From ecfeef7ff114011c8ff46c55790646d58d76ce04 Mon Sep 17 00:00:00 2001
From: faresobeid <111092724+faresobeid@users.noreply.github.com>
Date: Tue, 6 Oct 2026 11:57:20 +0000
Subject: [PATCH 1/2] feat(client): pass through sampling-mask logprobs

---
 renderers/client.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/renderers/client.py b/renderers/client.py
index d663f82cf..2b4b3dc40 100644
--- a/renderers/client.py
+++ b/renderers/client.py
@@ -396,8 +396,11 @@ def _prepare():
     routed_experts = choice.get("routed_experts")
     # vLLM's native kept-set sampling masks (``--return-sampling-mask``):
     # one list of surviving vocab ids per completion token, or (prime-rl's
-    # server) packed CSR ``{"ids", "counts"}`` base64 int32 arrays.
+    # server) packed CSR ``{"ids", "counts"}`` base64 int32 arrays. With score
+    # centering on, prime-rl's server also returns the sampler's renormalized
+    # logprob of each of those ids (packed float32, parallel to the ids).
     sampling_mask = choice.get("sampling_mask")
+    sampling_mask_logprobs = choice.get("sampling_mask_logprobs")
 
     # /inference/v1/generate returns finish_reason in {"stop","length",...} —
     # never "tool_calls" (a chat-completions concept). Promote stop→tool_calls
@@ -429,6 +432,7 @@ def _prepare():
         "reasoning_complete": parsed.reasoning_complete,
         "routed_experts": routed_experts,
         "sampling_mask": sampling_mask,
+        "sampling_mask_logprobs": sampling_mask_logprobs,
         # The mm sidecar consumed on the request side, surfaced back so
         # callers can persist it on the trajectory step for downstream
         # multi-turn bridging and training-sample construction.

From d3a1af006ad4cbdab615febc5aed0d9f1175607f Mon Sep 17 00:00:00 2001
From: faresobeid <111092724+faresobeid@users.noreply.github.com>
Date: Sat, 3 Oct 2026 21:39:23 +0000
Subject: [PATCH 2/2] feat(client): pass through by-handle payload segments

---
 renderers/client.py | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/renderers/client.py b/renderers/client.py
index 2b4b3dc40..7fc5906fb 100644
--- a/renderers/client.py
+++ b/renderers/client.py
@@ -261,9 +261,9 @@ async def generate(
     Returns a dict with: request_id, prompt_ids, renderer_prompt_ids,
     mm_placeholders, completion_ids, completion_logprobs, content,
     reasoning_content, tool_calls, finish_reason, routed_experts,
-    multi_modal_data, prompt_attribution. ``renderer_prompt_ids`` is the
-    unexpanded logical prompt when ``process_multimodal=False`` and ``None``
-    otherwise.
+    sampling_mask, sampling_mask_logprobs, payload, multi_modal_data,
+    prompt_attribution. ``renderer_prompt_ids`` is the unexpanded logical
+    prompt when ``process_multimodal=False`` and ``None`` otherwise.
 
     ``prompt_attribution`` is the renderer's :class:`RenderedTokens` for
     the prompt — either the one this call computed via
@@ -433,6 +433,9 @@ def _prepare():
         "routed_experts": routed_experts,
         "sampling_mask": sampling_mask,
         "sampling_mask_logprobs": sampling_mask_logprobs,
+        # By-handle side arrays: segments of a shared payload file the inference
+        # server wrote instead of returning routed_experts / sampling_mask inline.
+        "payload": choice.get("payload"),
         # The mm sidecar consumed on the request side, surfaced back so
         # callers can persist it on the trajectory step for downstream
         # multi-turn bridging and training-sample construction.