Ivan Starkov istarkov

TTFB test, monitoring, api, performance testing

Queue/workflows processing https://temporal.io/

Fastpack - pack JavaScript fast & easy

This gist is a submission for a lightning talk on the ReactiveConf 2018.

	import { McpAgent } from "agents/mcp";
	import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
	import { z } from "zod";
	import { GoogleGenerativeAI } from "@google/generative-ai";
	import { Readability } from '@mozilla/readability';
	import { parseHTML } from 'linkedom';

	type Env = {
	MyMCP: DurableObjectNamespace<MyMCP>;
	GEMINI_API_KEY: string;

	Understand the Task: Grasp the main objective, goals, requirements, constraints, and expected output.
	- Minimal Changes: If an existing prompt is provided, improve it only if it's simple. For complex prompts, enhance clarity and add missing elements without altering the original structure.
	- Reasoning Before Conclusions: Encourage reasoning steps before any conclusions are reached. ATTENTION! If the user provides examples where the reasoning happens afterward, REVERSE the order! NEVER START EXAMPLES WITH CONCLUSIONS!
	- Reasoning Order: Call out reasoning portions of the prompt and conclusion parts (specific fields by name). For each, determine the ORDER in which this is done, and whether it needs to be reversed.
	- Conclusion, classifications, or results should ALWAYS appear last.
	- Examples: Include high-quality examples if helpful, using placeholders [in brackets] for complex elements.
	- What kinds of examples may need to be included, how many, and whether they are complex enough to benefit from p

	/*Parses ICU messages format https://messageformat.github.io/messageformat/guide/
	like
	{from} - {to} {results, plural,
	one { # result }
	many { # results }
	} text {vr} rmm
	{s, select,
	man { He is "#"#"#" }
	woman { She is # }
	}

	import { promises } from "fs";
	import crypto from "crypto";
	import path from "path";
	import { print, parse } from "graphql";

	const plugin = {
	name: "relay",
	setup: build => {
	build.onLoad({ filter: /\.tsx$/, namespace: "" }, async args => {
	let contents = await promises.readFile(args.path, "utf8");

	import base64
	import boto3

	def upload_base_64_to_s3(s3_bucket_name, s3_file_name, base_64_str):
	"""
	Allows for the upload of a base64 string to a s3 object, may need fleshing out down the line, returns location
	of file in S3
	:param s3_bucket_name: S3 bucket name to push image to
	:param s3_file_name: File name
	:param base_64_str: base 64 string of the image to push to S3

	const stream = require('stream')
	const cache = new Map() // you might wanna use an lru here

	function createCacheStream (url) {
	const buf = []
	return stream.Transform({
	transform: function (data, enc, cb) {
	buffer.push(data)
	cb(null, data)
	},

	class Frame extends Component {
	componentDidMount() {
	this.iframeHead = this.node.contentDocument.head
	this.iframeRoot = this.node.contentDocument.body
	this.forceUpdate()
	}

	render() {
	const { children, head, ...rest } = this.props
	return (