From e2bdd2471188450114697926e4d1e373be9f65cb Mon Sep 17 00:00:00 2001 From: "ming01.wang" Date: Thu, 8 Oct 2026 07:36:18 +0800 Subject: [PATCH] fix: stop the GLM quota policy from rejecting long contexts 57 of the 68 "incomplete generation" rollouts were never truncated by the provider: the local broker refused the request with 413 REQUEST_EXCEEDS_INTERNAL_TPM. It reserves UTF-8 body bytes as tokens (about 3.7x the real count) and rejects any single request above tpm, so tpm 500000 ended every trajectory once its context passed ~135k tokens, mostly the long pose/mde/seg ones. GLM-5.3 accepts far longer contexts. Raise the default GLM tpm to 2000000, as the Qwen group already uses. Production configs and the stored ledger policy are updated alongside. Co-Authored-By: Claude Opus 5.5 --- config.yaml | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/config.yaml b/config.yaml index 74bbddd..50e5893 100644 --- a/config.yaml +++ b/config.yaml @@ -106,7 +106,9 @@ collection_v1: glm-coding-account: max_concurrency: 1 rpm: 4 - tpm: 500000 + # The broker reserves UTF-8 bytes as tokens (~3.7x real) and rejects any + # single request above tpm; 500000 killed contexts past ~135k tokens. + tpm: 2000000 lifecycle: version: collection-v1-phase-budgets-2 ordinary_tool_deadline_s: 300