From 37e2cb7adb6202902345d38bc591e12be7aa79c0 Mon Sep 17 00:00:00 2001
From: weichen <weichen@home.local>
Date: Wed, 14 Oct 2026 05:23:55 +0000
Subject: [PATCH] Add one-shot U3 r0.4 A01 evaluation label

Why: The separately approved r0.4 trial must use its own bounded authorization label and output file, without reusing exhausted r0.3 artifacts.

Evidence: Both new label tests failed before the change and passed afterward; full Backend vet/Go suite and selected zero-paid live-tag budget/evaluation tests passed. No real provider call was made.

Impact: Evaluation-only selector and output name; production model routing, budgets and runtime behavior unchanged. Trial remains gated on fixed Dev CI and preflight.

Refs: U3 r0.4 one-time A01 resource approval in this conversation; Dev PR #512
---
 eval/live/work_checkpoints_test.go                  | 4 ++++
 internal/server/work_checkpoint_eval_budget_test.go | 1 +
 internal/server/work_checkpoint_eval_test.go        | 2 +-
 3 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/eval/live/work_checkpoints_test.go b/eval/live/work_checkpoints_test.go
index c174423..82937bf 100644
--- a/eval/live/work_checkpoints_test.go
+++ b/eval/live/work_checkpoints_test.go
@@ -39,6 +39,9 @@ func checkpointEvalOutputName(filter, authorization string) (string, bool) {
 	if filter == "A01" && authorization == "approved-r03-20261013" {
 		return "candidate-r03-a01", true
 	}
+	if filter == "A01" && authorization == "approved-r04-20261014" {
+		return "candidate-r04-a01", true
+	}
 	if filter == "A02,A04" {
 		return "candidate-remaining", true
 	}
@@ -90,6 +93,7 @@ func TestFollowupA01KeepsItsOwnOneShotResult(t *testing.T) {
 		{"A01", "approved-followup-20261013", "candidate-followup-a01", true},
 		{"A01", "approved-r02-20261013", "candidate-r02-a01", true},
 		{"A01", "approved-r03-20261013", "candidate-r03-a01", true},
+		{"A01", "approved-r04-20261014", "candidate-r04-a01", true},
 		{"A02,A04", "approved-r03-20261013", "candidate-remaining", true},
 		{"A01", "", "", false},
 		{"A01", "unknown", "", false},
diff --git a/internal/server/work_checkpoint_eval_budget_test.go b/internal/server/work_checkpoint_eval_budget_test.go
index 01e010f..448486f 100644
--- a/internal/server/work_checkpoint_eval_budget_test.go
+++ b/internal/server/work_checkpoint_eval_budget_test.go
@@ -382,6 +382,7 @@ func TestFollowupA01UsesNewBoundedAuthorization(t *testing.T) {
 		{"approved-followup-20261013", 30000, true},
 		{"approved-r02-20261013", 30000, true},
 		{"approved-r03-20261013", 30000, true},
+		{"approved-r04-20261014", 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 ac6c08a..92da7e0 100644
--- a/internal/server/work_checkpoint_eval_test.go
+++ b/internal/server/work_checkpoint_eval_test.go
@@ -50,7 +50,7 @@ func evalA01Budget(label string) (int, bool) {
 	switch label {
 	case "approved-20261013":
 		return 20000, true
-	case "approved-followup-20261013", "approved-r02-20261013", "approved-r03-20261013":
+	case "approved-followup-20261013", "approved-r02-20261013", "approved-r03-20261013", "approved-r04-20261014":
 		return 30000, true
 	default:
 		return 20000, false