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/context-overflow.test.ts
+24
View File
@@ -466,6 +466,30 @@ describe("Context overflow error handling", () => {
}, 120000);
});
describe.skipIf(!process.env.QWEN_TOKEN_PLAN_API_KEY)("Qwen Token Plan", () => {
it("qwen3.7-max - should detect overflow via isContextOverflow", async () => {
const model = getModel("qwen-token-plan", "qwen3.7-max");
const result = await testContextOverflow(model, process.env.QWEN_TOKEN_PLAN_API_KEY!);
logResult(result);
expect(result.stopReason).toBe("error");
expect(result.errorMessage).toMatch(/input length/i);
expect(isContextOverflow(result.response, model.contextWindow)).toBe(true);
}, 120000);
});
describe.skipIf(!process.env.QWEN_TOKEN_PLAN_CN_API_KEY)("Qwen Token Plan (CN)", () => {
it("qwen3.7-max - should detect overflow via isContextOverflow", async () => {
const model = getModel("qwen-token-plan-cn", "qwen3.7-max");
const result = await testContextOverflow(model, process.env.QWEN_TOKEN_PLAN_CN_API_KEY!);
logResult(result);
expect(result.stopReason).toBe("error");
expect(result.errorMessage).toMatch(/input length/i);
expect(isContextOverflow(result.response, model.contextWindow)).toBe(true);
}, 120000);
});
// =============================================================================
// Kimi For Coding
// =============================================================================