From 5f834544b0b808cb16214a36725f2ae3cb90bfd4 Mon Sep 17 00:00:00 2001 From: weichen Date: Tue, 13 Oct 2026 17:59:26 +0000 Subject: [PATCH] Reserve a distinct r0.3 A01 evaluation entry 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 --- eval/live/work_checkpoints_test.go | 5 +++++ internal/server/work_checkpoint_eval_budget_test.go | 1 + internal/server/work_checkpoint_eval_test.go | 2 +- 3 files changed, 7 insertions(+), 1 deletion(-) diff --git a/eval/live/work_checkpoints_test.go b/eval/live/work_checkpoints_test.go index cb27b9e..c174423 100644 --- a/eval/live/work_checkpoints_test.go +++ b/eval/live/work_checkpoints_test.go @@ -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}, diff --git a/internal/server/work_checkpoint_eval_budget_test.go b/internal/server/work_checkpoint_eval_budget_test.go index 95a0e1c..d4edac5 100644 --- a/internal/server/work_checkpoint_eval_budget_test.go +++ b/internal/server/work_checkpoint_eval_budget_test.go @@ -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) diff --git a/internal/server/work_checkpoint_eval_test.go b/internal/server/work_checkpoint_eval_test.go index 2ec7ebe..311613b 100644 --- a/internal/server/work_checkpoint_eval_test.go +++ b/internal/server/work_checkpoint_eval_test.go @@ -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