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/cross-provider-handoff.test.ts
+3
View File
@@ -130,6 +130,9 @@ const PROVIDER_MODEL_PAIRS: ProviderModelPair[] = [
{ provider: "xiaomi-token-plan-cn", model: "mimo-v2.5-pro", label: "xiaomi-token-plan-cn-mimo-v2.5-pro" },
{ provider: "xiaomi-token-plan-ams", model: "mimo-v2.5-pro", label: "xiaomi-token-plan-ams-mimo-v2.5-pro" },
{ provider: "xiaomi-token-plan-sgp", model: "mimo-v2.5-pro", label: "xiaomi-token-plan-sgp-mimo-v2.5-pro" },
// Qwen Token Plan
{ provider: "qwen-token-plan", model: "qwen3.7-max", label: "qwen-token-plan-qwen3.7-max" },
{ provider: "qwen-token-plan-cn", model: "qwen3.7-max", label: "qwen-token-plan-cn-qwen3.7-max" },
];
// Cached context structure