diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index af9110a..29c90f0 100644
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -275,7 +275,7 @@ jobs:
 
           **npm 全局安装**
           \`\`\`bash
-          npm install -g lingxiao_cli
+          npm install -g @lingxiao-office/lingxiao-coding
           lingxiao
           \`\`\`
           EOF
@@ -315,3 +315,34 @@ jobs:
           generate_release_notes: true
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+  # ── 发布到 npm ──────────────────────────────────────────────────
+  publish-npm:
+    name: Publish to npm
+    needs: [check-release, build-portable, build-binary, build-source]
+    runs-on: ubuntu-latest
+    if: needs.check-release.outputs.should_run == 'true'
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '24'
+          registry-url: 'https://registry.npmjs.org'
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Install web dependencies
+        run: cd web && npm ci
+
+      - name: Build package
+        run: npm run build:package
+        env:
+          LINGXIAO_SKIP_MODELS_SNAPSHOT: '1'
+
+      - name: Publish
+        run: npm publish --access public
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
diff --git a/README.md b/README.md
index ae58fee..07da86f 100644
--- a/README.md
+++ b/README.md
@@ -132,6 +132,13 @@ LingXiao 内置了 Claude Code Driver 和 Codex Driver，可以把 `claude` CLI
 - npm 或兼容包管理器
 ```
 
+### npm 全局安装（推荐）
+
+```bash
+npm install -g @lingxiao-office/lingxiao-coding
+lingxiao
+```
+
 ### 源码安装
 
 ```bash
diff --git a/VERSION b/VERSION
index 1cac385..f8f4f03 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-1.11.0
+1.12.1
diff --git a/package-lock.json b/package-lock.json
index bcb3522..47c9d65 100644
--- a/package-lock.json
+++ b/package-lock.json
@@ -1,18 +1,18 @@
 {
-  "name": "lingxiao_cli",
-  "version": "1.12.0",
+  "name": "@lingxiao-office/lingxiao-coding",
+  "version": "1.12.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
-      "name": "lingxiao_cli",
-      "version": "1.12.0",
+      "name": "@lingxiao-office/lingxiao-coding",
+      "version": "1.12.1",
       "cpu": [
         "x64",
         "arm64"
       ],
       "hasInstallScript": true,
-      "license": "UNLICENSED",
+      "license": "AGPL-3.0-only",
       "os": [
         "darwin",
         "linux",
@@ -38,6 +38,7 @@
         "@langfuse/client": "^5.5.3",
         "@langfuse/otel": "^5.5.3",
         "@langfuse/tracing": "^5.5.3",
+        "@lingxiao-office/sdk": "^1.0.1",
         "@lydell/node-pty": "1.2.0-beta.10",
         "@modelcontextprotocol/sdk": "^1.29.0",
         "@nodesecure/js-x-ray": "^11.1.0",
@@ -3418,6 +3419,82 @@
       "integrity": "sha512-XlK9dERP2n9afkJ23JyJzpmesLgiOHmhqKuGgeytnT+IVGFdAsYl1wLr2o+byXNAN5fveNbc7CCI6RfBsd5FCw==",
       "license": "MIT"
     },
+    "node_modules/@lingxiao-office/sdk": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmmirror.com/@lingxiao-office/sdk/-/sdk-1.0.1.tgz",
+      "integrity": "sha512-P89YQCsDgRxBdcCxmb85T8kIKKDmGhuq9RY+I948bQE9oKJbWJJV/Ilqg2xetO8xuYN3sX4n+yjPmyAndOUFVw==",
+      "license": "MIT",
+      "dependencies": {
+        "@ai-sdk/amazon-bedrock": "^3.0.101",
+        "@ai-sdk/anthropic": "^2.0.81",
+        "@ai-sdk/google": "^2.0.74",
+        "@ai-sdk/openai": "^2.0.106",
+        "@ai-sdk/provider": "^2.0.0",
+        "@ai-sdk/provider-utils": "^3.0.0",
+        "@anthropic-ai/sdk": "^0.82.0",
+        "@fastify/cors": "^11.2.0",
+        "@fastify/static": "^9.1.1",
+        "@fastify/websocket": "^11.2.0",
+        "@modelcontextprotocol/sdk": "^1.29.0",
+        "acorn": "^8.16.0",
+        "ai": "^5.0.198",
+        "ajv": "^8.17.1",
+        "chokidar": "^5.0.0",
+        "fastify": "^5.8.4",
+        "glob": "^13.0.6",
+        "js-tiktoken": "^1.0.21",
+        "node-fetch": "^3.3.2",
+        "openai": "^6.33.0",
+        "proxy-agent": "^8.0.1",
+        "simple-git": "^3.36.0",
+        "string-width": "^8.2.0",
+        "typescript": "^6.0.2",
+        "undici": "^8.0.2",
+        "yaml": "^2.9.0",
+        "zod": "^4.3.6"
+      },
+      "engines": {
+        "node": ">=24.0.0"
+      },
+      "optionalDependencies": {
+        "@ast-grep/lang-c": "^0.0.6",
+        "@ast-grep/lang-cpp": "^0.0.6",
+        "@ast-grep/lang-go": "^0.0.6",
+        "@ast-grep/lang-java": "^0.0.7",
+        "@ast-grep/lang-python": "^0.0.6",
+        "@ast-grep/lang-ruby": "^0.0.7",
+        "@ast-grep/lang-rust": "^0.0.7",
+        "@ast-grep/napi": "^0.42.2",
+        "@langfuse/client": "^5.5.3",
+        "@langfuse/otel": "^5.5.3",
+        "@langfuse/tracing": "^5.5.3",
+        "@lydell/node-pty": "1.2.0-beta.10",
+        "@lydell/node-pty-darwin-arm64": "1.2.0-beta.10",
+        "@lydell/node-pty-darwin-x64": "1.2.0-beta.10",
+        "@lydell/node-pty-linux-arm64": "1.2.0-beta.10",
+        "@lydell/node-pty-linux-x64": "1.2.0-beta.10",
+        "@lydell/node-pty-win32-arm64": "1.2.0-beta.10",
+        "@lydell/node-pty-win32-x64": "1.2.0-beta.10",
+        "@nodesecure/js-x-ray": "^11.1.0",
+        "@opentelemetry/api": "^1.9.1",
+        "@opentelemetry/sdk-node": "^0.219.0",
+        "@slidev/cli": "^52.15.2",
+        "@xterm/headless": "5.5.0",
+        "docx": "^9.7.1",
+        "exceljs": "^4.4.0",
+        "jszip": "^3.10.1",
+        "mammoth": "^1.12.0",
+        "pdf-lib": "^1.17.1",
+        "pdf-parse": "^2.4.5",
+        "pdfkit": "^0.18.0",
+        "playwright": "^1.59.1",
+        "pptxgenjs": "^4.0.1",
+        "sharp": "^0.34.5",
+        "skia-canvas": "^3.0.8",
+        "tesseract.js": "^7.0.0",
+        "unzipper": "^0.12.5"
+      }
+    },
     "node_modules/@lukeed/ms": {
       "version": "2.0.2",
       "resolved": "https://registry.npmmirror.com/@lukeed/ms/-/ms-2.0.2.tgz",
diff --git a/package.json b/package.json
index 8373755..ae32458 100644
--- a/package.json
+++ b/package.json
@@ -1,7 +1,7 @@
 {
-  "name": "lingxiao_cli",
-  "version": "1.12.0",
-  "description": "凌霄剑域 - 动态智能编排系统 (Node.js 版本)",
+  "name": "@lingxiao-office/lingxiao-coding",
+  "version": "1.12.1",
+  "description": "凌霄剑域 - 动态智能编排系统 (Node.js 版本) | Lingxiao Coding - Dynamic Agent Orchestration System",
   "main": "dist/index.js",
   "type": "module",
   "engines": {
@@ -63,9 +63,20 @@
     "README.md",
     "LICENSE"
   ],
-  "keywords": [],
-  "author": "",
-  "license": "UNLICENSED",
+  "keywords": [
+    "lingxiao",
+    "agent",
+    "ai",
+    "llm",
+    "cli",
+    "orchestration",
+    "coding-assistant",
+    "multi-agent",
+    "tool-calling",
+    "framework"
+  ],
+  "author": "Lingxiao Office",
+  "license": "AGPL-3.0-only",
   "devDependencies": {
     "@types/node": "^25.5.0",
     "@types/pdfkit": "^0.17.6",
@@ -97,10 +108,10 @@
     "@langfuse/client": "^5.5.3",
     "@langfuse/otel": "^5.5.3",
     "@langfuse/tracing": "^5.5.3",
+    "@lingxiao-office/sdk": "^1.0.1",
     "@lydell/node-pty": "1.2.0-beta.10",
     "@modelcontextprotocol/sdk": "^1.29.0",
     "@nodesecure/js-x-ray": "^11.1.0",
-    "electron-updater": "^6.8.9",
     "@opentelemetry/api": "^1.9.1",
     "@opentelemetry/sdk-node": "^0.219.0",
     "@slidev/cli": "^52.15.2",
@@ -111,6 +122,7 @@
     "chokidar": "^5.0.0",
     "commander": "^14.0.3",
     "docx": "^9.7.1",
+    "electron-updater": "^6.8.9",
     "exceljs": "^4.4.0",
     "fastify": "^5.8.4",
     "glob": "^13.0.6",
@@ -224,5 +236,17 @@
       ],
       "category": "Development"
     }
+  },
+  "homepage": "https://github.com/hexian2001/lingxiao-coding",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/hexian2001/lingxiao-coding.git"
+  },
+  "bugs": {
+    "url": "https://github.com/hexian2001/lingxiao-coding/issues"
+  },
+  "publishConfig": {
+    "access": "public",
+    "registry": "https://registry.npmjs.org/"
   }
 }
diff --git a/src/llm/models-snapshot.json b/src/llm/models-snapshot.json
index 213d326..77faa67 100644
--- a/src/llm/models-snapshot.json
+++ b/src/llm/models-snapshot.json
@@ -20516,8 +20516,8 @@
           "output": 262144
         },
         "cost": {
-          "input": 0.95,
-          "output": 4,
+          "input": 0.8,
+          "output": 3.4,
           "cache_read": 0.16
         }
       },
@@ -21295,14 +21295,14 @@
           "output": 131072
         },
         "cost": {
-          "input": 2,
-          "output": 6,
-          "cache_read": 0.4,
+          "input": 0.522,
+          "output": 1.044,
+          "cache_read": 0.0043,
           "tiers": [
             {
-              "input": 2,
-              "output": 6,
-              "cache_read": 0.4,
+              "input": 0.522,
+              "output": 1.044,
+              "cache_read": 0.0043,
               "tier": {
                 "type": "context",
                 "size": 256000
@@ -21310,9 +21310,9 @@
             }
           ],
           "context_over_200k": {
-            "input": 2,
-            "output": 6,
-            "cache_read": 0.4
+            "input": 0.522,
+            "output": 1.044,
+            "cache_read": 0.0043
           }
         }
       },
@@ -21523,7 +21523,7 @@
           "output": 131072
         },
         "cost": {
-          "input": 1.4,
+          "input": 1.38,
           "output": 4.4,
           "cache_read": 0.26
         }
@@ -21682,7 +21682,8 @@
         },
         "cost": {
           "input": 0.13,
-          "output": 0.85
+          "output": 0.85,
+          "cache_read": 0.025
         }
       },
       "zai-org/glm-4.7-flash": {
@@ -22069,7 +22070,7 @@
         "cost": {
           "input": 1.25,
           "output": 3.75,
-          "cache_read": 0.125,
+          "cache_read": 0.25,
           "cache_write": 1.5625
         }
       },
@@ -22502,8 +22503,8 @@
           "output": 65536
         },
         "cost": {
-          "input": 0.3,
-          "output": 1.3
+          "input": 0.38,
+          "output": 1.55
         }
       },
       "qwen/qwen3.5-397b-a17b": {
@@ -23021,9 +23022,9 @@
           "output": 393216
         },
         "cost": {
-          "input": 1.69,
-          "output": 3.38,
-          "cache_read": 0.13
+          "input": 1.6,
+          "output": 3.2,
+          "cache_read": 0.135
         }
       },
       "deepseek/deepseek-v3.2-exp": {
@@ -29570,6 +29571,284 @@
       }
     }
   },
+  "trustedrouter": {
+    "id": "trustedrouter",
+    "env": [
+      "TRUSTEDROUTER_API_KEY"
+    ],
+    "npm": "@ai-sdk/openai-compatible",
+    "api": "https://api.trustedrouter.com/v1",
+    "name": "TrustedRouter",
+    "doc": "https://trustedrouter.com/docs",
+    "models": {
+      "zdr": {
+        "id": "zdr",
+        "name": "Zero Data Retention",
+        "description": "TrustedRouter privacy routing alias that prefers zero data retention model endpoints.",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "none",
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-06-01",
+        "last_updated": "2026-06-27",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 131072
+        }
+      },
+      "e2e": {
+        "id": "e2e",
+        "name": "End-to-End Encrypted",
+        "description": "TrustedRouter privacy routing alias for end-to-end encrypted provider routes where available.",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "none",
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-06-01",
+        "last_updated": "2026-06-27",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 131072
+        }
+      },
+      "synth-code": {
+        "id": "synth-code",
+        "name": "Synth Code",
+        "description": "TrustedRouter code synthesis orchestration alias that combines multiple model responses into one answer.",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "none",
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-06-20",
+        "last_updated": "2026-06-27",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 131072
+        }
+      },
+      "fast": {
+        "id": "fast",
+        "name": "Fast",
+        "description": "TrustedRouter speed routing alias that prefers low-latency healthy model endpoints.",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "none",
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-06-01",
+        "last_updated": "2026-06-27",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 131072
+        }
+      },
+      "synth": {
+        "id": "synth",
+        "name": "Synth",
+        "description": "TrustedRouter synthesis orchestration alias that combines multiple model responses into one answer.",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "none",
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-06-20",
+        "last_updated": "2026-06-27",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 131072
+        }
+      },
+      "auto": {
+        "id": "auto",
+        "name": "Auto",
+        "description": "TrustedRouter automatic routing alias that chooses a healthy supported model endpoint for the request.",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "none",
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-05-01",
+        "last_updated": "2026-06-27",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 131072
+        }
+      },
+      "cheap": {
+        "id": "cheap",
+        "name": "Cheap",
+        "description": "TrustedRouter low-cost routing alias that prefers inexpensive healthy model endpoints.",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "none",
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-05-01",
+        "last_updated": "2026-06-27",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 131072
+        }
+      }
+    }
+  },
   "zhipuai": {
     "id": "zhipuai",
     "env": [
@@ -33953,14 +34232,74 @@
     "name": "StepFun AI",
     "doc": "https://platform.stepfun.ai/docs/en/step-plan/integrations/open-code",
     "models": {
+      "step-2-16k": {
+        "id": "step-2-16k",
+        "name": "Step 2 (16K)",
+        "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [],
+        "tool_call": true,
+        "temperature": true,
+        "knowledge": "2024-06",
+        "release_date": "2025-01-01",
+        "last_updated": "2026-02-13",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 16384,
+          "input": 16384,
+          "output": 8192
+        },
+        "cost": {
+          "input": 5.21,
+          "output": 16.44,
+          "cache_read": 1.04
+        }
+      },
+      "step-tts-2": {
+        "id": "step-tts-2",
+        "name": "Step TTS 2",
+        "description": "Speech generation model for controllable voice, narration, and audio delivery",
+        "family": "step",
+        "attachment": false,
+        "reasoning": false,
+        "tool_call": false,
+        "temperature": false,
+        "release_date": "2026-03-01",
+        "last_updated": "2026-07-02",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "audio"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 0,
+          "output": 0
+        }
+      },
       "step-3.5-flash": {
         "id": "step-3.5-flash",
         "name": "Step 3.5 Flash",
-        "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use",
+        "description": "StepFun flash lane for quick multimodal reasoning and coding assistance",
         "attachment": false,
         "reasoning": true,
         "reasoning_options": [],
         "tool_call": true,
+        "interleaved": {
+          "field": "reasoning_content"
+        },
         "temperature": true,
         "knowledge": "2025-01",
         "release_date": "2026-01-29",
@@ -33985,6 +34324,56 @@
           "cache_read": 0.02
         }
       },
+      "stepaudio-2.5-asr": {
+        "id": "stepaudio-2.5-asr",
+        "name": "StepAudio 2.5 ASR",
+        "description": "Speech transcription model for accurate audio-to-text and captioning workflows",
+        "family": "step",
+        "attachment": false,
+        "reasoning": false,
+        "tool_call": false,
+        "temperature": false,
+        "release_date": "2026-04-24",
+        "last_updated": "2026-07-02",
+        "modalities": {
+          "input": [
+            "audio"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 0,
+          "output": 0
+        }
+      },
+      "stepaudio-2.5-tts": {
+        "id": "stepaudio-2.5-tts",
+        "name": "StepAudio 2.5 TTS",
+        "description": "Speech generation model for controllable voice, narration, and audio delivery",
+        "family": "step",
+        "attachment": false,
+        "reasoning": false,
+        "tool_call": false,
+        "temperature": false,
+        "release_date": "2026-04-16",
+        "last_updated": "2026-07-02",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "audio"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 0,
+          "output": 0
+        }
+      },
       "step-3.5-flash-2603": {
         "id": "step-3.5-flash-2603",
         "name": "Step 3.5 Flash 2603",
@@ -34001,6 +34390,9 @@
           }
         ],
         "tool_call": true,
+        "interleaved": {
+          "field": "reasoning_content"
+        },
         "temperature": true,
         "knowledge": "2025-01",
         "release_date": "2026-04-02",
@@ -34024,6 +34416,83 @@
           "output": 0.3,
           "cache_read": 0.02
         }
+      },
+      "step-3.7-flash": {
+        "id": "step-3.7-flash",
+        "name": "Step 3.7 Flash",
+        "description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "interleaved": {
+          "field": "reasoning_content"
+        },
+        "temperature": true,
+        "knowledge": "2026-01-01",
+        "release_date": "2026-05-29",
+        "last_updated": "2026-06-29",
+        "modalities": {
+          "input": [
+            "text",
+            "image"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 256000,
+          "input": 256000,
+          "output": 256000
+        },
+        "cost": {
+          "input": 0.2,
+          "output": 1.15,
+          "cache_read": 0.04
+        }
+      },
+      "step-1-32k": {
+        "id": "step-1-32k",
+        "name": "Step 1 (32K)",
+        "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [],
+        "tool_call": true,
+        "temperature": true,
+        "knowledge": "2024-06",
+        "release_date": "2025-01-01",
+        "last_updated": "2026-02-13",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 32768,
+          "input": 32768,
+          "output": 32768
+        },
+        "cost": {
+          "input": 2.05,
+          "output": 9.59,
+          "cache_read": 0.41
+        }
       }
     }
   },
@@ -48913,21 +49382,33 @@
           "output": 4.48
         }
       },
-      "anthropic/claude-3.5-haiku": {
-        "id": "anthropic/claude-3.5-haiku",
-        "name": "Claude 3.5 Haiku",
-        "description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
+      "anthropic/claude-sonnet-5-free": {
+        "id": "anthropic/claude-sonnet-5-free",
+        "name": "Claude Sonnet 5 (Free)",
+        "description": "Everyday Claude agent model for coding, planning, browsing, and general work",
+        "family": "claude-sonnet",
         "attachment": true,
-        "reasoning": false,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
         "tool_call": true,
-        "temperature": true,
-        "knowledge": "2025-01-01",
-        "release_date": "2024-11-04",
-        "last_updated": "2024-11-04",
+        "temperature": false,
+        "knowledge": "2026-01-31",
+        "release_date": "2026-06-30",
+        "last_updated": "2026-06-30",
         "modalities": {
           "input": [
             "text",
-            "image"
+            "image",
+            "pdf"
           ],
           "output": [
             "text"
@@ -48935,46 +49416,35 @@
         },
         "open_weights": false,
         "limit": {
-          "context": 200000,
-          "output": 64000
+          "context": 1000000,
+          "output": 128000
         },
         "provider": {
           "npm": "@ai-sdk/anthropic",
           "api": "https://zenmux.ai/api/anthropic/v1"
         },
         "cost": {
-          "input": 0.8,
-          "output": 4,
-          "cache_read": 0.08,
-          "cache_write": 1
+          "input": 0,
+          "output": 0,
+          "cache_read": 0,
+          "cache_write": 0
         }
       },
-      "anthropic/claude-sonnet-4.5": {
-        "id": "anthropic/claude-sonnet-4.5",
-        "name": "Claude Sonnet 4.5",
-        "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
+      "anthropic/claude-3.5-haiku": {
+        "id": "anthropic/claude-3.5-haiku",
+        "name": "Claude 3.5 Haiku",
+        "description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
         "attachment": true,
-        "reasoning": true,
-        "reasoning_options": [
-          {
-            "type": "effort",
-            "values": [
-              "low",
-              "medium",
-              "high"
-            ]
-          }
-        ],
+        "reasoning": false,
         "tool_call": true,
         "temperature": true,
         "knowledge": "2025-01-01",
-        "release_date": "2025-09-29",
-        "last_updated": "2025-09-29",
+        "release_date": "2024-11-04",
+        "last_updated": "2024-11-04",
         "modalities": {
           "input": [
             "text",
-            "image",
-            "pdf"
+            "image"
           ],
           "output": [
             "text"
@@ -48982,7 +49452,7 @@
         },
         "open_weights": false,
         "limit": {
-          "context": 1000000,
+          "context": 200000,
           "output": 64000
         },
         "provider": {
@@ -48990,15 +49460,15 @@
           "api": "https://zenmux.ai/api/anthropic/v1"
         },
         "cost": {
-          "input": 3,
-          "output": 15,
-          "cache_read": 0.3,
-          "cache_write": 3.75
+          "input": 0.8,
+          "output": 4,
+          "cache_read": 0.08,
+          "cache_write": 1
         }
       },
-      "anthropic/claude-sonnet-4": {
-        "id": "anthropic/claude-sonnet-4",
-        "name": "Claude Sonnet 4",
+      "anthropic/claude-sonnet-4.5": {
+        "id": "anthropic/claude-sonnet-4.5",
+        "name": "Claude Sonnet 4.5",
         "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
         "attachment": true,
         "reasoning": true,
@@ -49015,11 +49485,58 @@
         "tool_call": true,
         "temperature": true,
         "knowledge": "2025-01-01",
-        "release_date": "2025-05-22",
-        "last_updated": "2025-05-22",
+        "release_date": "2025-09-29",
+        "last_updated": "2025-09-29",
         "modalities": {
           "input": [
-            "image",
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 64000
+        },
+        "provider": {
+          "npm": "@ai-sdk/anthropic",
+          "api": "https://zenmux.ai/api/anthropic/v1"
+        },
+        "cost": {
+          "input": 3,
+          "output": 15,
+          "cache_read": 0.3,
+          "cache_write": 3.75
+        }
+      },
+      "anthropic/claude-sonnet-4": {
+        "id": "anthropic/claude-sonnet-4",
+        "name": "Claude Sonnet 4",
+        "description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "temperature": true,
+        "knowledge": "2025-01-01",
+        "release_date": "2025-05-22",
+        "last_updated": "2025-05-22",
+        "modalities": {
+          "input": [
+            "image",
             "text",
             "pdf"
           ],
@@ -49079,6 +49596,54 @@
           "cache_write": 1.25
         }
       },
+      "anthropic/claude-sonnet-5": {
+        "id": "anthropic/claude-sonnet-5",
+        "name": "Claude Sonnet 5",
+        "description": "Everyday Claude agent model for coding, planning, browsing, and general work",
+        "family": "claude-sonnet",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "temperature": false,
+        "knowledge": "2026-01-31",
+        "release_date": "2026-06-30",
+        "last_updated": "2026-06-30",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 128000
+        },
+        "provider": {
+          "npm": "@ai-sdk/anthropic",
+          "api": "https://zenmux.ai/api/anthropic/v1"
+        },
+        "cost": {
+          "input": 2,
+          "output": 10,
+          "cache_read": 0.2,
+          "cache_write": 4
+        }
+      },
       "anthropic/claude-opus-4.7": {
         "id": "anthropic/claude-opus-4.7",
         "name": "Claude Opus 4.7",
@@ -50437,6 +51002,882 @@
       }
     }
   },
+  "kenari": {
+    "id": "kenari",
+    "env": [
+      "KENARI_API_KEY"
+    ],
+    "npm": "@ai-sdk/openai-compatible",
+    "api": "https://kenari.id/v1",
+    "name": "Kenari",
+    "doc": "https://kenari.id/docs",
+    "models": {
+      "deepseek-v4-flash": {
+        "id": "deepseek-v4-flash",
+        "name": "DeepSeek V4 Flash",
+        "description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
+        "family": "deepseek-flash",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "high",
+              "xhigh"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "knowledge": "2025-05",
+        "release_date": "2026-04-24",
+        "last_updated": "2026-04-24",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 1000000,
+          "output": 384000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "kimi-k2-6": {
+        "id": "kimi-k2-6",
+        "name": "Kimi K2.6",
+        "description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
+        "family": "kimi-k2",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "knowledge": "2025-01",
+        "release_date": "2026-04-21",
+        "last_updated": "2026-04-21",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "video"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 262144,
+          "output": 262144
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "glm-5-1": {
+        "id": "glm-5-1",
+        "name": "GLM-5.1",
+        "description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
+        "family": "glm",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-04-07",
+        "last_updated": "2026-04-07",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 200000,
+          "output": 131072
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "gemma-4-31b-it": {
+        "id": "gemma-4-31b-it",
+        "name": "Gemma 4 31B IT",
+        "description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
+        "family": "gemma",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-04-02",
+        "last_updated": "2026-04-02",
+        "modalities": {
+          "input": [
+            "text",
+            "image"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 262144,
+          "output": 32768
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "grok-4-3": {
+        "id": "grok-4-3",
+        "name": "Grok 4.3",
+        "description": "xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk",
+        "family": "grok",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "none",
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-04-17",
+        "last_updated": "2026-04-17",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 30000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "qwen3-7-plus": {
+        "id": "qwen3-7-plus",
+        "name": "Qwen3.7 Plus",
+        "description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
+        "family": "qwen",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [],
+        "tool_call": true,
+        "temperature": true,
+        "knowledge": "2025-04",
+        "release_date": "2026-06-02",
+        "last_updated": "2026-06-02",
+        "modalities": {
+          "input": [
+            "text",
+            "image"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 64000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "kimi-k2-7-code": {
+        "id": "kimi-k2-7-code",
+        "name": "Kimi K2.7 Code",
+        "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
+        "family": "kimi-k2",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": false,
+        "knowledge": "2025-01",
+        "release_date": "2026-06-12",
+        "last_updated": "2026-06-12",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "video"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 262144,
+          "output": 262144
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "deepseek-v4-pro": {
+        "id": "deepseek-v4-pro",
+        "name": "DeepSeek V4 Pro",
+        "description": "Open MoE flagship with million-token context for coding and long agent runs",
+        "family": "deepseek-thinking",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "high",
+              "xhigh"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "knowledge": "2025-05",
+        "release_date": "2026-04-24",
+        "last_updated": "2026-04-24",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 1000000,
+          "output": 384000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "deepseek-v4-flash:free": {
+        "id": "deepseek-v4-flash:free",
+        "name": "DeepSeek V4 Flash (Free)",
+        "description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
+        "family": "deepseek-flash",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "high",
+              "xhigh"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "knowledge": "2025-05",
+        "release_date": "2026-04-24",
+        "last_updated": "2026-04-24",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 1000000,
+          "output": 384000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "claude-opus-4-7": {
+        "id": "claude-opus-4-7",
+        "name": "Claude Opus 4.7",
+        "description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
+        "family": "claude-opus",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "temperature": false,
+        "knowledge": "2026-01-31",
+        "release_date": "2026-04-16",
+        "last_updated": "2026-04-16",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 128000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "minimax-m3": {
+        "id": "minimax-m3",
+        "name": "MiniMax-M3",
+        "description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
+        "family": "minimax",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [],
+        "tool_call": true,
+        "temperature": true,
+        "release_date": "2026-06-01",
+        "last_updated": "2026-06-01",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "video"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 512000,
+          "output": 128000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "claude-opus-4-8": {
+        "id": "claude-opus-4-8",
+        "name": "Claude Opus 4.8",
+        "description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
+        "family": "claude-opus",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "temperature": false,
+        "release_date": "2026-05-28",
+        "last_updated": "2026-05-28",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 128000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "gpt-5-4-mini": {
+        "id": "gpt-5-4-mini",
+        "name": "GPT-5.4 mini",
+        "description": "Strong small GPT for coding subagents, quick tool use, and high-volume work",
+        "family": "gpt-mini",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "none",
+              "low",
+              "medium",
+              "high",
+              "xhigh"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": false,
+        "knowledge": "2025-08-31",
+        "release_date": "2026-03-17",
+        "last_updated": "2026-03-17",
+        "modalities": {
+          "input": [
+            "text",
+            "image"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 400000,
+          "input": 272000,
+          "output": 128000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "mimo-v2-5": {
+        "id": "mimo-v2-5",
+        "name": "MiMo-V2.5",
+        "description": "Open MiMo model for multimodal coding agents and long-context automation",
+        "family": "mimo",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [],
+        "tool_call": true,
+        "temperature": true,
+        "knowledge": "2024-12",
+        "release_date": "2026-04-22",
+        "last_updated": "2026-04-22",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "audio",
+            "video"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 1048576,
+          "output": 131072
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "gpt-oss-120b": {
+        "id": "gpt-oss-120b",
+        "name": "GPT OSS 120B",
+        "description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
+        "family": "gpt-oss",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2025-08-05",
+        "last_updated": "2025-08-05",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 131072,
+          "output": 32768
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "gpt-5-5": {
+        "id": "gpt-5-5",
+        "name": "GPT-5.5",
+        "description": "Default frontier GPT for coding, computer use, research, and knowledge work",
+        "family": "gpt",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "none",
+              "low",
+              "medium",
+              "high",
+              "xhigh"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": false,
+        "knowledge": "2025-12-01",
+        "release_date": "2026-04-23",
+        "last_updated": "2026-04-23",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1050000,
+          "input": 922000,
+          "output": 128000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "glm-5-2": {
+        "id": "glm-5-2",
+        "name": "GLM-5.2",
+        "description": "Open flagship GLM for long-horizon coding agents and million-token context work",
+        "family": "glm",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "high",
+              "xhigh"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-06-13",
+        "last_updated": "2026-06-13",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 1000000,
+          "output": 131072
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "grok-build-0-1": {
+        "id": "grok-build-0-1",
+        "name": "Grok Build 0.1",
+        "description": "Fast Grok coding model tuned for agentic engineering and iterative edits",
+        "family": "grok-build",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "release_date": "2026-04-16",
+        "last_updated": "2026-04-16",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 256000,
+          "output": 256000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "claude-sonnet-4-6": {
+        "id": "claude-sonnet-4-6",
+        "name": "Claude Sonnet 4.6",
+        "description": "Claude workhorse for coding agents, careful analysis, and production cost control",
+        "family": "claude-sonnet",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high",
+              "max"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "temperature": true,
+        "knowledge": "2025-08-31",
+        "release_date": "2026-02-17",
+        "last_updated": "2026-03-13",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 64000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "gpt-oss-20b": {
+        "id": "gpt-oss-20b",
+        "name": "GPT OSS 20B",
+        "description": "Open-weight GPT reasoning model for self-hosted agents and controllable deployments",
+        "family": "gpt-oss",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "release_date": "2025-08-05",
+        "last_updated": "2025-08-05",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 131072,
+          "output": 32768
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "mimo-v2-5-pro": {
+        "id": "mimo-v2-5-pro",
+        "name": "MiMo-V2.5-Pro",
+        "description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
+        "family": "mimo",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [],
+        "tool_call": true,
+        "temperature": true,
+        "knowledge": "2024-12",
+        "release_date": "2026-04-22",
+        "last_updated": "2026-04-22",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 1048576,
+          "output": 131072
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "deepseek-v4-pro:free": {
+        "id": "deepseek-v4-pro:free",
+        "name": "DeepSeek V4 Pro (Free)",
+        "description": "Open MoE flagship with million-token context for coding and long agent runs",
+        "family": "deepseek-thinking",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "high",
+              "xhigh"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "knowledge": "2025-05",
+        "release_date": "2026-04-24",
+        "last_updated": "2026-04-24",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 1000000,
+          "output": 384000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
+      "gpt-image-2": {
+        "id": "gpt-image-2",
+        "name": "GPT-Image-2",
+        "description": "Image model for prompt-driven generation, editing, and visual design workflows",
+        "family": "gpt-image",
+        "attachment": true,
+        "reasoning": false,
+        "tool_call": false,
+        "temperature": false,
+        "release_date": "2026-04-21",
+        "last_updated": "2026-04-21",
+        "modalities": {
+          "input": [
+            "text",
+            "image"
+          ],
+          "output": [
+            "image"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 272000,
+          "output": 16384
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      }
+    }
+  },
   "openai": {
     "id": "openai",
     "env": [
@@ -73911,10 +75352,10 @@
           "output": 1000000
         },
         "cost": {
-          "input": 3,
-          "output": 15,
-          "cache_read": 0.3,
-          "cache_write": 3.75
+          "input": 2,
+          "output": 10,
+          "cache_read": 0.2,
+          "cache_write": 2.5
         }
       },
       "grok-4-1-fast-non-reasoning": {
@@ -92094,6 +93535,7 @@
           "context": 131072,
           "output": 131072
         },
+        "status": "deprecated",
         "cost": {
           "input": 0,
           "output": 0
@@ -102819,6 +104261,9 @@
           }
         ],
         "tool_call": true,
+        "interleaved": {
+          "field": "reasoning_content"
+        },
         "temperature": true,
         "knowledge": "2026-01-01",
         "release_date": "2026-05-29",
@@ -102860,6 +104305,9 @@
           }
         ],
         "tool_call": true,
+        "interleaved": {
+          "field": "reasoning_content"
+        },
         "temperature": true,
         "knowledge": "2025-01",
         "release_date": "2026-04-02",
@@ -102884,6 +104332,56 @@
           "cache_read": 0.02
         }
       },
+      "stepaudio-2.5-tts": {
+        "id": "stepaudio-2.5-tts",
+        "name": "StepAudio 2.5 TTS",
+        "description": "Speech generation model for controllable voice, narration, and audio delivery",
+        "family": "step",
+        "attachment": false,
+        "reasoning": false,
+        "tool_call": false,
+        "temperature": false,
+        "release_date": "2026-04-16",
+        "last_updated": "2026-07-02",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "audio"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 0,
+          "output": 0
+        }
+      },
+      "stepaudio-2.5-asr": {
+        "id": "stepaudio-2.5-asr",
+        "name": "StepAudio 2.5 ASR",
+        "description": "Speech transcription model for accurate audio-to-text and captioning workflows",
+        "family": "step",
+        "attachment": false,
+        "reasoning": false,
+        "tool_call": false,
+        "temperature": false,
+        "release_date": "2026-04-24",
+        "last_updated": "2026-07-02",
+        "modalities": {
+          "input": [
+            "audio"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 0,
+          "output": 0
+        }
+      },
       "step-3.5-flash": {
         "id": "step-3.5-flash",
         "name": "Step 3.5 Flash",
@@ -102892,6 +104390,9 @@
         "reasoning": true,
         "reasoning_options": [],
         "tool_call": true,
+        "interleaved": {
+          "field": "reasoning_content"
+        },
         "temperature": true,
         "knowledge": "2025-01",
         "release_date": "2026-01-29",
@@ -102916,6 +104417,31 @@
           "cache_read": 0.02
         }
       },
+      "step-tts-2": {
+        "id": "step-tts-2",
+        "name": "Step TTS 2",
+        "description": "Speech generation model for controllable voice, narration, and audio delivery",
+        "family": "step",
+        "attachment": false,
+        "reasoning": false,
+        "tool_call": false,
+        "temperature": false,
+        "release_date": "2026-03-01",
+        "last_updated": "2026-07-02",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "audio"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 0,
+          "output": 0
+        }
+      },
       "step-2-16k": {
         "id": "step-2-16k",
         "name": "Step 2 (16K)",
@@ -115042,6 +116568,52 @@
           "output": 0
         }
       },
+      "duo-chat-fable-5": {
+        "id": "duo-chat-fable-5",
+        "name": "Agentic Chat (Claude Fable 5)",
+        "description": "Claude model for creative writing, analysis, and controlled agent workflows",
+        "family": "claude-fable",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "temperature": false,
+        "knowledge": "2026-01-31",
+        "release_date": "2026-06-09",
+        "last_updated": "2026-06-09",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 128000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0,
+          "cache_read": 0,
+          "cache_write": 0
+        }
+      },
       "duo-chat-gpt-5-5": {
         "id": "duo-chat-gpt-5-5",
         "name": "Agentic Chat (GPT-5.5)",
@@ -115284,6 +116856,55 @@
           "output": 0
         }
       },
+      "duo-chat-sonnet-5": {
+        "id": "duo-chat-sonnet-5",
+        "name": "Agentic Chat (Claude Sonnet 5)",
+        "description": "Everyday Claude agent model for coding, planning, browsing, and general work",
+        "family": "claude-sonnet",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "toggle"
+          },
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "temperature": false,
+        "knowledge": "2026-01-31",
+        "release_date": "2026-06-30",
+        "last_updated": "2026-06-30",
+        "modalities": {
+          "input": [
+            "text",
+            "image",
+            "pdf"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 1000000,
+          "output": 64000
+        },
+        "cost": {
+          "input": 0,
+          "output": 0,
+          "cache_read": 0,
+          "cache_write": 0
+        }
+      },
       "duo-chat-gpt-5-4-mini": {
         "id": "duo-chat-gpt-5-4-mini",
         "name": "Agentic Chat (GPT-5.4 Mini)",
@@ -132479,7 +134100,7 @@
         "temperature": true,
         "knowledge": "2023-12",
         "release_date": "2024-12-06",
-        "last_updated": "2024-12-06",
+        "last_updated": "2026-07-02",
         "modalities": {
           "input": [
             "text"
@@ -132494,8 +134115,8 @@
           "output": 131072
         },
         "cost": {
-          "input": 0.88,
-          "output": 0.88
+          "input": 1.04,
+          "output": 1.04
         }
       },
       "moonshotai/Kimi-K2.6": {
@@ -132680,7 +134301,7 @@
         "tool_call": true,
         "temperature": true,
         "release_date": "2026-05-21",
-        "last_updated": "2026-06-15",
+        "last_updated": "2026-07-02",
         "modalities": {
           "input": [
             "text"
@@ -133207,7 +134828,7 @@
         "temperature": true,
         "knowledge": "2025-11",
         "release_date": "2026-04-07",
-        "last_updated": "2026-04-07",
+        "last_updated": "2026-07-02",
         "modalities": {
           "input": [
             "text"
@@ -135423,9 +137044,9 @@
           "output": 262144
         },
         "cost": {
-          "input": 0.55,
-          "output": 3.2,
-          "cache_read": 0.11
+          "input": 0.66,
+          "output": 3.41,
+          "cache_read": 0.14
         }
       },
       "moonshotai/kimi-k2-0905": {
@@ -137160,6 +138781,36 @@
           "output": 0.62
         }
       },
+      "poolside/laguna-xs-2.1:free": {
+        "id": "poolside/laguna-xs-2.1:free",
+        "name": "Laguna XS 2.1 (free)",
+        "description": "Free provider route for experiments, demos, and cost-sensitive chat workloads",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [],
+        "tool_call": true,
+        "structured_output": false,
+        "temperature": true,
+        "release_date": "2026-07-02",
+        "last_updated": "2026-07-02",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 262144,
+          "output": 32768
+        },
+        "cost": {
+          "input": 0,
+          "output": 0
+        }
+      },
       "poolside/laguna-xs.2": {
         "id": "poolside/laguna-xs.2",
         "name": "Laguna XS.2",
@@ -137255,6 +138906,37 @@
           "cache_read": 0.1
         }
       },
+      "poolside/laguna-xs-2.1": {
+        "id": "poolside/laguna-xs-2.1",
+        "name": "Laguna XS 2.1",
+        "description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [],
+        "tool_call": true,
+        "structured_output": false,
+        "temperature": true,
+        "release_date": "2026-07-02",
+        "last_updated": "2026-07-02",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 262144,
+          "output": 32768
+        },
+        "cost": {
+          "input": 0.06,
+          "output": 0.12,
+          "cache_read": 0.03
+        }
+      },
       "poolside/laguna-m.1:free": {
         "id": "poolside/laguna-m.1:free",
         "name": "Laguna M.1 (free)",
@@ -143193,9 +144875,9 @@
           "output": 262144
         },
         "cost": {
-          "input": 0.55,
-          "output": 3.2,
-          "cache_read": 0.11
+          "input": 0.66,
+          "output": 3.41,
+          "cache_read": 0.14
         }
       },
       "relace/relace-search": {
@@ -144099,8 +145781,8 @@
           "output": 32768
         },
         "cost": {
-          "input": 0.08,
-          "output": 0.5
+          "input": 0.117,
+          "output": 0.455
         }
       },
       "qwen/qwen3.7-plus": {
@@ -146095,7 +147777,7 @@
           "output": 16384
         },
         "cost": {
-          "input": 0.09,
+          "input": 0.089,
           "output": 0.18,
           "cache_read": 0.018
         }
@@ -162032,6 +163714,54 @@
           "cache_read": 0.125
         }
       },
+      "claude-opus-4-8": {
+        "id": "claude-opus-4-8",
+        "name": "Claude Opus 4.8",
+        "description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
+        "family": "claude-opus",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "toggle"
+          },
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "interleaved": true,
+        "temperature": false,
+        "release_date": "2026-05-28",
+        "last_updated": "2026-05-28",
+        "modalities": {
+          "input": [
+            "text",
+            "image"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 200000,
+          "output": 32000
+        },
+        "cost": {
+          "input": 5,
+          "output": 25,
+          "cache_read": 0.5,
+          "cache_write": 6.25
+        }
+      },
       "gemini-3.1-pro-preview-customtools": {
         "id": "gemini-3.1-pro-preview-customtools",
         "name": "Gemini 3.1 Pro Preview Custom Tools",
@@ -163207,6 +164937,56 @@
           "output": 0.2
         }
       },
+      "claude-opus-4-8-think": {
+        "id": "claude-opus-4-8-think",
+        "name": "Claude Opus 4.8",
+        "description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
+        "family": "claude-opus",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "toggle"
+          },
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high",
+              "xhigh",
+              "max"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "interleaved": {
+          "field": "reasoning_content"
+        },
+        "temperature": false,
+        "release_date": "2026-05-28",
+        "last_updated": "2026-05-28",
+        "modalities": {
+          "input": [
+            "text",
+            "image"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 200000,
+          "output": 32000
+        },
+        "cost": {
+          "input": 5,
+          "output": 25,
+          "cache_read": 0.5,
+          "cache_write": 6.25
+        }
+      },
       "qwen3.6-max-preview": {
         "id": "qwen3.6-max-preview",
         "name": "Qwen3.6 Max Preview",
@@ -189130,6 +190910,41 @@
           "input_audio": 1.5
         }
       },
+      "kimi-k2.7-code": {
+        "id": "kimi-k2.7-code",
+        "name": "Kimi K2.7 Code",
+        "description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
+        "family": "kimi-k2",
+        "attachment": true,
+        "reasoning": true,
+        "reasoning_options": [],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": false,
+        "knowledge": "2025-01",
+        "release_date": "2026-06-12",
+        "last_updated": "2026-06-12",
+        "modalities": {
+          "input": [
+            "text",
+            "image"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": true,
+        "limit": {
+          "context": 256000,
+          "input": 224000,
+          "output": 32000
+        },
+        "cost": {
+          "input": 0.95,
+          "output": 4,
+          "cache_read": 0.19
+        }
+      },
       "claude-sonnet-5": {
         "id": "claude-sonnet-5",
         "name": "Claude Sonnet 5",
@@ -189278,6 +191093,49 @@
           "cache_write": 6.25
         }
       },
+      "mai-code-1-flash-picker": {
+        "id": "mai-code-1-flash-picker",
+        "name": "MAI-Code-1-Flash",
+        "description": "Microsoft coding model built for fast, efficient assistance in everyday developer workflows",
+        "family": "mai",
+        "attachment": false,
+        "reasoning": true,
+        "reasoning_options": [
+          {
+            "type": "effort",
+            "values": [
+              "low",
+              "medium",
+              "high"
+            ]
+          }
+        ],
+        "tool_call": true,
+        "structured_output": true,
+        "temperature": true,
+        "knowledge": "2025-12",
+        "release_date": "2026-06-02",
+        "last_updated": "2026-06-08",
+        "modalities": {
+          "input": [
+            "text"
+          ],
+          "output": [
+            "text"
+          ]
+        },
+        "open_weights": false,
+        "limit": {
+          "context": 256000,
+          "input": 128000,
+          "output": 128000
+        },
+        "cost": {
+          "input": 0.75,
+          "output": 4.5,
+          "cache_read": 0.075
+        }
+      },
       "gpt-5.2": {
         "id": "gpt-5.2",
         "name": "GPT-5.2",
diff --git a/web/package-lock.json b/web/package-lock.json
index 17ac22d..e873f34 100644
--- a/web/package-lock.json
+++ b/web/package-lock.json
@@ -1,12 +1,12 @@
 {
   "name": "lingxiao-web",
-  "version": "1.12.0",
+  "version": "1.12.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "lingxiao-web",
-      "version": "1.12.0",
+      "version": "1.12.1",
       "dependencies": {
         "@monaco-editor/react": "^4.7.0",
         "@xterm/addon-fit": "^0.11.0",
diff --git a/web/package.json b/web/package.json
index ca5edb2..4a051c8 100644
--- a/web/package.json
+++ b/web/package.json
@@ -1,7 +1,7 @@
 {
   "name": "lingxiao-web",
   "private": true,
-  "version": "1.12.0",
+  "version": "1.12.1",
   "type": "module",
   "scripts": {
     "dev": "vite",
diff --git a/web/src/components/settings/SettingsView.tsx b/web/src/components/settings/SettingsView.tsx
index 75969cc..4a96d14 100644
--- a/web/src/components/settings/SettingsView.tsx
+++ b/web/src/components/settings/SettingsView.tsx
@@ -196,7 +196,7 @@ export default function SettingsView() {
               search={navSearch}
               onSearchChange={setNavSearch}
             />
-            <div className="min-w-0 flex-1 overflow-y-auto lg:h-full lg:pr-1">
+            <div className="settings-panel min-w-0 flex-1 overflow-y-auto rounded-lg border border-border-default bg-bg-primary/80 p-4 shadow-sm lg:h-full lg:pr-1">
               {renderSection()}
             </div>
           </div>
diff --git a/web/src/components/sidebar/SidebarVersionBadge.tsx b/web/src/components/sidebar/SidebarVersionBadge.tsx
index 902b376..48db5af 100644
--- a/web/src/components/sidebar/SidebarVersionBadge.tsx
+++ b/web/src/components/sidebar/SidebarVersionBadge.tsx
@@ -29,9 +29,16 @@ async function fetchVersionCheck(): Promise<VersionCheckData> {
 /**
  * 侧边栏版本号徽章
  *
- * 显示当前版本号 v1.0.0，如果有新版本则显示橙色小圆点提示。
+ * 显示当前版本号（构建期注入），如果有新版本则显示橙色小圆点提示。
  * 点击版本号或圆点可触发更新对话框（UpdateNotification 组件监听 CustomEvent）。
  */
+// 构建期注入的版本号，用于立即展示（避免冷启动显示 '—'）
+declare const __APP_VERSION__: string;
+const BUILD_VERSION: string =
+  typeof __APP_VERSION__ === 'string' && __APP_VERSION__.length > 0
+    ? __APP_VERSION__
+    : '';
+
 export function SidebarVersionBadge() {
   const [versionInfo, setVersionInfo] = useState<VersionCheckData | null>(null);
 
@@ -53,7 +60,8 @@ export function SidebarVersionBadge() {
     };
   }, []);
 
-  const currentVersion = versionInfo?.current ?? '—';
+  // API 回来前用构建期版本兜底，避免显示 '—'
+  const currentVersion = (versionInfo?.current ?? BUILD_VERSION) || '—';
   const hasUpdate = versionInfo?.hasUpdate ?? false;
 
   const handleClick = () => {