Please let me pass in a tracer into the helper functions renderPrompt and the JSON one

[TylerLeonhardt]

I had to write this wrapper function to make things play nice:

export async function renderPrompt<P extends BasePromptElementProps>(endpoint: IChatEndpointInfo, ctor: PromptElementCtor<P, any>, props: P, model: LanguageModelChat, token: CancellationToken) {
    const renderer = new PromptRenderer(endpoint, ctor, props, new AnyTokenizer(model.countTokens));
    const tracer = new HTMLTracer();
    renderer.tracer = tracer;
    const result = await renderer.render(undefined, token);
    const server = await tracer.serveHTML();
    await window.withProgress({ location: ProgressLocation.Notification, title: `Tracer server running at ${server.address}`, cancellable: true }, async (progress, token) => {
        await new Promise<void>(resolve => {
            const dispose = token.onCancellationRequested(() => {
                dispose.dispose();
                server.dispose();
                resolve();
            });
        });
    });

    return {
        messages: toVsCodeChatMessages(result.messages) as LanguageModelChatMessage[],
        references: result.references
    };
}

Couple weird things about using PromptRenderer directly:

• requires import { AnyTokenizer } from "@vscode/prompt-tsx/dist/base/tokenizer/tokenizer";
• requires using toVsCodeChatMessages (which returns any[] btw)
• uses a ctor for something that's really only one time use (low pri)