mirror of
https://github.com/DayuanJiang/next-ai-draw-io.git
synced 2026-10-12 20:49:53 +08:00
## Problem
A review of how the app uses the Vercel AI SDK (two Claude reviewers and Codex, each finding checked against the SDK's type definitions and source) found five behaviours that are wrong and a set of places where the app re-implements what the SDK already provides:
1. Quota tokens were recorded in `onFinish`, which the SDK does not call when a later step fails; only a user stop was handled (`onAbort`), and the write was not awaited.
2. An automatic retry after a tool error re-sent the request body as it was when the message was sent, so the model was told the "authoritative" canvas XML was the diagram from before the turn, although `display_diagram` commits a drawing before its screenshot check can fail.
3. The screenshot check and the connection test ran their model call on `AbortSignal.timeout` only, so pressing Stop (or closing the dialog) did not stop a paid model call.
4. The client ignored `finishReason`; a reasoning model that spent the whole output budget before calling a tool left the user with no diagram and no message.
5. The connection test counted an `invalid` tool call (a tool that does not exist, unreadable input) as proof of tool support.
## Change
- `onStepFinish` records each step's `usage.totalTokens` and awaits the write; the copies in `onFinish` and `onAbort` are gone.
- `DefaultChatTransport.prepareSendMessagesRequest` sends the current canvas page XML on every request after the first of a turn; the first keeps the exported (or snapshot) XML.
- `validate-diagram` and the connection test pass `req.signal` and use the SDK's `timeout` option; `validate-diagram` reports to Langfuse under `functionId: "validate-diagram"`.
- The connection test only counts a valid tool call.
- The client's `onFinish` shows a notice (with Retry) when `finishReason === "length"` and no tool was called.
- The server validates incoming messages with `safeValidateUIMessages` (400 otherwise), drops client system messages explicitly and prunes empty model messages with `pruneMessages`.
- The chat's tools live in `lib/chat-tools.ts` with an `outputSchema` for the client-side ones; `lib/chat-message.ts` defines `ChatUIMessage` (metadata, a `data-notice` part, `InferUITools`) so `useChat`, `addToolOutput` and the tool handlers are typed.
- Error notices are assistant messages with a `data-notice` part instead of role `system` UI messages.
- Regenerate, edit and retry use `sendMessage({ messageId })`; `isResending` and `flushSync` are gone.
- `isToolUIPart` / `getToolName` replace slicing `"tool-"` off part types; `ToolPartLike` derives from the SDK's part types.
Net: 578 insertions, 439 deletions over 16 files.
## Testing
- New unit tests: a step that fails after a finished step still counts that step's tokens; the screenshot check's model call ends when the request is aborted; an invalid tool call in the connection test gives the warning; malformed messages get a 400. The first and third confirm SDK behaviour the review relied on.
- `tsc`, `biome ci` (0 errors), root `vitest run` 723 passed on the branch rebased onto #986, `next build`: clean
- Playwright, 10 chat-related specs on the dev server: 199 passed, 0 failed, both before and after the rebase onto #986
385 lines
13 KiB
TypeScript
385 lines
13 KiB
TypeScript
// @vitest-environment node
|
|
import { streamText } from "ai"
|
|
import { afterEach, describe, expect, it, vi } from "vitest"
|
|
import { POST as testModel } from "@/app/api/admin/test-model/route"
|
|
import { POST as validateModel } from "@/app/api/validate-model/route"
|
|
import { getAIModel } from "@/lib/ai-providers"
|
|
|
|
// No saved admin providers
|
|
vi.mock("@/lib/admin/settings", () => ({
|
|
loadSettings: () => ({}),
|
|
getEnvFallback: (key: string) => process.env[key] ?? null,
|
|
}))
|
|
|
|
// Every URL is public (no DNS in tests), unless a test says otherwise
|
|
const privateUrls = vi.hoisted(() => ({ all: false }))
|
|
vi.mock("@/lib/ssrf-protection", async (importOriginal) => ({
|
|
...(await importOriginal<typeof import("@/lib/ssrf-protection")>()),
|
|
isPrivateUrl: async () => privateUrls.all,
|
|
}))
|
|
|
|
// The quota, off unless a test turns it on; every request is refused
|
|
const quota = vi.hoisted(() => ({ enabled: false, checks: 0 }))
|
|
vi.mock("@/lib/dynamo-quota-manager", () => ({
|
|
isQuotaEnabled: () => quota.enabled,
|
|
checkAndIncrementRequest: async () => {
|
|
quota.checks++
|
|
return { allowed: false, error: "Daily limit reached" }
|
|
},
|
|
}))
|
|
vi.mock("@/lib/user-id", () => ({ getUserIdFromRequest: () => "user-1" }))
|
|
|
|
afterEach(() => {
|
|
quota.enabled = false
|
|
quota.checks = 0
|
|
privateUrls.all = false
|
|
vi.unstubAllGlobals()
|
|
})
|
|
|
|
/** An OpenAI-compatible streaming reply made of the given deltas */
|
|
function streamReply(...deltas: object[]) {
|
|
const chunk = (delta: object, finish: string | null) =>
|
|
`data: ${JSON.stringify({
|
|
id: "c1",
|
|
object: "chat.completion.chunk",
|
|
created: 1,
|
|
model: "m",
|
|
choices: [{ index: 0, delta, finish_reason: finish }],
|
|
})}\n\n`
|
|
const body =
|
|
deltas.map((d) => chunk(d, null)).join("") +
|
|
chunk({}, "stop") +
|
|
"data: [DONE]\n\n"
|
|
vi.stubGlobal(
|
|
"fetch",
|
|
vi.fn(
|
|
async () =>
|
|
new Response(body, {
|
|
headers: { "content-type": "text/event-stream" },
|
|
}),
|
|
),
|
|
)
|
|
}
|
|
|
|
const testGlm = async () => {
|
|
const res = await validateModel(
|
|
new Request("http://localhost/api/validate-model", {
|
|
method: "POST",
|
|
headers: { "Content-Type": "application/json" },
|
|
body: JSON.stringify({
|
|
provider: "glm",
|
|
apiKey: "key",
|
|
modelId: "glm-5",
|
|
}),
|
|
}),
|
|
)
|
|
return res.json()
|
|
}
|
|
|
|
describe("POST /api/validate-model", () => {
|
|
it("passes when the model calls the test tool", async () => {
|
|
streamReply({
|
|
role: "assistant",
|
|
tool_calls: [
|
|
{
|
|
index: 0,
|
|
id: "call_1",
|
|
type: "function",
|
|
function: { name: "ping", arguments: "{}" },
|
|
},
|
|
],
|
|
})
|
|
const data = await testGlm()
|
|
expect(data.valid).toBe(true)
|
|
expect(data.warning).toBeUndefined()
|
|
expect(typeof data.responseTime).toBe("number")
|
|
})
|
|
|
|
it("reports a model that did not answer in time", async () => {
|
|
// The 15 s timeout has fired: the SDK ends the stream with an
|
|
// abort part instead of throwing
|
|
const timedOut = AbortSignal.abort(
|
|
new DOMException("The operation timed out.", "TimeoutError"),
|
|
)
|
|
const timeout = vi
|
|
.spyOn(AbortSignal, "timeout")
|
|
.mockReturnValue(timedOut)
|
|
vi.stubGlobal(
|
|
"fetch",
|
|
vi.fn(async () => {
|
|
throw timedOut.reason
|
|
}),
|
|
)
|
|
try {
|
|
const data = await testGlm()
|
|
expect(data.valid).toBe(false)
|
|
expect(data.code).toBe("timeout")
|
|
} finally {
|
|
timeout.mockRestore()
|
|
}
|
|
})
|
|
|
|
it("does not run on the server's keys", async () => {
|
|
vi.stubEnv("OLLAMA_API_KEY", "server-ollama-key")
|
|
const res = await validateModel(
|
|
new Request("http://localhost/api/validate-model", {
|
|
method: "POST",
|
|
headers: { "Content-Type": "application/json" },
|
|
body: JSON.stringify({
|
|
provider: "ollama",
|
|
modelId: "any-cloud-model",
|
|
}),
|
|
}),
|
|
)
|
|
expect(res.status).toBe(400)
|
|
expect((await res.json()).error).toMatch(/API key/)
|
|
})
|
|
|
|
it("warns when the model answers without a tool call", async () => {
|
|
streamReply({ role: "assistant", content: "OK" })
|
|
const data = await testGlm()
|
|
expect(data.valid).toBe(true)
|
|
expect(data.warning).toMatch(/without calling a tool/)
|
|
})
|
|
|
|
it("warns when the model calls a tool that does not exist", async () => {
|
|
// The SDK passes the call on, marked invalid
|
|
streamReply({
|
|
role: "assistant",
|
|
tool_calls: [
|
|
{
|
|
index: 0,
|
|
id: "call_1",
|
|
type: "function",
|
|
function: { name: "pong", arguments: "{}" },
|
|
},
|
|
],
|
|
})
|
|
const data = await testGlm()
|
|
expect(data.valid).toBe(true)
|
|
expect(data.warning).toMatch(/without calling a tool/)
|
|
})
|
|
})
|
|
|
|
describe("chat requests to a client base URL", () => {
|
|
it("refuse redirects when private URLs are blocked", async () => {
|
|
vi.stubEnv("ALLOW_PRIVATE_URLS", "false")
|
|
vi.stubGlobal(
|
|
"fetch",
|
|
vi.fn(
|
|
async () =>
|
|
new Response(null, {
|
|
status: 302,
|
|
headers: { location: "http://169.254.169.254/" },
|
|
}),
|
|
),
|
|
)
|
|
const { model } = getAIModel({
|
|
provider: "glm",
|
|
apiKey: "key",
|
|
baseUrl: "https://attacker.example/v1",
|
|
modelId: "glm-5",
|
|
})
|
|
let error: unknown
|
|
const result = streamText({
|
|
model,
|
|
prompt: "hi",
|
|
maxRetries: 0,
|
|
onError: ({ error: e }) => {
|
|
error = e
|
|
},
|
|
})
|
|
await result.consumeStream()
|
|
expect(String(error)).toMatch(/Redirects are not allowed/)
|
|
})
|
|
})
|
|
|
|
describe("testing EdgeOne", () => {
|
|
// The request validate-model sends to the EdgeOne function
|
|
const capture = () => {
|
|
const calls: Array<{ url: string; headers: Headers }> = []
|
|
vi.stubGlobal(
|
|
"fetch",
|
|
vi.fn(async (url: string, init?: RequestInit) => {
|
|
calls.push({
|
|
url: String(url),
|
|
headers: new Headers(init?.headers),
|
|
})
|
|
throw new Error("no network in tests")
|
|
}),
|
|
)
|
|
return calls
|
|
}
|
|
|
|
it("calls the site's own function, also without a base URL", async () => {
|
|
// The admin panel's Test sends none; a relative one cannot be fetched
|
|
const calls = capture()
|
|
await validateModel(
|
|
new Request("http://localhost/api/validate-model", {
|
|
method: "POST",
|
|
headers: {
|
|
"Content-Type": "application/json",
|
|
origin: "https://draw.example",
|
|
},
|
|
body: JSON.stringify({
|
|
provider: "edgeone",
|
|
modelId: "@tx/deepseek-ai/deepseek-v3-0324",
|
|
baseUrl: "https://elsewhere.example/api/edgeai",
|
|
}),
|
|
}),
|
|
)
|
|
expect(calls[0]?.url).toBe(
|
|
"https://draw.example/api/edgeai/chat/completions",
|
|
)
|
|
})
|
|
|
|
it("passes the admin's access code and cookies on", async () => {
|
|
// The EdgeOne function checks the access code too
|
|
vi.stubEnv("ADMIN_PASSWORD", "admin-pw")
|
|
const calls = capture()
|
|
await testModel(
|
|
new Request("http://localhost/api/admin/test-model", {
|
|
method: "POST",
|
|
headers: {
|
|
"Content-Type": "application/json",
|
|
"x-admin-password": "admin-pw",
|
|
"x-access-code": "visitor-code",
|
|
cookie: "eo_token=t",
|
|
origin: "https://draw.example",
|
|
},
|
|
body: JSON.stringify({
|
|
provider: {
|
|
id: "p1",
|
|
provider: "edgeone",
|
|
models: ["@tx/deepseek-ai/deepseek-v3-0324"],
|
|
},
|
|
modelId: "@tx/deepseek-ai/deepseek-v3-0324",
|
|
}),
|
|
}),
|
|
)
|
|
expect(calls[0]?.url).toBe(
|
|
"https://draw.example/api/edgeai/chat/completions",
|
|
)
|
|
expect(calls[0]?.headers.get("x-access-code")).toBe("visitor-code")
|
|
expect(calls[0]?.headers.get("cookie")).toBe("eo_token=t")
|
|
})
|
|
})
|
|
|
|
describe("the admin Test of the server's own base URL", () => {
|
|
// An admin panel entry without a URL of its own
|
|
const adminTest = () =>
|
|
testModel(
|
|
new Request("http://localhost/api/admin/test-model", {
|
|
method: "POST",
|
|
headers: {
|
|
"Content-Type": "application/json",
|
|
"x-admin-password": "admin-pw",
|
|
},
|
|
body: JSON.stringify({
|
|
provider: {
|
|
id: "p1",
|
|
provider: "openai",
|
|
apiKey: "panel-key",
|
|
models: ["gpt-5.5"],
|
|
},
|
|
modelId: "gpt-5.5",
|
|
}),
|
|
}),
|
|
)
|
|
// A user naming the same address in the Settings dialog
|
|
const userTest = () =>
|
|
validateModel(
|
|
new Request("http://localhost/api/validate-model", {
|
|
method: "POST",
|
|
headers: { "Content-Type": "application/json" },
|
|
body: JSON.stringify({
|
|
provider: "openai",
|
|
apiKey: "panel-key",
|
|
modelId: "gpt-5.5",
|
|
baseUrl: "http://10.0.0.5:8000/v1",
|
|
}),
|
|
}),
|
|
)
|
|
|
|
it("tests it as chat uses it: an internal address is allowed", async () => {
|
|
// ALLOW_PRIVATE_URLS=false guards URLs users type, not the server's
|
|
vi.stubEnv("ALLOW_PRIVATE_URLS", "false")
|
|
vi.stubEnv("OPENAI_BASE_URL", "http://10.0.0.5:8000/v1")
|
|
vi.stubEnv("ADMIN_PASSWORD", "admin-pw")
|
|
privateUrls.all = true
|
|
streamReply({ role: "assistant", content: "OK" })
|
|
const admin = await (await adminTest()).json()
|
|
expect(admin.valid).toBe(true)
|
|
// A user typing the same address is still refused
|
|
const other = await userTest()
|
|
expect(other.status).toBe(400)
|
|
})
|
|
})
|
|
|
|
describe("the admin panel's Test button", () => {
|
|
it("works when access codes are set", async () => {
|
|
// The admin password stands in for the visitor access code
|
|
vi.stubEnv("ACCESS_CODE_LIST", "visitor-code")
|
|
vi.stubEnv("ADMIN_PASSWORD", "admin-pw")
|
|
streamReply({ role: "assistant", content: "OK" })
|
|
const res = await testModel(
|
|
new Request("http://localhost/api/admin/test-model", {
|
|
method: "POST",
|
|
headers: {
|
|
"Content-Type": "application/json",
|
|
"x-admin-password": "admin-pw",
|
|
},
|
|
body: JSON.stringify({
|
|
provider: {
|
|
id: "p1",
|
|
provider: "glm",
|
|
apiKey: "key",
|
|
models: ["glm-5"],
|
|
},
|
|
modelId: "glm-5",
|
|
}),
|
|
}),
|
|
)
|
|
expect(res.status).toBe(200)
|
|
expect((await res.json()).valid).toBe(true)
|
|
})
|
|
})
|
|
|
|
describe("the Test on the deployment's own endpoints", () => {
|
|
const test = (body: object) =>
|
|
validateModel(
|
|
new Request("http://localhost/api/validate-model", {
|
|
method: "POST",
|
|
headers: { "Content-Type": "application/json" },
|
|
body: JSON.stringify({ modelId: "m", ...body }),
|
|
}),
|
|
)
|
|
|
|
it("counts as a chat request with the quota on", async () => {
|
|
quota.enabled = true
|
|
// EdgeOne, and a model server on the server's network with a dummy key
|
|
const edgeone = await test({ provider: "edgeone" })
|
|
expect(edgeone.status).toBe(429)
|
|
privateUrls.all = true
|
|
const internal = await test({
|
|
provider: "openai",
|
|
apiKey: "x",
|
|
baseUrl: "http://10.0.0.5:8000/v1",
|
|
})
|
|
expect(internal.status).toBe(429)
|
|
expect(quota.checks).toBe(2)
|
|
})
|
|
|
|
it("does not count a user's own endpoint", async () => {
|
|
quota.enabled = true
|
|
streamReply({ role: "assistant", content: "OK" })
|
|
const res = await test({
|
|
provider: "openai",
|
|
apiKey: "user-key",
|
|
baseUrl: "https://api.example.com/v1",
|
|
})
|
|
expect(res.status).toBe(200)
|
|
expect(quota.checks).toBe(0)
|
|
})
|
|
})
|