mirror of
https://github.com/DayuanJiang/next-ai-draw-io.git
synced 2026-10-07 10:17:47 +08:00
dayuan.jiang
ac62a58c9f
- Update ai to 6.0.300 and the @ai-sdk providers to their latest v6-line versions. @ai-sdk/anthropic 3.0.47 did not know claude-opus-4-7/4-8 and capped their output at 32000 tokens; 3.0.127 allows 128000 - Drop the fine-grained-tool-streaming beta header for the Anthropic API: the provider now streams tool input per tool (eager_input_streaming) - Claude 4.7 and later reject a non-default temperature/top_p/top_k and the extended thinking budget with a 400. A middleware retries once without them, so TEMPERATURE and *_THINKING_BUDGET_TOKENS no longer break those models - Prompt caching also reaches Claude on the Anthropic API and OpenRouter; before, only Bedrock got a cache marker - GOOGLE_TOP_K and GOOGLE_TOP_P never reached Gemini: they were sent as Google provider options, which drops them. They are call settings now. GOOGLE_CANDIDATE_COUNT and GOOGLE_REASONING_EFFORT, which the provider does not support, are removed - Add @ai-sdk/openai-compatible as a direct dependency
113 lines
3.9 KiB
TypeScript
113 lines
3.9 KiB
TypeScript
// @vitest-environment node
|
|
import { simulateReadableStream, streamText } from "ai"
|
|
import { MockLanguageModelV3 } from "ai/test"
|
|
import { describe, expect, it } from "vitest"
|
|
import {
|
|
withDeprecatedParamsFallback,
|
|
withoutDeprecatedParams,
|
|
} from "@/lib/deprecated-params"
|
|
|
|
// The error texts Claude 4.7 and later return (the Anthropic API and Bedrock)
|
|
const rejection = (message: string) => ({
|
|
statusCode: 400,
|
|
message,
|
|
responseBody: JSON.stringify({ error: { message } }),
|
|
})
|
|
const TEMPERATURE = rejection("`temperature` is deprecated for this model.")
|
|
const THINKING = rejection(
|
|
'"thinking.type.enabled" is not supported for this model. Use "thinking.type.adaptive" and "output_config.effort" to control thinking behavior.',
|
|
)
|
|
|
|
describe("withoutDeprecatedParams", () => {
|
|
const params = {
|
|
temperature: 0.2,
|
|
topP: 0.9,
|
|
maxOutputTokens: 1000,
|
|
providerOptions: {
|
|
anthropic: {
|
|
thinking: { type: "enabled", budgetTokens: 4000 },
|
|
cacheControl: { type: "ephemeral" },
|
|
},
|
|
},
|
|
}
|
|
|
|
it("drops sampling settings and the thinking budget", () => {
|
|
for (const error of [TEMPERATURE, THINKING]) {
|
|
expect(withoutDeprecatedParams(error, params)).toEqual({
|
|
maxOutputTokens: 1000,
|
|
providerOptions: {
|
|
anthropic: { cacheControl: { type: "ephemeral" } },
|
|
},
|
|
})
|
|
}
|
|
})
|
|
|
|
it("drops a Bedrock thinking budget", () => {
|
|
const bedrock = {
|
|
providerOptions: {
|
|
bedrock: {
|
|
reasoningConfig: { type: "enabled", budgetTokens: 4000 },
|
|
},
|
|
},
|
|
}
|
|
expect(withoutDeprecatedParams(THINKING, bedrock)).toEqual({
|
|
providerOptions: { bedrock: {} },
|
|
})
|
|
})
|
|
|
|
it("leaves other errors and requests with nothing to drop alone", () => {
|
|
expect(withoutDeprecatedParams(rejection("bad key"), params)).toBeNull()
|
|
expect(
|
|
withoutDeprecatedParams(
|
|
{ ...TEMPERATURE, statusCode: 401 },
|
|
params,
|
|
),
|
|
).toBeNull()
|
|
const nothingToDrop = {
|
|
providerOptions: {
|
|
anthropic: { cacheControl: { type: "ephemeral" } },
|
|
},
|
|
}
|
|
expect(withoutDeprecatedParams(TEMPERATURE, nothingToDrop)).toBeNull()
|
|
})
|
|
})
|
|
|
|
describe("withDeprecatedParamsFallback", () => {
|
|
it("retries the stream once without the rejected settings", async () => {
|
|
const calls: any[] = []
|
|
const model = new MockLanguageModelV3({
|
|
// The test stream only has the parts this check needs
|
|
doStream: (async (options: any) => {
|
|
calls.push(options)
|
|
if (options.temperature !== undefined) throw TEMPERATURE
|
|
return {
|
|
stream: simulateReadableStream({
|
|
chunks: [
|
|
{ type: "text-start", id: "t" },
|
|
{ type: "text-delta", id: "t", delta: "ok" },
|
|
{ type: "text-end", id: "t" },
|
|
{
|
|
type: "finish",
|
|
finishReason: { unified: "stop", raw: "stop" },
|
|
usage: {
|
|
inputTokens: { total: 1 },
|
|
outputTokens: { total: 1 },
|
|
},
|
|
},
|
|
],
|
|
}),
|
|
}
|
|
}) as any,
|
|
})
|
|
const result = streamText({
|
|
model: withDeprecatedParamsFallback(model as any),
|
|
prompt: "hi",
|
|
temperature: 0.2,
|
|
maxRetries: 0,
|
|
})
|
|
expect(await result.text).toBe("ok")
|
|
expect(calls).toHaveLength(2)
|
|
expect(calls[1].temperature).toBeUndefined()
|
|
})
|
|
})
|