mirror of
https://github.com/DayuanJiang/next-ai-draw-io.git
synced 2026-10-12 20:49:53 +08:00
dayuan.jiang
8ca2d03e7f
- lib/system-prompts.ts: delete the extended prompt kept only to reach the 4096-token cache threshold of two old Claude models; describe the current canvas-first UI in the App Features section - app/api/chat/route.ts: remove the server-side example cache (the browser answers examples itself), the ENABLE_HISTORY_XML_REPLACE option and its helper, the unread messageMetadata fields; the DEBUG_LLM_PAYLOAD blocks become one describeMessages summary - app/api/log-feedback and log-save share scoreLatestTrace in lib/langfuse.ts - app/api/admin/test-model and validate-model call a shared testModelConnection() instead of one route faking a request to the other and passing trust through the body - lib/dynamo-quota-manager.ts reads the failing item from the conditional update instead of a second GetItem - lib/ai-providers.ts: geminiThinkingOptions helper for the google and vertexai cases, drop the unused fourth resolveBaseURL parameter - edge-functions: always stream, shrink messageSchema, drop model aliases nothing sends - delete app/api/chat/xml_guide.md, parseOutputTokenLimit, unused type exports and export keywords on file-internal symbols - env.example: drop variables nothing reads, document the quota, validation and analytics variables, mention the apiKeyEnv array form (also in docs/*/ai-providers.md)
99 lines
3.3 KiB
TypeScript
99 lines
3.3 KiB
TypeScript
// @vitest-environment node
|
|
import { generateText } from "ai"
|
|
import { afterEach, describe, expect, it, vi } from "vitest"
|
|
import { getAIModel } from "@/lib/ai-providers"
|
|
|
|
const ENV = [
|
|
"GOOGLE_GENERATIVE_AI_API_KEY",
|
|
"GOOGLE_TOP_K",
|
|
"GOOGLE_TOP_P",
|
|
"GOOGLE_THINKING_BUDGET",
|
|
"GOOGLE_THINKING_LEVEL",
|
|
]
|
|
const saved = Object.fromEntries(ENV.map((k) => [k, process.env[k]]))
|
|
|
|
afterEach(() => {
|
|
for (const k of ENV) {
|
|
if (saved[k] === undefined) delete process.env[k]
|
|
else process.env[k] = saved[k]
|
|
}
|
|
vi.unstubAllGlobals()
|
|
})
|
|
|
|
/** Send one request through the real Google provider and return its body */
|
|
async function googleRequestBody(modelId = "gemini-2.5-flash") {
|
|
let body: any
|
|
vi.stubGlobal(
|
|
"fetch",
|
|
vi.fn(async (_url: string, init: RequestInit) => {
|
|
body = JSON.parse(init.body as string)
|
|
return new Response(
|
|
JSON.stringify({
|
|
candidates: [
|
|
{
|
|
content: { role: "model", parts: [{ text: "ok" }] },
|
|
finishReason: "STOP",
|
|
},
|
|
],
|
|
}),
|
|
{ headers: { "content-type": "application/json" } },
|
|
)
|
|
}),
|
|
)
|
|
// providerOptions carry the thinking settings, as the chat route passes them
|
|
const { model, providerOptions } = getAIModel({
|
|
provider: "google",
|
|
modelId,
|
|
})
|
|
await generateText({
|
|
model,
|
|
prompt: "hi",
|
|
maxRetries: 0,
|
|
...(providerOptions && { providerOptions }),
|
|
})
|
|
return body
|
|
}
|
|
|
|
describe("Google sampling settings", () => {
|
|
it("sends GOOGLE_TOP_K and GOOGLE_TOP_P in the generation config", async () => {
|
|
process.env.GOOGLE_GENERATIVE_AI_API_KEY = "test-key"
|
|
process.env.GOOGLE_TOP_K = "40"
|
|
process.env.GOOGLE_TOP_P = "0.9"
|
|
const body = await googleRequestBody()
|
|
expect(body.generationConfig).toMatchObject({ topK: 40, topP: 0.9 })
|
|
})
|
|
|
|
it("sends neither when they are not set", async () => {
|
|
process.env.GOOGLE_GENERATIVE_AI_API_KEY = "test-key"
|
|
delete process.env.GOOGLE_TOP_K
|
|
delete process.env.GOOGLE_TOP_P
|
|
const body = await googleRequestBody()
|
|
expect(body.generationConfig?.topK).toBeUndefined()
|
|
expect(body.generationConfig?.topP).toBeUndefined()
|
|
})
|
|
})
|
|
|
|
describe("Gemini thinking settings", () => {
|
|
it("sends GOOGLE_THINKING_BUDGET as the Gemini 2.5 thinking budget", async () => {
|
|
process.env.GOOGLE_GENERATIVE_AI_API_KEY = "test-key"
|
|
process.env.GOOGLE_THINKING_BUDGET = "8192"
|
|
delete process.env.GOOGLE_THINKING_LEVEL
|
|
const body = await googleRequestBody("gemini-2.5-flash")
|
|
expect(body.generationConfig.thinkingConfig).toEqual({
|
|
includeThoughts: true,
|
|
thinkingBudget: 8192,
|
|
})
|
|
})
|
|
|
|
it("sends GOOGLE_THINKING_LEVEL as the Gemini 3 thinking level", async () => {
|
|
process.env.GOOGLE_GENERATIVE_AI_API_KEY = "test-key"
|
|
process.env.GOOGLE_THINKING_LEVEL = "high"
|
|
delete process.env.GOOGLE_THINKING_BUDGET
|
|
const body = await googleRequestBody("gemini-3-pro-preview")
|
|
expect(body.generationConfig.thinkingConfig).toEqual({
|
|
includeThoughts: true,
|
|
thinkingLevel: "high",
|
|
})
|
|
})
|
|
})
|