From afe83eb4428afeeeabc90ccc53403a3cc1890081 Mon Sep 17 00:00:00 2001
From: connermanuel <manuel.conner.g@gmail.com>
Date: Mon, 30 Mar 2026 16:42:07 -0700
Subject: [PATCH 1/2] Make target tokens required

---
 openapi.yaml | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/openapi.yaml b/openapi.yaml
index 1fc5f4a..121d12e 100644
--- a/openapi.yaml
+++ b/openapi.yaml
@@ -7900,12 +7900,14 @@ components:
       properties:
         target_tokens:
           $ref: '#/components/schemas/RL.LossTargetTokens'
-          description: Target tokens for loss computation (optional, defaults to shifted input_ids)
+          description: Target tokens for loss computation
         loss_mask:
           $ref: '#/components/schemas/RL.LossMask'
           description: Per-token loss mask (1=compute loss, 0=ignore)
         grpo_inputs:
           $ref: '#/components/schemas/RL.GRPOLossInputs'
+      required:
+        - target_tokens
     RL.TrainingSample:
       type: object
       required:

From ce4e67f551ed7388921261d67af0e2e8440c5090 Mon Sep 17 00:00:00 2001
From: connermanuel <manuel.conner.g@gmail.com>
Date: Thu, 2 Apr 2026 08:00:07 -0700
Subject: [PATCH 2/2] add grpo loss agg type sequence mean

---
 openapi.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/openapi.yaml b/openapi.yaml
index 121d12e..6f53452 100644
--- a/openapi.yaml
+++ b/openapi.yaml
@@ -7789,6 +7789,7 @@ components:
         - GRPO_LOSS_AGGREGATION_TYPE_UNSPECIFIED
         - GRPO_LOSS_AGGREGATION_TYPE_FIXED_HORIZON
         - GRPO_LOSS_AGGREGATION_TYPE_TOKEN_MEAN
+        - GRPO_LOSS_AGGREGATION_TYPE_SEQUENCE_MEAN
       default: GRPO_LOSS_AGGREGATION_TYPE_UNSPECIFIED
     RL.LossConfig:
       type: object