From 10d3c7f88c7c04297cc83e20bdaf1ad726fa5f36 Mon Sep 17 00:00:00 2001
From: vibe-code <root@vibe-code.228998.xyz>
Date: Thu, 24 Sep 2026 15:37:56 +0800
Subject: [PATCH] =?UTF-8?q?fix(config):=20=E4=B8=BA=E7=81=AB=E5=B1=B1?=
 =?UTF-8?q?=E6=B8=A0=E9=81=93=E7=99=BD=E5=90=8D=E5=8D=95=20reasoning=5Feff?=
 =?UTF-8?q?ort=EF=BC=8C=E4=BF=AE=E5=A4=8D=E6=80=9D=E8=80=83=E5=BC=BA?=
 =?UTF-8?q?=E5=BA=A6=E8=A2=AB=E9=9D=99=E9=BB=98=E4=B8=A2=E5=BC=83?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

LiteLLM 的 VolcEngineChatConfig.get_supported_openai_params() 白名单不含
reasoning_effort，客户端一传就抛 UnsupportedParamsError；叠加 drop_params
后更糟 —— Router._deployment_params_with_request_reasoning_override 会先剥掉
部署侧 extra_body/thinking，drop_params 再把客户端参数丢掉，两者同归于尽，
上游 body 皆无该字段，方舟回落默认 high（静默失效）。

改动：17 个 volcengine 条目全部加 allowed_openai_params: [reasoning_effort]。
- 透传组（huoshan/deepseek-v4-*、doubao-seed-2-1-*、glm-5.2）：客户端显式指定生效
- 档位别名组（doubao-seed-nothink/-minimal/-low/-medium/-high、fanyi）：
  extra_body 钉死值为默认档位，客户端显式传参可覆盖；不传则走钉死档位

语义为「默认档位 + 客户端可覆盖」，非硬锁：LiteLLM 无纯配置手段实现强制覆盖。
实测依据见 config.yaml 注释（本地 echo 抓上游请求体）。
---
 config.yaml | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/config.yaml b/config.yaml
index cf28567..e662b77 100644
--- a/config.yaml
+++ b/config.yaml
@@ -44,6 +44,7 @@ model_list:
       model: volcengine/deepseek-v4-flash-ga-260731
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
 
   - model_name: huoshan/deepseek-v4-pro
@@ -52,6 +53,7 @@ model_list:
       model: volcengine/deepseek-v4-pro-ga-260813
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
   
         
@@ -63,6 +65,7 @@ model_list:
       model: volcengine/doubao-seed-2-1-turbo-260628
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
       extra_headers:
         Connection: "close"
@@ -76,6 +79,7 @@ model_list:
       model: volcengine/doubao-seed-2-1-pro-260628
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
       extra_headers:
         Connection: "close"
@@ -90,6 +94,17 @@ model_list:
       model: volcengine/glm-5-2-260617
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY 
+      # 方舟 glm-5-2-260617 支持 reasoning_effort（none/minimal/high/max，默认 high；
+      # 官方参数页 + 实测 curl 均确认），但 LiteLLM 的 VolcEngineChatConfig
+      # get_supported_openai_params() 白名单里没有它 —— 它是 openai-like 的固定
+      # 参数表，不含 reasoning_effort —— 客户端一传就抛 UnsupportedParamsError。
+      # allowed_openai_params 是官方逃生口：get_optional_params 用它在校验前
+      # extend supported_params，随后 _apply_openai_param_overrides 把该参数从
+      # non_default_params 原样写回 optional_params，最终透传到请求体。
+      # 不用 drop_params：那是把该模型所有不支持参数静默丢弃，会掩盖其它真错。
+      # 注意 thinking.type 无需此项，VolcEngineChatConfig 已原生白名单。
+      allowed_openai_params:
+        - reasoning_effort
       extra_headers:
         Connection: "close"
     model_info:
@@ -97,6 +112,21 @@ model_list:
       max_context_length: 1024000 # 上下文窗口上限
 
   #=======================豆包汇总nothink
+  # 【思考档位别名组】doubao-seed-nothink / -minimal / -low / -medium / -high / fanyi
+  # 语义：别名后缀即【默认】档位，非硬锁。
+  #   - 客户端不传 reasoning_effort：按 extra_body 钉的档位发给方舟。
+  #   - 客户端显式传 reasoning_effort：以客户端为准（覆盖默认档位）。
+  # 为什么钉不成硬锁（实测，本地 echo 抓上游 body）：
+  #   请求带 reasoning_effort 时，Router._deployment_params_with_request_reasoning_override
+  #   会【无条件】剥掉部署侧 extra_body.reasoning_effort / thinking；
+  #   此时若没有 allowed_openai_params 放行，drop_params 又把客户端这个参数丢掉，
+  #   两者同归于尽 ⇒ 上游 body 两者都没有 ⇒ 方舟回落默认 high（静默失效）。
+  #   故必须加 allowed_openai_params：让客户端值能通过校验，使结果至少是
+  #   「客户端说了算」而不是「悄悄变回 high」。
+  #   LiteLLM 当前无纯配置手段做到「不论客户端传什么一律覆盖」；要硬锁只能加
+  #   pre-call hook（本仓库当前不采用）。
+  # 注：方舟 doubao 上 minimal 等价于关闭思考（实测 reasoning_tokens=0），
+  #     故 nothink/minimal/fanyi 三个别名默认档位统一用 minimal。
 
 
   - model_name: doubao-seed-nothink
@@ -105,6 +135,7 @@ model_list:
       model: volcengine/doubao-seed-2-1-pro-260628
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
       extra_headers:
         Connection: "close"
@@ -117,6 +148,7 @@ model_list:
       model: volcengine/doubao-seed-2-1-turbo-260628
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
       extra_headers:
         Connection: "close"
@@ -134,6 +166,7 @@ model_list:
       model: volcengine/doubao-seed-2-1-pro-260628
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
       extra_headers:
         Connection: "close"
@@ -146,6 +179,7 @@ model_list:
       model: volcengine/doubao-seed-2-1-turbo-260628
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
       extra_headers:
         Connection: "close"
@@ -163,6 +197,7 @@ model_list:
       model: volcengine/doubao-seed-2-1-pro-260628
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
       extra_headers:
         Connection: "close"
@@ -175,6 +210,7 @@ model_list:
       model: volcengine/doubao-seed-2-1-turbo-260628
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
       extra_headers:
         Connection: "close"
@@ -191,6 +227,7 @@ model_list:
       model: volcengine/doubao-seed-2-1-pro-260628
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
       extra_headers:
         Connection: "close"
@@ -203,6 +240,7 @@ model_list:
       model: volcengine/doubao-seed-2-1-turbo-260628
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
       extra_headers:
         Connection: "close"
@@ -220,6 +258,7 @@ model_list:
       model: volcengine/doubao-seed-2-1-pro-260628
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
       extra_headers:
         Connection: "close"
@@ -232,6 +271,7 @@ model_list:
       model: volcengine/doubao-seed-2-1-turbo-260628
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
       extra_headers:
         Connection: "close"
@@ -247,6 +287,7 @@ model_list:
       model: volcengine/doubao-seed-2-1-pro-260628
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
       extra_headers:
         Connection: "close"
@@ -259,6 +300,7 @@ model_list:
       model: volcengine/doubao-seed-2-1-turbo-260628
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY
+      allowed_openai_params: ["reasoning_effort"]
       drop_params: true
       extra_headers:
         Connection: "close"