mirror of
https://github.com/DayuanJiang/next-ai-draw-io.git
synced 2026-10-11 12:09:53 +08:00
dayuan.jiang
0855b35ff2
Found by the PR review, each with a test that failed first: - Quota: any key header skipped it, even one the provider never reads (x-aws-access-key-id with OpenAI), so a request ran on the server's key without being counted. The check now runs after the model is resolved and uses usesServerCredentials. On main already. - usesServerCredentials read the raw base URL; "/" cleans up to none, so an Ollama request ran on the server's key past the server-model check. - SGLang's default 127.0.0.1:8000 only fills the settings form. Chat and the model list used it as a real address, so the server called its own machine even with private URLs blocked. Now a base URL is required. - With a user's OpenAI key and no base URL, the SDK read the server's OPENAI_BASE_URL. The official endpoint is now passed. On main already. - The Test button refused nothing on the server's keys (Ollama Cloud), and a 15 s timeout reported "connected, no tool call". - The model list for Ollama without a base URL came from ollama.com while chat went to the server's Ollama. - Bedrock's "Too many tokens, please wait" counted as context too long. - On the server's keys the provider's error text stays in the server log; it can name the server's AWS account, role or internal hosts. - Desktop app: the preset keys are the user's own (NEXT_AI_DRAWIO_DESKTOP), so Max Output Tokens can be raised and keyless models in settings work again. A launch that found the remembered port taken no longer replaces it, which hid the user's chats and settings for good.
92 lines
2.6 KiB
TypeScript
92 lines
2.6 KiB
TypeScript
// @vitest-environment node
|
|
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest"
|
|
|
|
// Quota on, and every check answers that the daily limit is used up
|
|
const quota = vi.hoisted(() => ({ checks: 0 }))
|
|
vi.mock("@/lib/dynamo-quota-manager", () => ({
|
|
isQuotaEnabled: () => true,
|
|
checkAndIncrementRequest: async () => {
|
|
quota.checks++
|
|
return {
|
|
allowed: false,
|
|
error: "Daily limit reached",
|
|
type: "request",
|
|
used: 10,
|
|
limit: 10,
|
|
}
|
|
},
|
|
recordTokenUsage: async () => {},
|
|
}))
|
|
|
|
import { POST as chat } from "@/app/api/chat/route"
|
|
|
|
const ENV = ["AI_PROVIDER", "AI_MODEL", "OPENAI_API_KEY"]
|
|
const saved: Record<string, string | undefined> = {}
|
|
|
|
beforeEach(() => {
|
|
for (const k of ENV) saved[k] = process.env[k]
|
|
process.env.AI_PROVIDER = "openai"
|
|
process.env.AI_MODEL = "gpt-5.5"
|
|
process.env.OPENAI_API_KEY = "server-key"
|
|
quota.checks = 0
|
|
// No request may reach a provider
|
|
vi.stubGlobal(
|
|
"fetch",
|
|
vi.fn(async () => {
|
|
throw new Error("no network in tests")
|
|
}),
|
|
)
|
|
})
|
|
|
|
afterEach(() => {
|
|
for (const k of ENV) {
|
|
if (saved[k] === undefined) delete process.env[k]
|
|
else process.env[k] = saved[k]
|
|
}
|
|
vi.unstubAllGlobals()
|
|
})
|
|
|
|
const send = (headers: Record<string, string>) =>
|
|
chat(
|
|
new Request("http://localhost/api/chat", {
|
|
method: "POST",
|
|
headers: {
|
|
"Content-Type": "application/json",
|
|
"x-forwarded-for": "203.0.113.7",
|
|
...headers,
|
|
},
|
|
body: JSON.stringify({
|
|
messages: [
|
|
{
|
|
id: "u1",
|
|
role: "user",
|
|
parts: [{ type: "text", text: "Draw two boxes" }],
|
|
},
|
|
],
|
|
xml: "",
|
|
}),
|
|
}),
|
|
)
|
|
|
|
describe("chat quota", () => {
|
|
it("counts a request whose key header the provider never reads", async () => {
|
|
// OpenAI ignores the AWS key, so this runs on the server's key
|
|
const res = await send({
|
|
"x-ai-provider": "openai",
|
|
"x-aws-access-key-id": "x",
|
|
})
|
|
expect(res.status).toBe(429)
|
|
expect(quota.checks).toBe(1)
|
|
})
|
|
|
|
it("does not count a request on the user's own key", async () => {
|
|
const res = await send({
|
|
"x-ai-provider": "openai",
|
|
"x-ai-api-key": "user-key",
|
|
"x-ai-model": "gpt-5.5",
|
|
})
|
|
expect(res.status).not.toBe(429)
|
|
expect(quota.checks).toBe(0)
|
|
})
|
|
})
|