infiplot/infiplot-web
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(ai-client): replace AI SDK adapters with OpenAI SDK

Browse Source
This commit is contained in:
baizhi958216
2026-06-11 16:11:44 +08:00
parent 6cd7d88326
commit ef3b57953b
11 changed files with 191 additions and 275 deletions
Download Patch File Download Diff File Expand all files Collapse all files
lib/ai-client/chat.ts
+29 -34
View File
@@ -1,29 +1,24 @@
import { generateText } from "ai";
import type { LanguageModelUsage, ModelMessage } from "ai";
import OpenAI from "openai";
import type { ProviderConfig } from "@infiplot/types";
import { createLanguageModel, resolveProtocol } from "./model";
import { normalizeBaseUrl } from "./normalizeUrl";
export type ChatMessage = {
role: "system" | "user" | "assistant";
content: string;
};
// AI SDK 6 unifies cache stats across providers into usage.inputTokenDetails,
// so a single shape covers Anthropic, Gemini, and OpenAI-compatible providers.
function summarizeSdkUsage(
tag: string,
usage: LanguageModelUsage | undefined,
usage: OpenAI.Completions.CompletionUsage | undefined,
): string {
if (!usage) return `[cache] ${tag} no-usage`;
const input = usage.inputTokens ?? 0;
const output = usage.outputTokens ?? 0;
const read = usage.inputTokenDetails?.cacheReadTokens;
const write = usage.inputTokenDetails?.cacheWriteTokens;
if (typeof read === "number" || typeof write === "number") {
const hit = read ?? 0;
const create = write ?? 0;
const rate = input > 0 ? ((hit / input) * 100).toFixed(1) : "n/a";
return `[cache] ${tag} hit=${hit} create=${create} input=${input} rate=${rate}% completion=${output}`;
const input = usage.prompt_tokens ?? 0;
const output = usage.completion_tokens ?? 0;
const details = (usage as { prompt_tokens_details?: { cached_tokens?: number } }).prompt_tokens_details;
const cached = details?.cached_tokens;
if (typeof cached === "number") {
const rate = input > 0 ? ((cached / input) * 100).toFixed(1) : "n/a";
return `[cache] ${tag} hit=${cached} input=${input} rate=${rate}% completion=${output}`;
}
return `[cache] ${tag} input=${input} completion=${output} (provider didn't report cache stats)`;
}
@@ -36,28 +31,28 @@ export async function chat(
tag?: string;
},
): Promise<string> {
const protocol = resolveProtocol(config);
const model = createLanguageModel(config, protocol);
const system = messages.find((m) => m.role === "system")?.content;
const convo: ModelMessage[] = messages
.filter((m) => m.role !== "system")
.map((m) => ({
role: m.role as "user" | "assistant",
content: m.content,
}));
const { text, usage } = await generateText({
model,
system,
messages: convo,
temperature: opts?.temperature ?? 0.9,
const client = new OpenAI({
apiKey: config.apiKey,
baseURL: normalizeBaseUrl(config.baseUrl, "openai_compatible"),
maxRetries: 0,
dangerouslyAllowBrowser: true,
});
console.log(summarizeSdkUsage(opts?.tag ?? "chat", usage));
const completion = await client.chat.completions.create({
model: config.model,
messages: messages.map((m) => ({
role: m.role as "system" | "user" | "assistant",
content: m.content,
})),
temperature: opts?.temperature ?? 0.9,
stream: false,
});
if (typeof text !== "string" || text.length === 0) {
throw new Error(`Chat API (AI SDK ${protocol}) returned no content.`);
const text = completion.choices[0]?.message?.content ?? "";
console.log(summarizeSdkUsage(opts?.tag ?? "chat", completion.usage ?? undefined));
if (text.length === 0) {
throw new Error(`Chat API returned no content.`);
}
return text;
}