ton/pi_harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ai): add Qwen Token Plan as built-in provider (#6858)

Browse Source 
Add Alibaba Cloud Model Studio Token Plan subscription service as two
built-in API-key providers: qwen-token-plan (international, Singapore)
and qwen-token-plan-cn (China, Beijing).

Each provider exposes 15 text-generation models (Qwen, DeepSeek, GLM,
Kimi, MiniMax) via the OpenAI-compatible endpoint with DashScope
enable_thinking support. Model metadata is sourced from models.dev;
qwen3.8-max-preview is hardcoded until models.dev includes it.

Also fixes kimi-coding test references (k2p7 -> kimi-for-coding) after
models.dev catalog update picked up by generate-models.

Closes #6850
This commit is contained in:
QuintinShaw
2026-07-20 19:53:30 +08:00
committed by GitHub
parent d9f7f81473
commit bbb91fa8ae
27 changed files with 605 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/test/stream.test.ts
+59
View File
@@ -1168,6 +1168,65 @@ describe("Generate E2E Tests", () => {
},
);
describe.skipIf(!process.env.QWEN_TOKEN_PLAN_API_KEY)(
"Qwen Token Plan Provider (Qwen3.7-Max, international)",
() => {
const llm = getModel("qwen-token-plan", "qwen3.7-max");
const thinkingOptions = {
thinkingEnabled: true,
reasoningEffort: "high",
} satisfies StreamOptionsWithExtras;
it("should complete basic text generation", { retry: 3 }, async () => {
await basicTextGeneration(llm);
});
it("should handle tool calling", { retry: 3 }, async () => {
await handleToolCall(llm);
});
it("should handle streaming", { retry: 3 }, async () => {
await handleStreaming(llm);
});
it("should handle thinking mode", { retry: 3 }, async () => {
await handleThinking(llm, thinkingOptions);
});
it("should handle multi-turn with thinking and tools", { retry: 3 }, async () => {
await multiTurn(llm, thinkingOptions);
});
},
);
describe.skipIf(!process.env.QWEN_TOKEN_PLAN_CN_API_KEY)("Qwen Token Plan Provider (Qwen3.7-Max, CN region)", () => {
const llm = getModel("qwen-token-plan-cn", "qwen3.7-max");
const thinkingOptions = {
thinkingEnabled: true,
reasoningEffort: "high",
} satisfies StreamOptionsWithExtras;
it("should complete basic text generation", { retry: 3 }, async () => {
await basicTextGeneration(llm);
});
it("should handle tool calling", { retry: 3 }, async () => {
await handleToolCall(llm);
});
it("should handle streaming", { retry: 3 }, async () => {
await handleStreaming(llm);
});
it("should handle thinking mode", { retry: 3 }, async () => {
await handleThinking(llm, thinkingOptions);
});
it("should handle multi-turn with thinking and tools", { retry: 3 }, async () => {
await multiTurn(llm, thinkingOptions);
});
});
describe.skipIf(!process.env.ANT_LING_API_KEY)("Ant Ling Provider (Ling 2.6 Flash via OpenAI Completions)", () => {
const llm = getModel("ant-ling", "Ling-2.6-flash");