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:
@@ -994,7 +994,7 @@ describe("Generate E2E Tests", () => {
|
||||
);
|
||||
|
||||
describe.skipIf(!process.env.XIAOMI_API_KEY)(
|
||||
"Xiaomi MiMo Token Plan Provider (Xiaomi MiMo-V2.5-Pro via Anthropic Messages)",
|
||||
"Xiaomi MiMo (API billing) Provider (Xiaomi MiMo-V2.5-Pro via Anthropic Messages)",
|
||||
() => {
|
||||
const llm = getModel("xiaomi", "mimo-v2.5-pro");
|
||||
const thinkingOptions = {
|
||||
@@ -1023,6 +1023,100 @@ describe("Generate E2E Tests", () => {
|
||||
});
|
||||
},
|
||||
);
|
||||
|
||||
describe.skipIf(!process.env.XIAOMI_TOKEN_PLAN_CN_API_KEY)(
|
||||
"Xiaomi MiMo Token Plan Provider (Xiaomi MiMo-V2.5-Pro via Anthropic Messages, CN region)",
|
||||
() => {
|
||||
const llm = getModel("xiaomi-token-plan-cn", "mimo-v2.5-pro");
|
||||
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.XIAOMI_TOKEN_PLAN_AMS_API_KEY)(
|
||||
"Xiaomi MiMo Token Plan Provider (Xiaomi MiMo-V2.5-Pro via Anthropic Messages, AMS region)",
|
||||
() => {
|
||||
const llm = getModel("xiaomi-token-plan-ams", "mimo-v2.5-pro");
|
||||
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.XIAOMI_TOKEN_PLAN_SGP_API_KEY)(
|
||||
"Xiaomi MiMo Token Plan Provider (Xiaomi MiMo-V2.5-Pro via Anthropic Messages, SGP region)",
|
||||
() => {
|
||||
const llm = getModel("xiaomi-token-plan-sgp", "mimo-v2.5-pro");
|
||||
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);
|
||||
});
|
||||
},
|
||||
);
|
||||
|
||||
// =========================================================================
|
||||
// OAuth-based providers (credentials from ~/.pi/agent/oauth.json)
|
||||
// Tokens are resolved at module level (see oauthTokens above)
|
||||
|
||||
Reference in New Issue
Block a user