true},
{"unapproved", 20000, false},
} {
tokens, guard := evalA01Budget(tc.label)
+1 -1
View File
@@ -47,7 +47,7 @@ func evalA01Budget(label string) (int, bool) {
switch label {
case "approved-20261013":
return 20000, true
case "approved-followup-20261013", "approved-r02-20261013":
case "approved-followup-20261013", "approved-r02-20261013", "approved-r03-20261013":
return 30000, true
default:
return 20000, false