feat(ai): switch xiaomi default to api billing, add per-region token plan providers (#4112)

Built-in `xiaomi` provider now targets the API billing endpoint (https://api.xiaomimimo.com/anthropic) — a single stable URL for keys issued at platform.xiaomimimo.com. The Token Plan endpoints are exposed as three sibling providers, each with its own env var:

- xiaomi-token-plan-cn: XIAOMI_TOKEN_PLAN_CN_API_KEY
- xiaomi-token-plan-ams: XIAOMI_TOKEN_PLAN_AMS_API_KEY
- xiaomi-token-plan-sgp: XIAOMI_TOKEN_PLAN_SGP_API_KEY

BREAKING CHANGE: users who previously set XIAOMI_API_KEY against the Token Plan AMS endpoint must move to xiaomi-token-plan-ams and set XIAOMI_TOKEN_PLAN_AMS_API_KEY. This also resolves the 401 reported by on #4005, where a platform.xiaomimimo.com key fails against the Token Plan endpoint.

closes #4082
This commit is contained in:
Jake Jia
2026-05-03 18:57:11 +08:00
committed by Mario Zechner
parent 924a1395bc
commit b326bf1a3a
22 changed files with 859 additions and 46 deletions

View File

@@ -393,7 +393,7 @@ describe("Context overflow error handling", () => {
// Xiaomi MiMo
// =============================================================================
describe.skipIf(!process.env.XIAOMI_API_KEY)("Xiaomi MiMo", () => {
describe.skipIf(!process.env.XIAOMI_API_KEY)("Xiaomi MiMo (API billing)", () => {
// Xiaomi silently truncates oversized input to fill the context window exactly,
// then returns finish_reason "length" with output=0 (no room left to generate).
// This is a detectable overflow signal but uses stopReason "length" rather than "error".
@@ -408,6 +408,42 @@ describe("Context overflow error handling", () => {
}, 120000);
});
describe.skipIf(!process.env.XIAOMI_TOKEN_PLAN_CN_API_KEY)("Xiaomi MiMo Token Plan (CN)", () => {
it("mimo-v2.5-pro - should detect overflow via isContextOverflow", async () => {
const model = getModel("xiaomi-token-plan-cn", "mimo-v2.5-pro");
const result = await testContextOverflow(model, process.env.XIAOMI_TOKEN_PLAN_CN_API_KEY!);
logResult(result);
expect(result.stopReason).toBe("length");
expect(result.usage.output).toBe(0);
expect(isContextOverflow(result.response, model.contextWindow)).toBe(true);
}, 120000);
});
describe.skipIf(!process.env.XIAOMI_TOKEN_PLAN_AMS_API_KEY)("Xiaomi MiMo Token Plan (AMS)", () => {
it("mimo-v2.5-pro - should detect overflow via isContextOverflow", async () => {
const model = getModel("xiaomi-token-plan-ams", "mimo-v2.5-pro");
const result = await testContextOverflow(model, process.env.XIAOMI_TOKEN_PLAN_AMS_API_KEY!);
logResult(result);
expect(result.stopReason).toBe("length");
expect(result.usage.output).toBe(0);
expect(isContextOverflow(result.response, model.contextWindow)).toBe(true);
}, 120000);
});
describe.skipIf(!process.env.XIAOMI_TOKEN_PLAN_SGP_API_KEY)("Xiaomi MiMo Token Plan (SGP)", () => {
it("mimo-v2.5-pro - should detect overflow via isContextOverflow", async () => {
const model = getModel("xiaomi-token-plan-sgp", "mimo-v2.5-pro");
const result = await testContextOverflow(model, process.env.XIAOMI_TOKEN_PLAN_SGP_API_KEY!);
logResult(result);
expect(result.stopReason).toBe("length");
expect(result.usage.output).toBe(0);
expect(isContextOverflow(result.response, model.contextWindow)).toBe(true);
}, 120000);
});
// =============================================================================
// Kimi For Coding
// =============================================================================