From 7819f96003ee825e162d778d7ac2d42ee25b1490 Mon Sep 17 00:00:00 2001 From: Vuong Hoang Date: Sat, 20 Jun 2026 10:14:28 -0700 Subject: [PATCH] =?UTF-8?q?feat(litellm):=20add=20gen-frontier=20/=20gen-f?= =?UTF-8?q?rontier-reasoning=20aliases=20(=E2=86=92=20GLM=205.2)?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Capability aliases for the PAID frontier tier, mirroring glm-5.2 / glm-5.2- reasoning (thinking off / on) → openai/glm-5.2 @ z.ai. Worldtree binds these for a frontier-grade generation/reasoning capability so the backing frontier model can be swapped gateway-side (operator jump-started WT's request). PAID: only all-proxy-models / explicitly-scoped keys reach them; the free all-agents-local key stays fenced off z.ai spend. Verified both resolve + route to GLM 5.2. --- stacks/litellm/conf/config.yaml | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/stacks/litellm/conf/config.yaml b/stacks/litellm/conf/config.yaml index 0bc5ad5..41d5513 100644 --- a/stacks/litellm/conf/config.yaml +++ b/stacks/litellm/conf/config.yaml @@ -257,6 +257,28 @@ model_list: extra_body: thinking: type: enabled + # gen-frontier / gen-frontier-reasoning: capability aliases for the PAID + # frontier tier (GLM 5.2 @ z.ai), mirroring glm-5.2 / glm-5.2-reasoning + # (thinking off / on). Worldtree binds these for frontier-grade generation + # / reasoning; swap the backing frontier model here, callers unaffected. + # PAID — only all-proxy-models / explicitly-scoped keys reach them; the free + # all-agents-local key is fenced off z.ai spend and cannot. + - model_name: gen-frontier + litellm_params: + model: openai/glm-5.2 + api_base: https://api.z.ai/api/coding/paas/v4 + api_key: os.environ/Z_AI_API_KEY + extra_body: + thinking: + type: disabled + - model_name: gen-frontier-reasoning + litellm_params: + model: openai/glm-5.2 + api_base: https://api.z.ai/api/coding/paas/v4 + api_key: os.environ/Z_AI_API_KEY + extra_body: + thinking: + type: enabled - model_name: glm-5-turbo litellm_params: model: openai/glm-5-turbo