@zwbigi/ink-xy 0.1.2 → 0.1.4

package/inkos/packages/core/src/llm/providers/endpoints/wenxin.ts

@@ -0,0 +1,106 @@
+/**
+ * 百度文心 (ERNIE)
+ *
+ * - 官网：https://cloud.baidu.com/product/wenxinworkshop
+ * - 控制台 / API key：https://console.bce.baidu.com/qianfan/ais/console/applicationConsole/application/v2
+ * - API 文档：https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html
+ */
+import type { InkosEndpoint } from "../types.js";
+
+export const WENXIN: InkosEndpoint = {
+  id: "wenxin",
+  label: "文心一言 (千帆)",
+  group: "china",
+  api: "openai-completions",
+  baseUrl: "https://qianfan.baidubce.com/v2",
+  checkModel: "ernie-3.5-8k",
+  temperatureRange: [0, 1],
+  defaultTemperature: 0.95,
+  writingTemperature: 0.95,
+  models: [
+    { id: "ernie-5.0-thinking-latest", maxOutput: 65536, contextWindowTokens: 131072, enabled: true, releasedAt: "2025-11-12" },
+    { id: "ernie-5.0-thinking-preview", maxOutput: 65536, contextWindowTokens: 131072, releasedAt: "2025-11-12" },
+    { id: "ernie-4.5-turbo-128k", maxOutput: 12288, contextWindowTokens: 131072, enabled: true },
+    { id: "ernie-4.5-turbo-128k-preview", maxOutput: 12288, contextWindowTokens: 131072 },
+    { id: "ernie-4.5-turbo-32k", maxOutput: 12288, contextWindowTokens: 32768 },
+    { id: "ernie-4.5-turbo-latest", maxOutput: 12288, contextWindowTokens: 131072 },
+    { id: "ernie-speed-pro-128k", maxOutput: 4096, contextWindowTokens: 131072 },
+    { id: "ernie-lite-pro-128k", maxOutput: 4096, contextWindowTokens: 131072 },
+    { id: "ernie-char-8k", maxOutput: 2048, contextWindowTokens: 8192 },
+    { id: "ernie-char-fiction-8k", maxOutput: 2048, contextWindowTokens: 8192 },
+    { id: "ernie-char-fiction-8k-preview", maxOutput: 2048, contextWindowTokens: 8192 },
+    { id: "ernie-novel-8k", maxOutput: 2048, contextWindowTokens: 8192 },
+    { id: "ernie-4.5-0.3b", maxOutput: 8192, contextWindowTokens: 131072 },
+    { id: "ernie-4.5-21b-a3b", maxOutput: 8192, contextWindowTokens: 131072 },
+    { id: "ernie-4.5-21b-a3b-thinking", maxOutput: 8192, contextWindowTokens: 131072 },
+    { id: "ernie-4.5-vl-28b-a3b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "qianfan-8b", maxOutput: 16384, contextWindowTokens: 32768 },
+    { id: "qianfan-70b", maxOutput: 16384, contextWindowTokens: 32768 },
+    { id: "qianfan-agent-intent-32k", maxOutput: 4096, contextWindowTokens: 32768 },
+    { id: "qianfan-agent-lite-8k", maxOutput: 2048, contextWindowTokens: 8192 },
+    { id: "ernie-4.5-turbo-vl-preview", maxOutput: 16384, contextWindowTokens: 131072 },
+    { id: "ernie-4.5-turbo-vl", maxOutput: 16384, contextWindowTokens: 131072 },
+    { id: "ernie-4.5-turbo-vl-32k", maxOutput: 12288, contextWindowTokens: 32768 },
+    { id: "ernie-4.5-turbo-vl-32k-preview", maxOutput: 16384, contextWindowTokens: 32768 },
+    { id: "ernie-4.5-turbo-vl-latest", maxOutput: 16384, contextWindowTokens: 131072 },
+    { id: "ernie-4.5-8k-preview", maxOutput: 2048, contextWindowTokens: 8192 },
+    { id: "ernie-x1.1", maxOutput: 65536, contextWindowTokens: 65536, enabled: true },
+    { id: "ernie-x1.1-preview", maxOutput: 65536, contextWindowTokens: 65536 },
+    { id: "ernie-x1-turbo-32k", maxOutput: 28160, contextWindowTokens: 32768 },
+    { id: "ernie-x1-turbo-32k-preview", maxOutput: 28160, contextWindowTokens: 32768 },
+    { id: "qianfan-composition", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "qianfan-check-vl", maxOutput: 131072, contextWindowTokens: 131072 },
+    { id: "qianfan-multipicocr", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qianfan-vl-70b", maxOutput: 28672, contextWindowTokens: 32768 },
+    { id: "qianfan-vl-8b", maxOutput: 28672, contextWindowTokens: 32768 },
+    { id: "qianfan-llama-vl-8b", maxOutput: 16384, contextWindowTokens: 32768 },
+    { id: "qianfan-qi-vl", maxOutput: 131072, contextWindowTokens: 131072 },
+    { id: "qianfan-engcard-vl", maxOutput: 4000, contextWindowTokens: 4096 },
+    { id: "qianfan-singlepicocr", maxOutput: 4096, contextWindowTokens: 4096 },
+    { id: "internvl3-38b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "internvl3-14b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "internvl3-1b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "internvl2.5-38b-mpo", maxOutput: 4096, contextWindowTokens: 32768 },
+    { id: "qwen3-vl-32b-instruct", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qwen3-vl-32b-thinking", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qwen3-vl-8b-instruct", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qwen3-vl-8b-thinking", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qwen3-vl-30b-a3b-instruct", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qwen3-vl-30b-a3b-thinking", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qwen3-vl-235b-a22b-instruct", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qwen3-vl-235b-a22b-thinking", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qwen2.5-vl-32b-instruct", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "qwen2.5-vl-7b-instruct", maxOutput: 4096, contextWindowTokens: 16384 },
+    { id: "glm-4.5v", maxOutput: 16384, contextWindowTokens: 65536 },
+    { id: "deepseek-vl2", maxOutput: 2048, contextWindowTokens: 4096 },
+    { id: "deepseek-vl2-small", maxOutput: 2048, contextWindowTokens: 4096 },
+    { id: "deepseek-v3.2-think", maxOutput: 32768, contextWindowTokens: 144000 },
+    { id: "deepseek-v3.1-think-250821", maxOutput: 32768, contextWindowTokens: 144000 },
+    { id: "deepseek-r1-250528", maxOutput: 32768, contextWindowTokens: 144000 },
+    { id: "deepseek-r1", maxOutput: 32768, contextWindowTokens: 144000 },
+    { id: "deepseek-r1-distill-qianfan-70b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "deepseek-r1-distill-qianfan-8b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "deepseek-r1-distill-qianfan-llama-70b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "deepseek-r1-distill-llama-70b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "deepseek-r1-distill-qwen-32b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "deepseek-r1-distill-qwen-14b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "deepseek-r1-distill-qwen-7b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "deepseek-r1-distill-qwen-1.5b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "qwen3-next-80b-a3b-thinking", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qwen3-235b-a22b-thinking-2507", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qwen3-30b-a3b-thinking-2507", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qwq-32b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "kimi-k2-instruct", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qwen3-coder-480b-a35b-instruct", maxOutput: 65536, contextWindowTokens: 131072 },
+    { id: "qwen3-235b-a22b-instruct-2507", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qwen3-30b-a3b-instruct-2507", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "qwen3-30b-a3b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "qwen3-32b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "qwen3-14b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "qwen3-8b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "qwen3-4b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "qwen3-1.7b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "qwen3-0.6b", maxOutput: 8192, contextWindowTokens: 32768 },
+    { id: "qwen2.5-7b-instruct", maxOutput: 8192, contextWindowTokens: 32768 },
+  ],
+};

package/inkos/packages/core/src/llm/providers/endpoints/xai.ts

@@ -0,0 +1,34 @@
+/**
+ * xAI (Grok)
+ *
+ * - 官网：https://x.ai/
+ * - 控制台 / API key：https://console.x.ai/
+ * - API 文档：https://docs.x.ai/docs/overview
+ * - 模型列表：https://docs.x.ai/docs/models
+ */
+import type { InkosEndpoint } from "../types.js";
+
+export const XAI: InkosEndpoint = {
+  id: "xai",
+  label: "xAI (Grok)",
+  group: "overseas",
+  api: "openai-completions",
+  baseUrl: "https://api.x.ai/v1",
+  checkModel: "grok-2-1212",
+  temperatureRange: [0, 2],
+  defaultTemperature: 1,
+  writingTemperature: 1,
+  models: [
+    { id: "grok-4.20-beta-0309-reasoning", maxOutput: 4096, contextWindowTokens: 2000000, enabled: true, releasedAt: "2026-03-09" },
+    { id: "grok-4.20-beta-0309-non-reasoning", maxOutput: 4096, contextWindowTokens: 2000000, enabled: true, releasedAt: "2026-03-09" },
+    { id: "grok-4.20-multi-agent-beta-0309", maxOutput: 4096, contextWindowTokens: 2000000, enabled: true, releasedAt: "2026-03-09" },
+    { id: "grok-4-1-fast-non-reasoning", maxOutput: 4096, contextWindowTokens: 2000000, enabled: true, releasedAt: "2025-11-20" },
+    { id: "grok-4-1-fast-reasoning", maxOutput: 4096, contextWindowTokens: 2000000, enabled: true, releasedAt: "2025-11-20" },
+    { id: "grok-4-fast-non-reasoning", maxOutput: 4096, contextWindowTokens: 2000000, releasedAt: "2025-09-09" },
+    { id: "grok-4-fast-reasoning", maxOutput: 4096, contextWindowTokens: 2000000, releasedAt: "2025-09-09" },
+    { id: "grok-code-fast-1", maxOutput: 4096, contextWindowTokens: 256000, releasedAt: "2025-08-27" },
+    { id: "grok-4", maxOutput: 4096, contextWindowTokens: 256000, releasedAt: "2025-07-09" },
+    { id: "grok-3", maxOutput: 4096, contextWindowTokens: 131072, releasedAt: "2025-04-03" },
+    { id: "grok-3-mini", maxOutput: 4096, contextWindowTokens: 131072, releasedAt: "2025-04-03" },
+  ],
+};

package/inkos/packages/core/src/llm/providers/endpoints/xiaomimimo.ts

@@ -0,0 +1,26 @@
+/**
+ * 小米 MiMo
+ *
+ * - 官网：https://api-ai.xiaomi.com/
+ * - API 端点：https://api-ai.xiaomi.com/v1 (OpenAI 兼容)
+ * - 模型卡 (HuggingFace)：https://huggingface.co/XiaomiMiMo
+ *
+ * MiMo 是小米自研模型系列，除小米官方 /v1 外，也在 PPIO / 百炼等第三方平台开放。
+ */
+import type { InkosEndpoint } from "../types.js";
+
+export const XIAOMI_MIMO: InkosEndpoint = {
+  id: "xiaomimimo",
+  label: "小米 MiMo",
+  group: "china",
+  api: "openai-completions",
+  baseUrl: "https://api-ai.xiaomi.com/v1",
+  temperatureRange: [0, 2],
+  defaultTemperature: 0.7,
+  writingTemperature: 1,
+  models: [
+    { id: "mimo-v2-pro", maxOutput: 131072, contextWindowTokens: 1000000, enabled: true, releasedAt: "2026-03-18" },
+    { id: "mimo-v2-omni", maxOutput: 131072, contextWindowTokens: 262144, enabled: true, releasedAt: "2026-03-18" },
+    { id: "mimo-v2-flash", maxOutput: 65536, contextWindowTokens: 262144, enabled: true, releasedAt: "2026-03-03" },
+  ],
+};

package/inkos/packages/core/src/llm/providers/endpoints/zeroone.ts

@@ -0,0 +1,34 @@
+/**
+ * 零一万物 (01.AI / Yi)
+ *
+ * - 官网：https://www.lingyiwanwu.com/
+ * - 控制台 / API key：https://platform.lingyiwanwu.com/apikeys
+ * - API 文档：https://platform.lingyiwanwu.com/docs
+ */
+import type { InkosEndpoint } from "../types.js";
+
+export const ZEROONE: InkosEndpoint = {
+  id: "zeroone",
+  label: "零一万物 (01.AI)",
+  group: "china",
+  api: "openai-completions",
+  baseUrl: "https://api.lingyiwanwu.com/v1",
+  checkModel: "yi-lightning",
+  temperatureRange: [0, 2],
+  defaultTemperature: 0.3,
+  writingTemperature: 1,
+  models: [
+    { id: "yi-lightning", maxOutput: 4096, contextWindowTokens: 16384, enabled: true },
+    { id: "yi-vision-v2", maxOutput: 4096, contextWindowTokens: 16384, enabled: true },
+    { id: "yi-spark", maxOutput: 4096, contextWindowTokens: 16384 },
+    { id: "yi-medium", maxOutput: 4096, contextWindowTokens: 16384 },
+    { id: "yi-medium-200k", maxOutput: 4096, contextWindowTokens: 200000 },
+    { id: "yi-large-turbo", maxOutput: 4096, contextWindowTokens: 16384 },
+    { id: "yi-large-rag", maxOutput: 4096, contextWindowTokens: 16384 },
+    { id: "yi-large-fc", maxOutput: 4096, contextWindowTokens: 32768 },
+    { id: "yi-large", maxOutput: 4096, contextWindowTokens: 32768 },
+    { id: "yi-vision", maxOutput: 4096, contextWindowTokens: 16384 },
+    { id: "yi-large-preview", maxOutput: 4096, contextWindowTokens: 16384 },
+    { id: "yi-lightning-lite", maxOutput: 4096, contextWindowTokens: 16384 },
+  ],
+};

package/inkos/packages/core/src/llm/providers/endpoints/zhipu.ts

@@ -0,0 +1,61 @@
+/**
+ * 智谱 GLM (Zhipu AI)
+ *
+ * - 官网：https://www.bigmodel.cn/
+ * - 控制台：https://open.bigmodel.cn/
+ * - API key：https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys
+ * - API 文档：https://docs.bigmodel.cn/cn/api/normal-model/glm-4
+ * - 模型列表：https://open.bigmodel.cn/dev/howuse/model
+ */
+import type { InkosEndpoint } from "../types.js";
+
+export const ZHIPU: InkosEndpoint = {
+  id: "zhipu",
+  label: "智谱 GLM",
+  group: "china",
+  api: "openai-completions",
+  baseUrl: "https://open.bigmodel.cn/api/paas/v4",
+  checkModel: "glm-4-flash",
+  temperatureRange: [0, 1],
+  defaultTemperature: 0.95,
+  writingTemperature: 0.95,
+  models: [
+    { id: "glm-5.1", maxOutput: 131072, contextWindowTokens: 200000, enabled: true, releasedAt: "2026-03-27" },
+    { id: "glm-5-turbo", maxOutput: 131072, contextWindowTokens: 200000, releasedAt: "2026-03-15" },
+    { id: "glm-5", maxOutput: 131072, contextWindowTokens: 200000, enabled: true, releasedAt: "2026-02-12" },
+    { id: "glm-4.7", maxOutput: 131072, contextWindowTokens: 200000, releasedAt: "2025-12-22" },
+    { id: "glm-4.7-flash", maxOutput: 131072, contextWindowTokens: 200000, enabled: true, releasedAt: "2026-01-19" },
+    { id: "glm-4.7-flashx", maxOutput: 131072, contextWindowTokens: 200000, releasedAt: "2026-01-19" },
+    { id: "glm-5v-turbo", maxOutput: 131072, contextWindowTokens: 200000, enabled: true, releasedAt: "2026-04-02" },
+    { id: "glm-4.6v", maxOutput: 32768, contextWindowTokens: 131072, releasedAt: "2025-12-08" },
+    { id: "glm-4.6v-flashx", maxOutput: 32768, contextWindowTokens: 131072, releasedAt: "2025-12-08" },
+    { id: "glm-4.6v-flash", maxOutput: 32768, contextWindowTokens: 131072, releasedAt: "2025-12-08" },
+    { id: "glm-4.6", maxOutput: 131072, contextWindowTokens: 200000, releasedAt: "2025-09-08" },
+    { id: "glm-4.5v", maxOutput: 16384, contextWindowTokens: 65536 },
+    { id: "glm-4.5", maxOutput: 98304, contextWindowTokens: 131072 },
+    { id: "glm-4.5-x", maxOutput: 98304, contextWindowTokens: 131072 },
+    { id: "glm-4.5-air", maxOutput: 98304, contextWindowTokens: 131072 },
+    { id: "glm-4.5-airx", maxOutput: 98304, contextWindowTokens: 131072 },
+    { id: "glm-4.1v-thinking-flashx", maxOutput: 32768, contextWindowTokens: 65536 },
+    { id: "glm-4.1v-thinking-flash", maxOutput: 32768, contextWindowTokens: 65536 },
+    { id: "glm-zero-preview", maxOutput: 4096, contextWindowTokens: 16384 },
+    { id: "glm-z1-air", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "glm-z1-airx", maxOutput: 32768, contextWindowTokens: 32768 },
+    { id: "glm-z1-flashx", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "glm-z1-flash", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "glm-4-flash", maxOutput: 32768, contextWindowTokens: 131072, enabled: true },
+    { id: "glm-4-flash-250414", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "glm-4-flashx", maxOutput: 4095, contextWindowTokens: 131072 },
+    { id: "glm-4-long", maxOutput: 4095, contextWindowTokens: 1024000 },
+    { id: "glm-4-air-250414", maxOutput: 16384, contextWindowTokens: 131072 },
+    { id: "glm-4-airx", maxOutput: 4095, contextWindowTokens: 8192 },
+    { id: "glm-4-plus", maxOutput: 4095, contextWindowTokens: 131072 },
+    { id: "glm-4-0520", maxOutput: 4096, contextWindowTokens: 131072 },
+    { id: "glm-4v-flash", maxOutput: 1024, contextWindowTokens: 4096, releasedAt: "2024-12-09" },
+    { id: "glm-4v-plus-0111", maxOutput: 8192, contextWindowTokens: 16000 },
+    { id: "glm-4v", maxOutput: 1024, contextWindowTokens: 4096 },
+    { id: "codegeex-4", maxOutput: 32768, contextWindowTokens: 131072 },
+    { id: "charglm-4", maxOutput: 4000, contextWindowTokens: 8192 },
+    { id: "emohaa", maxOutput: 4000, contextWindowTokens: 8192 },
+  ],
+};

package/inkos/packages/core/src/llm/providers/index.ts

@@ -0,0 +1,71 @@
+import type { InkosEndpoint } from "./types.js";
+import { ANTHROPIC } from "./endpoints/anthropic.js";
+import { OPENAI } from "./endpoints/openai.js";
+import { GOOGLE } from "./endpoints/google.js";
+import { DEEPSEEK } from "./endpoints/deepseek.js";
+import { MINIMAX } from "./endpoints/minimax.js";
+// B1
+import { MOONSHOT } from "./endpoints/moonshot.js";
+import { ZHIPU } from "./endpoints/zhipu.js";
+import { SILICONCLOUD } from "./endpoints/siliconcloud.js";
+import { BAILIAN } from "./endpoints/bailian.js";
+import { VOLCENGINE } from "./endpoints/volcengine.js";
+import { HUNYUAN } from "./endpoints/hunyuan.js";
+import { BAICHUAN } from "./endpoints/baichuan.js";
+import { STEPFUN } from "./endpoints/stepfun.js";
+import { WENXIN } from "./endpoints/wenxin.js";
+// B2
+import { SPARK } from "./endpoints/spark.js";
+import { SENSENOVA } from "./endpoints/sensenova.js";
+import { TENCENTCLOUD } from "./endpoints/tencentcloud.js";
+import { XIAOMI_MIMO } from "./endpoints/xiaomimimo.js";
+import { LONGCAT } from "./endpoints/longcat.js";
+import { INTERNLM } from "./endpoints/internlm.js";
+import { ZEROONE } from "./endpoints/zeroone.js";
+import { AI360 } from "./endpoints/ai360.js";
+// B4
+import { OLLAMA } from "./endpoints/ollama.js";
+import { OPENROUTER } from "./endpoints/openrouter.js";
+import { CUSTOM } from "./endpoints/custom.js";
+import { MISTRAL } from "./endpoints/mistral.js";
+import { XAI } from "./endpoints/xai.js";
+import { NEWAPI } from "./endpoints/newapi.js";
+import { GITHUB_COPILOT } from "./endpoints/githubCopilot.js";
+import { KKAIAPI } from "./endpoints/kkaiapi.js";
+// B6 CodingPlan
+import { KIMI_CODING_PLAN } from "./endpoints/kimiCodingPlan.js";
+import { KIMI_CODE } from "./endpoints/kimiCode.js";
+import { MINIMAX_CODING_PLAN } from "./endpoints/minimaxCodingPlan.js";
+import { BAILIAN_CODING_PLAN } from "./endpoints/bailianCodingPlan.js";
+import { GLM_CODING_PLAN } from "./endpoints/glmCodingPlan.js";
+import { VOLCENGINE_CODING_PLAN } from "./endpoints/volcengineCodingPlan.js";
+import { OPENCODE_CODING_PLAN } from "./endpoints/opencodeCodingPlan.js";
+import { ASTRON_CODING_PLAN } from "./endpoints/astronCodingPlan.js";
+
+export type { InkosEndpoint, InkosModel, ApiProtocol, EndpointGroup } from "./types.js";
+
+/**
+ * 所有已注册 provider 的扁平列表。顺序定义了 lookup Layer 2 的遍历顺序，
+ * 但 Layer 2 还会按 PROVIDER_PRIORITY 显式排序，所以此处顺序不影响结果。
+ */
+const ALL_PROVIDERS: readonly InkosEndpoint[] = [
+  ANTHROPIC, OPENAI, GOOGLE, DEEPSEEK, MINIMAX,
+  MOONSHOT, ZHIPU, SILICONCLOUD, BAILIAN, VOLCENGINE, HUNYUAN, BAICHUAN, STEPFUN, WENXIN,
+  SPARK, SENSENOVA, TENCENTCLOUD, XIAOMI_MIMO, LONGCAT, INTERNLM,
+  ZEROONE, AI360,
+  OLLAMA, OPENROUTER, CUSTOM, MISTRAL, XAI, NEWAPI, GITHUB_COPILOT, KKAIAPI,
+  // B6 CodingPlan（8 个）
+  KIMI_CODING_PLAN, KIMI_CODE, MINIMAX_CODING_PLAN, BAILIAN_CODING_PLAN, GLM_CODING_PLAN, VOLCENGINE_CODING_PLAN, OPENCODE_CODING_PLAN, ASTRON_CODING_PLAN,
+];
+
+const PROVIDERS_BY_ID: Map<string, InkosEndpoint> = new Map(
+  ALL_PROVIDERS.map((p) => [p.id, p]),
+);
+
+export function getAllEndpoints(): readonly InkosEndpoint[] {
+  return ALL_PROVIDERS;
+}
+
+export function getEndpoint(id: string): InkosEndpoint | undefined {
+  return PROVIDERS_BY_ID.get(id);
+}

package/inkos/packages/core/src/llm/providers/lookup.ts

@@ -0,0 +1,70 @@
+import type { InkosModel } from "./types.js";
+import { getAllEndpoints, getEndpoint } from "./index.js";
+
+/**
+ * provider id 优先级。Layer 2 全局扫时同 id 多条匹配按这个顺序取第一条，
+ * 保证结果确定性。白名单外的 provider 视同 999（排最后）。
+ */
+const PROVIDER_PRIORITY: readonly string[] = [
+  "anthropic", "openai", "google", "deepseek", "bailian", "moonshot", "kimicode",
+  "zhipu", "minimax", "xai",
+  "siliconcloud",
+  "openrouter", "aihubmix", "novita",
+];
+
+/**
+ * 两层 lookup：
+ * - Layer 1: 已知 provider 精确查（整串比较，不拆斜线）
+ * - Layer 2: 全局扫所有 provider 的 models，按 provider id 优先级取第一条
+ * - 都 miss: 返回 undefined，调用方走保守默认
+ *
+ * 不做斜线前缀拆分。lobe 的 processModelList 证实了"靠调用入口带 provider 消歧"
+ * 是对的做法，斜线拆分对 PPIO / SiliconCloud 原生命名会误匹配。
+ */
+export function lookupModel(
+  serviceId: string,
+  modelId: string,
+): InkosModel | undefined {
+  const lowerId = modelId.toLowerCase();
+
+  const provider = getEndpoint(serviceId);
+  if (provider) {
+    const hit = provider.models.find((m) => m.id.toLowerCase() === lowerId);
+    if (hit) return hit;
+  }
+
+  const matches: Array<{ model: InkosModel; providerId: string }> = [];
+  for (const p of getAllEndpoints()) {
+    const hit = p.models.find((m) => m.id.toLowerCase() === lowerId);
+    if (hit) matches.push({ model: hit, providerId: p.id });
+  }
+  if (matches.length === 0) return undefined;
+
+  matches.sort((a, b) => {
+    const ai = PROVIDER_PRIORITY.indexOf(a.providerId);
+    const bi = PROVIDER_PRIORITY.indexOf(b.providerId);
+    return (ai === -1 ? 999 : ai) - (bi === -1 ? 999 : bi);
+  });
+  return matches[0].model;
+}
+
+/** 某 service 下可用（enabled !== false）的模型列表 */
+export function listEnabledModels(serviceId: string): InkosModel[] {
+  const provider = getEndpoint(serviceId);
+  if (!provider) return [];
+  return provider.models.filter((m) => m.enabled !== false);
+}
+
+export function isActiveTextModel(model: InkosModel): boolean {
+  if (model.enabled === false) return false;
+  if (model.status === "disabled" || model.status === "deprecated" || model.status === "nonText") return false;
+  if (model.capabilities?.text === false) return false;
+  if (model.capabilities?.imageOutput === true && model.capabilities?.text !== true) return false;
+  return true;
+}
+
+export function listActiveTextModels(serviceId: string): InkosModel[] {
+  const provider = getEndpoint(serviceId);
+  if (!provider) return [];
+  return provider.models.filter(isActiveTextModel);
+}

package/inkos/packages/core/src/llm/providers/probe.ts

@@ -0,0 +1,35 @@
+import { fetchWithProxy } from "../../utils/proxy-fetch.js";
+
+/**
+ * 通用 OpenAI 兼容 /models 探针。
+ * 任何失败（网络错、超时、非 JSON、非 2xx）一律返回空数组，不抛异常。
+ */
+
+export interface ProbedModel {
+  readonly id: string;
+  readonly name: string;
+  readonly contextWindow: number;
+}
+
+export async function probeModelsFromUpstream(
+  baseUrl: string,
+  apiKey: string,
+  timeoutMs = 10_000,
+): Promise<ReadonlyArray<ProbedModel>> {
+  if (!baseUrl) return [];
+  try {
+    const modelsUrl = baseUrl.replace(/\/$/, "") + "/models";
+    const res = await fetchWithProxy(modelsUrl, {
+      headers: apiKey ? { Authorization: `Bearer ${apiKey}` } : {},
+      signal: AbortSignal.timeout(timeoutMs),
+    });
+    if (!res.ok) return [];
+    const json = (await res.json()) as { data?: Array<{ id: unknown }> };
+    if (!Array.isArray(json.data)) return [];
+    return json.data
+      .filter((m): m is { id: string } => typeof m.id === "string" && m.id.length > 0)
+      .map((m) => ({ id: m.id, name: m.id, contextWindow: 0 }));
+  } catch {
+    return [];
+  }
+}

package/inkos/packages/core/src/llm/providers/types.ts

@@ -0,0 +1,89 @@
+/**
+ * inkos 自维护的 provider 定义。每个 provider 一个 .ts 文件，
+ * 里面一个 InkosEndpoint 对象（provider 元数据 + models 数组）。
+ *
+ * 数据冷启动自 lobe-chat/packages/model-bank，之后由 inkos 自管。
+ * 新模型发布 / 参数调整时手动加 card，不做持续 sync。
+ */
+
+export type ApiProtocol =
+  | "openai-completions"
+  | "openai-responses"
+  | "anthropic-messages"
+  | "google-generative-ai";
+
+export type EndpointGroup =
+  | "overseas"
+  | "china"
+  | "aggregator"
+  | "local"
+  | "codingPlan";
+
+export interface InkosModel {
+  /** API 请求体里实际用的 model id（可能带斜线如 'deepseek/deepseek-v3'）。UI 也直接用 id 显示 */
+  readonly id: string;
+  /** 模型输出上限 tokens */
+  readonly maxOutput: number;
+  /** 上下文窗口总 tokens */
+  readonly contextWindowTokens: number;
+  /** 默认 true。false 表示 lobe 标记此模型不可用 */
+  readonly enabled?: boolean;
+  /** CodingPlan 专用：API 调用时用这个代替 id 作为 model 字段 */
+  readonly deploymentName?: string;
+  /** 发布日期 ISO 字符串，可选（用于 UI 的"新模型"徽章） */
+  readonly releasedAt?: string;
+  /**
+   * API 硬要求的 temperature 值（例：Moonshot kimi-k2.5/k2.6 强制 1，违反直接 400）。
+   * 有值时 provider 层会 clamp 所有 per-call 温度到该值——这是服务端约束，
+   * 不是"推荐值"。普通模型不要设这个字段。
+   */
+  readonly temperature?: number;
+  /** 生命周期状态；enabled=false 仍保留为兼容旧数据的硬下线标记。 */
+  readonly status?: "active" | "deprecated" | "disabled" | "nonText";
+  readonly replacement?: string;
+  readonly capabilities?: {
+    readonly text?: boolean;
+    readonly imageInput?: boolean;
+    readonly imageOutput?: boolean;
+    readonly tools?: boolean;
+    readonly reasoning?: boolean;
+  };
+}
+
+export interface ProviderCompat {
+  /** OpenAI Responses store 参数是否被兼容层接受；Google Gemini OpenAI-compatible 不接受。 */
+  readonly supportsStore?: boolean;
+  readonly supportsSystemRole?: boolean;
+  readonly supportsDeveloperRole?: boolean;
+  /** Some OpenAI-compatible providers reject restored histories ending in toolResult; only those providers get a synthetic assistant bridge during context projection. */
+  readonly requiresAssistantAfterToolResult?: boolean;
+}
+
+export interface ProviderTransportDefaults {
+  readonly apiFormat?: "chat" | "responses";
+  readonly stream?: boolean;
+}
+
+export interface InkosEndpoint {
+  readonly id: string;
+  readonly label: string;
+  /** UI 分组。custom 不参与分组，其他 endpoint 必填。 */
+  readonly group?: EndpointGroup;
+
+  readonly api: ApiProtocol;
+  readonly baseUrl: string;
+  /** /models 接口的 baseUrl 跟主 baseUrl path 不同时（如百炼 dashscope） */
+  readonly modelsBaseUrl?: string;
+
+  /** apikey 两步验证时发 chat hello 用的模型 id */
+  readonly checkModel?: string;
+
+  readonly temperatureRange?: readonly [number, number];
+  readonly defaultTemperature?: number;
+  readonly writingTemperature?: number;
+  readonly temperatureHint?: string;
+  readonly compat?: ProviderCompat;
+  readonly transportDefaults?: ProviderTransportDefaults;
+
+  readonly models: readonly InkosModel[];
+}

package/inkos/packages/core/src/llm/providers/verify.ts

@@ -0,0 +1,104 @@
+import { getEndpoint } from "./index.js";
+import { resolveServiceModelsBaseUrl } from "../service-presets.js";
+import { fetchWithProxy } from "../../utils/proxy-fetch.js";
+
+export interface VerifyResult {
+  readonly recommendedTransport?: {
+    readonly apiFormat?: "chat" | "responses";
+    readonly stream?: boolean;
+  };
+  readonly probe: {
+    readonly ok: boolean;
+    readonly models: number;
+    readonly error?: string;
+  };
+  readonly chat: {
+    readonly ok: boolean;
+    readonly latencyMs?: number;
+    readonly error?: string;
+  } | null;
+}
+
+/**
+ * Step 1: 用 apikey 调 /models endpoint 探测。
+ * 返回 models 条数 + ok 标志；失败原因落到 error 字段。
+ */
+async function probe(
+  service: string,
+  apiKey: string,
+  baseUrl?: string,
+  proxyUrl?: string,
+): Promise<VerifyResult["probe"]> {
+  const provider = getEndpoint(service);
+  const probeBaseUrl = baseUrl || provider?.modelsBaseUrl || provider?.baseUrl || resolveServiceModelsBaseUrl(service);
+  if (!probeBaseUrl) {
+    return { ok: false, models: 0, error: "无 baseUrl 可探测（custom / newapi / higress 需要用户填）" };
+  }
+  try {
+    const url = probeBaseUrl.replace(/\/$/, "") + "/models";
+    const res = await fetchWithProxy(url, {
+      headers: { Authorization: `Bearer ${apiKey}` },
+      signal: AbortSignal.timeout(10_000),
+    }, proxyUrl);
+    if (!res.ok) {
+      return { ok: false, models: 0, error: `HTTP ${res.status} ${res.statusText}` };
+    }
+    const json = (await res.json()) as { data?: Array<{ id: string }> };
+    const count = json.data?.length ?? 0;
+    return { ok: count > 0, models: count };
+  } catch (error) {
+    return {
+      ok: false,
+      models: 0,
+      error: error instanceof Error ? error.message : String(error),
+    };
+  }
+}
+
+/**
+ * verifyService: 两步验证。
+ * Step 1 probe /models。
+ * Step 2 chat hello 到 checkModel（命中 provider.checkModel 才做；custom / newapi / higress 没有 checkModel，chat 字段返回 null）。
+ */
+export async function verifyService(
+  service: string,
+  apiKey: string,
+  opts?: { checkModel?: string; baseUrl?: string; proxyUrl?: string },
+): Promise<VerifyResult> {
+  const probeResult = await probe(service, apiKey, opts?.baseUrl, opts?.proxyUrl);
+
+  const provider = getEndpoint(service);
+  const recommendedTransport = provider?.transportDefaults;
+  const checkModel = opts?.checkModel ?? provider?.checkModel;
+  if (!checkModel) {
+    return { recommendedTransport, probe: probeResult, chat: null };
+  }
+
+  const start = Date.now();
+  try {
+    const { createLLMClient, chatCompletion } = await import("../provider.js");
+    const { LLMConfigSchema } = await import("../../models/project.js");
+    const client = createLLMClient(LLMConfigSchema.parse({
+      provider: provider?.api === "anthropic-messages" ? "anthropic" : "openai",
+      service,
+      model: checkModel,
+      apiKey,
+      baseUrl: opts?.baseUrl ?? provider?.baseUrl ?? "",
+      proxyUrl: opts?.proxyUrl,
+      configSource: "studio",
+      stream: false,
+    }));
+    await chatCompletion(client, checkModel, [{ role: "user", content: "hi" }], { maxTokens: 10 });
+    return { recommendedTransport, probe: probeResult, chat: { ok: true, latencyMs: Date.now() - start } };
+  } catch (error) {
+    return {
+      recommendedTransport,
+      probe: probeResult,
+      chat: {
+        ok: false,
+        latencyMs: Date.now() - start,
+        error: error instanceof Error ? error.message : String(error),
+      },
+    };
+  }
+}