feat(codex): use native Responses API for CN providers that support it

Several Chinese providers now expose a native OpenAI Responses API
endpoint, so Codex can reach them directly without the Responses->Chat
route-takeover conversion. Switch these presets to apiFormat
"openai_responses" and drop the now-unused codexChatReasoning and
modelCatalog (removing modelCatalog also keeps the "local route mapping"
toggle unchecked by default):

- Qwen / DashScope Bailian (/compatible-mode/v1/responses)
- Xiaomi MiMo + Token Plan (api.xiaomimimo.com/v1)
- Volcengine Doubao (/api/v3/responses)
- Meituan LongCat (/openai/v1)
- MiniMax CN + intl (/v1/responses, confirmed in the official API reference)

SiliconFlow-hosted MiniMax stays openai_chat (third-party endpoint, not
MiniMax's own base_url).

Also refresh stale model ids on the remaining chat-only providers:
GLM 5.1->5.2, StepFun 3.5-flash-2603->3.7-flash, Ling 2.5-1T->2.6-1T.

src/config/codexProviderPresets.ts

@@ -202,14 +202,8 @@ export const codexProviderPresets: CodexProviderPreset[] = [
       "doubao-seed-2-1-pro",
     ),
     endpointCandidates: ["https://ark.cn-beijing.volces.com/api/v3"],
-    apiFormat: "openai_chat",
+    // 火山方舟主数据面 /api/v3 原生支持 Responses API（/api/v3/responses），无需路由接管转换
-    modelCatalog: modelCatalog([
+    apiFormat: "openai_responses",
-      {
-        model: "doubao-seed-2-1-pro",
-        displayName: "Doubao Seed 2.1 Pro",
-        contextWindow: 256000,
-      },
-    ]),
     category: "cn_official",
     isPartner: true,
     partnerPromotionKey: "doubaoseed",
@@ -320,12 +314,12 @@ requires_openai_auth = true`,
     config: generateThirdPartyConfig(
       "zhipu_glm",
       "https://open.bigmodel.cn/api/coding/paas/v4",
-      "glm-5.1",
+      "glm-5.2",
     ),
     endpointCandidates: ["https://open.bigmodel.cn/api/coding/paas/v4"],
     apiFormat: "openai_chat",
     modelCatalog: modelCatalog([
-      { model: "glm-5.1", displayName: "GLM-5.1", contextWindow: 200000 },
+      { model: "glm-5.2", displayName: "GLM-5.2", contextWindow: 200000 },
     ]),
     codexChatReasoning: {
       supportsThinking: true,
@@ -346,12 +340,12 @@ requires_openai_auth = true`,
     config: generateThirdPartyConfig(
       "zhipu_glm_en",
       "https://api.z.ai/api/coding/paas/v4",
-      "glm-5.1",
+      "glm-5.2",
     ),
     endpointCandidates: ["https://api.z.ai/api/coding/paas/v4"],
     apiFormat: "openai_chat",
     modelCatalog: modelCatalog([
-      { model: "glm-5.1", displayName: "GLM-5.1", contextWindow: 200000 },
+      { model: "glm-5.2", displayName: "GLM-5.2", contextWindow: 200000 },
     ]),
     codexChatReasoning: {
       supportsThinking: true,
@@ -399,22 +393,8 @@ requires_openai_auth = true`,
       "qwen3-coder-plus",
     ),
     endpointCandidates: ["https://dashscope.aliyuncs.com/compatible-mode/v1"],
-    apiFormat: "openai_chat",
+    // 阿里百炼 DashScope 原生支持 OpenAI Responses API（/compatible-mode/v1/responses，同一 base_url），无需路由接管转换
-    modelCatalog: modelCatalog([
+    apiFormat: "openai_responses",
-      {
-        model: "qwen3-coder-plus",
-        displayName: "Qwen3 Coder Plus",
-        contextWindow: 1000000,
-      },
-      { model: "qwen3-max", displayName: "Qwen3 Max", contextWindow: 262144 },
-    ]),
-    codexChatReasoning: {
-      supportsThinking: true,
-      supportsEffort: false,
-      thinkingParam: "enable_thinking",
-      effortParam: "none",
-      outputFormat: "reasoning_content",
-    },
     category: "cn_official",
     icon: "bailian",
     iconColor: "#624AFF",
@@ -489,11 +469,16 @@ requires_openai_auth = true`,
     config: generateThirdPartyConfig(
       "stepfun",
       "https://api.stepfun.com/step_plan/v1",
-      "step-3.5-flash-2603",
+      "step-3.7-flash",
     ),
     endpointCandidates: ["https://api.stepfun.com/step_plan/v1"],
     apiFormat: "openai_chat",
     modelCatalog: modelCatalog([
+      {
+        model: "step-3.7-flash",
+        displayName: "Step 3.7 Flash",
+        contextWindow: 262144,
+      },
       {
         model: "step-3.5-flash-2603",
         displayName: "Step 3.5 Flash 2603",
@@ -517,11 +502,16 @@ requires_openai_auth = true`,
     config: generateThirdPartyConfig(
       "stepfun_en",
       "https://api.stepfun.ai/step_plan/v1",
-      "step-3.5-flash-2603",
+      "step-3.7-flash",
     ),
     endpointCandidates: ["https://api.stepfun.ai/step_plan/v1"],
     apiFormat: "openai_chat",
     modelCatalog: modelCatalog([
+      {
+        model: "step-3.7-flash",
+        displayName: "Step 3.7 Flash",
+        contextWindow: 262144,
+      },
       {
         model: "step-3.5-flash-2603",
         displayName: "Step 3.5 Flash 2603",
@@ -575,17 +565,11 @@ requires_openai_auth = true`,
     config: generateThirdPartyConfig(
       "longcat",
       "https://api.longcat.chat/openai/v1",
-      "LongCat-Flash-Chat",
+      "LongCat-2.0-Preview",
     ),
     endpointCandidates: ["https://api.longcat.chat/openai/v1"],
-    apiFormat: "openai_chat",
+    // 美团 LongCat 官方 Codex 文档用 wire_api=responses 对自家 base_url，原生 Responses，无需路由接管转换
-    modelCatalog: modelCatalog([
+    apiFormat: "openai_responses",
-      {
-        model: "LongCat-Flash-Chat",
-        displayName: "LongCat Flash Chat",
-        contextWindow: 262144,
-      },
-    ]),
     category: "cn_official",
     icon: "longcat",
     iconColor: "#29E154",
@@ -598,24 +582,11 @@ requires_openai_auth = true`,
     config: generateThirdPartyConfig(
       "minimax",
       "https://api.minimaxi.com/v1",
-      "MiniMax-M2.7",
+      "MiniMax-M3",
     ),
     endpointCandidates: ["https://api.minimaxi.com/v1"],
-    apiFormat: "openai_chat",
+    // MiniMax 官方 API 参考已列 /v1/responses 为正式端点（CN/intl 双区，POST /v1/responses），原生 Responses，无需路由接管转换
-    modelCatalog: modelCatalog([
+    apiFormat: "openai_responses",
-      {
-        model: "MiniMax-M2.7",
-        displayName: "MiniMax M2.7",
-        contextWindow: 200000,
-      },
-    ]),
-    codexChatReasoning: {
-      supportsThinking: true,
-      supportsEffort: false,
-      thinkingParam: "reasoning_split",
-      effortParam: "none",
-      outputFormat: "reasoning_details",
-    },
     category: "cn_official",
     partnerPromotionKey: "minimax_cn",
     theme: {
@@ -633,24 +604,11 @@ requires_openai_auth = true`,
     config: generateThirdPartyConfig(
       "minimax_en",
       "https://api.minimax.io/v1",
-      "MiniMax-M2.7",
+      "MiniMax-M3",
     ),
     endpointCandidates: ["https://api.minimax.io/v1"],
-    apiFormat: "openai_chat",
+    // MiniMax 官方 API 参考已列 /v1/responses 为正式端点（CN/intl 双区，POST /v1/responses），原生 Responses，无需路由接管转换
-    modelCatalog: modelCatalog([
+    apiFormat: "openai_responses",
-      {
-        model: "MiniMax-M2.7",
-        displayName: "MiniMax M2.7",
-        contextWindow: 200000,
-      },
-    ]),
-    codexChatReasoning: {
-      supportsThinking: true,
-      supportsEffort: false,
-      thinkingParam: "reasoning_split",
-      effortParam: "none",
-      outputFormat: "reasoning_details",
-    },
     category: "cn_official",
     partnerPromotionKey: "minimax_en",
     theme: {
@@ -668,15 +626,15 @@ requires_openai_auth = true`,
     config: generateThirdPartyConfig(
       "bailing",
       "https://api.tbox.cn/api/llm/v1",
-      "Ling-2.5-1T",
+      "Ling-2.6-1T",
     ),
     endpointCandidates: ["https://api.tbox.cn/api/llm/v1"],
     apiFormat: "openai_chat",
     modelCatalog: modelCatalog([
       {
-        model: "Ling-2.5-1T",
+        model: "Ling-2.6-1T",
-        displayName: "Ling-2.5-1T",
+        displayName: "Ling-2.6-1T",
-        contextWindow: 131072,
+        contextWindow: 262144,
       },
     ]),
     category: "cn_official",
@@ -692,21 +650,8 @@ requires_openai_auth = true`,
       "mimo-v2.5-pro",
     ),
     endpointCandidates: ["https://api.xiaomimimo.com/v1"],
-    apiFormat: "openai_chat",
+    // 小米 MiMo 官方 Codex 文档已声明原生支持 Responses API（wire_api=responses 对自家 base_url），无需路由接管转换
-    modelCatalog: modelCatalog([
+    apiFormat: "openai_responses",
-      {
-        model: "mimo-v2.5-pro",
-        displayName: "MiMo V2.5 Pro",
-        contextWindow: 1048576,
-      },
-    ]),
-    codexChatReasoning: {
-      supportsThinking: true,
-      supportsEffort: false,
-      thinkingParam: "thinking",
-      effortParam: "none",
-      outputFormat: "reasoning_content",
-    },
     category: "cn_official",
     icon: "xiaomimimo",
     iconColor: "#000000",
@@ -722,21 +667,8 @@ requires_openai_auth = true`,
       "mimo-v2.5-pro",
     ),
     endpointCandidates: ["https://token-plan-cn.xiaomimimo.com/v1"],
-    apiFormat: "openai_chat",
+    // 小米 MiMo 官方 Codex 文档已声明原生支持 Responses API（wire_api=responses 对自家 base_url），无需路由接管转换
-    modelCatalog: modelCatalog([
+    apiFormat: "openai_responses",
-      {
-        model: "mimo-v2.5-pro",
-        displayName: "MiMo V2.5 Pro",
-        contextWindow: 1048576,
-      },
-    ]),
-    codexChatReasoning: {
-      supportsThinking: true,
-      supportsEffort: false,
-      thinkingParam: "thinking",
-      effortParam: "none",
-      outputFormat: "reasoning_content",
-    },
     category: "cn_official",
     icon: "xiaomimimo",
     iconColor: "#000000",