diff --git a/recipes/glm-5-3-flash-qad-csf-on-2x-rtx-pro-6000-blackwell-tp2-dcp2-mtp3/recipe.yaml b/recipes/glm-5-3-flash-qad-csf-on-2x-rtx-pro-6000-blackwell-tp2-dcp2-mtp3/recipe.yaml
index 62c756660..fc89c71f9 100644
--- a/recipes/glm-5-3-flash-qad-csf-on-2x-rtx-pro-6000-blackwell-tp2-dcp2-mtp3/recipe.yaml
+++ b/recipes/glm-5-3-flash-qad-csf-on-2x-rtx-pro-6000-blackwell-tp2-dcp2-mtp3/recipe.yaml
@@ -115,3 +115,5 @@ provenance:
     - 'https://huggingface.co/local-inference-lab/GLM-5.3-Flash-NVFP4-MXFP8-CSF-QAD'
     - 'https://huggingface.co/local-inference-lab/GLM-5.3-Flash-NVFP4'
   notes: "Ingested by lar-scout (kanban t_1a24b45b) from the local-inference-lab #daily-summaries 2026-10-04T08:25Z summary of the 10-03 production config. Launch argv is the guild env summary expressed with this image's documented env knobs (SPECULATOR=mtp + MTP_DEPTH=3 verified from the LIL launcher's own release posts R29-R32; MTP_TOKENS in the scout card was a reconstruction error). ENGINE verification: image tag karmic-kraken-beta-20261003-a717f13e26c631e3 confirmed present on ghcr (matches beta commit a717f13e in the summary). Weights artifact reconciled: guild serves local-inference-lab/GLM-5.3-Flash-NVFP4-MXFP8-CSF-QAD (main @ fd660d51d1fc..., 188.87 GB); the card's revision pin cfd47bd7680e... is the head of the base repo's mtp-bf16 branch (verified) and is kept as upstream lineage, not the weights pin. Hardware: guild post says 2x RTX PRO 6000 WS 96GB; site carries only Max-Q variants of this card, so a plain WS 2x profile is created at ingest. gpu-memory-utilization 0.985 is the guild production value as reported (existing 4x recipes use 0.93)."
+max_context_len: 1048576
+kv_pool_tokens: 2053877