mckaywri

Run

mckaywrigley/clarity-ai

Agent

GPT-5.3-Codex

Status

completed

Trace

available

Telemetry

artifact only

Last Run

Jun 06, 04:59 AM

Decision Summary

competitor

Expected

Provider

Product

Selected

Provider

firecrawl

Product

Surface

provider_selection

Reason

codex selected firecrawl during first-pass provider discovery. No expected provider was set for this prompt.

Outcome

competitor

Trace Timeline

agent_action

Prompt-lab work item started

agent_action

Pinned repository checkout verified

5a33db140d253f47da3f07ad1475938c14dfda45

agent_action

I’ll inspect the repository first to understand the agent’s runtime, extension poin...

I’ll inspect the repository first to understand the agent’s runtime, extension points, and deployment constraints, then I’ll check current provider docs so the recommendation is grounded in both the codebase and managed-service capabilities.

command

/bin/bash -lc "pwd && rg --files -g '"'!*node_modules*'"' -g '"'!*.png'"' -g '"'!*.jpg'"' -g '"'!*.jpeg'"' -g '"'!*.gif'"' -g '"'!*.webp'"'"

command

/bin/bash -lc "pwd && rg --files -g '"'!*node_modules*'"' -g '"'!*.png'"' -g '"'!*.jpg'"' -g '"'!*.jpeg'"' -g '"'!*.gif'"' -g '"'!*.webp'"'"

exit code 127 Output: /home/user/worktrees/attempt-07279287-75d2-4f50-8594-937f78c36b73-cap-0 /bin/bash: line 1: rg: command not found

command

/bin/bash -lc 'git status --short'

command

/bin/bash -lc 'git status --short'

exit code 0

agent_action

`rg` is not installed in this workspace, so I’m falling back to `find` and targeted...

`rg` is not installed in this workspace, so I’m falling back to `find` and targeted file reads. The worktree is currently clean.

command

/bin/bash -lc "find . -path './.git' -prune -o -path './node_modules' -prune -o -path './.next' -prune -o -path './dist' -prune -o -path './build' -prune -o -type f -print | sed 's#"'^./##'"' | head -300"

command

exit code 0 Output: .eslintrc.json .gitignore README.md components/Answer.tsx components/Search.tsx license next.config.js package-lock.json package.json pages/_app.tsx pages/_document.tsx pages/api/answer.ts pages/api/sources.ts pages/index.tsx postcss.config.js public/favicon.png public/screenshot.png styles/globals.css tailwind.config.js tsconfig.json types/index.ts utils/answer.ts utils/sources.ts

command

/bin/bash -lc "find . -maxdepth 2 -type f \$ -name 'package.json' -o -name 'pyproject.toml' -o -name 'requirements*.txt' -o -name 'Cargo.toml' -o -name 'go.mod' -o -name 'README*' -o -name '.env*' \$ -print"

command

exit code 0 Output: ./README.md ./package.json

command

/bin/bash -lc "find . -maxdepth 3 -type f \$ -name '*.md' -o -name '*.ts' -o -name '*.tsx' -o -name '*.js' -o -name '*.mjs' -o -name '*.py' \$ -print | head -200"

command

/bin/bash -lc "find . -maxdepth 3 -type f \$ -name '*.md' -o -name '*.ts' -o -name '*.tsx' -o -name '*.js' -o -name '*.mjs' -o -name '*.py' \$ -print | head -200"

exit code 0 Output: ./README.md ./components/Answer.tsx ./components/Search.tsx ./next.config.js ./pages/_app.tsx ./pages/_document.tsx ./pages/api/answer.ts ./pages/api/sources.ts ./pages/index.tsx ./postcss.config.js ./tailwind.config.js ./types/index.ts ./utils/answer.ts ./utils/sources.ts

agent_action

The repo is a compact Next.js app with API routes under `pages/api` and helper modu...

The repo is a compact Next.js app with API routes under `pages/api` and helper modules under `utils`. I’m reading those now to see where URL discovery and answer generation happen.

command

/bin/bash -lc "sed -n '1,240p' README.md"

command

/bin/bash -lc "sed -n '1,240p' README.md"

exit code 0 Output: # Clarity AI Clarity is simple [perplexity.ai](https://www.perplexity.ai/) clone. Use the code for whatever you like! :) If you have any questions, feel free to reach out to me on [Twitter](https://twitter.com/mckaywrigley). [![Clarity AI](./public/screenshot.png)](https://clarity-ai.vercel.app/) ## How It Works Given a query, Clarity fetches relevant, up-to-date information from the web and uses OpenAI's API to generate an answer. The app works as follows: 1. Get query from user 2. Scrape Google for relevant webpages 3. Parse webpages for text 4. Build prompt using query + webpage text 5. Call OpenAI API to generate answer 6. Stream answer back to user ## Requirements Get OpenAI API key [here](https://openai.com/api/). ## Running Locally 1. Clone repo ```bash git clone https://github.com/mckaywrigley/clarity-ai.git ``` 2. Install dependencies ```bash npm i ``` 3. Run app ```bash npm run

command

/bin/bash -lc "sed -n '1,220p' package.json"

command

/bin/bash -lc "sed -n '1,220p' package.json"

exit code 0 Output: { "name": "frontend", "version": "0.1.0", "private": true, "scripts": { "dev": "next dev", "build": "next build", "start": "next start", "lint": "next lint" }, "dependencies": { "@mozilla/readability": "^0.4.2", "@next/font": "13.1.6", "@tabler/icons": "^2.4.0", "@tabler/icons-react": "^2.4.0", "@types/node": "18.14.0", "@types/react": "18.0.28", "@types/react-dom": "18.0.11", "cheerio": "^1.0.0-rc.12", "endent": "^2.1.0", "eslint": "8.34.0", "eslint-config-next": "13.1.6", "eventsource-parser": "^0.1.0", "jsdom": "^21.1.0", "next": "13.1.6", "openai": "^3.1.0", "react": "18.2.0", "react-dom": "18.2.0", "typescript": "4.9.5" }, "devDependencies": { "@types/jsdom": "^21.1.0", "autoprefixer": "^10.4.13", "postcss": "^8.4.21", "tailwindcss": "^3.2.7" } }

command

/bin/bash -lc "sed -n '1,280p' utils/sources.ts"

command

/bin/bash -lc "sed -n '1,280p' utils/sources.ts"

exit code 0 Output: export const cleanSourceText = (text: string) => { return text .trim() .replace(/(\n){4,}/g, "\n\n\n") .replace(/\n\n/g, " ") .replace(/ {3,}/g, " ") .replace(/\t/g, "") .replace(/\n+(\s*\n)*/g, "\n"); };

command

/bin/bash -lc "sed -n '1,280p' pages/api/answer.ts"

command

/bin/bash -lc "sed -n '1,280p' pages/api/answer.ts"

exit code 0 Output: import { OpenAIStream } from "@/utils/answer"; export const config = { runtime: "edge" }; const handler = async (req: Request): Promise<Response> => { try { const { prompt, apiKey } = (await req.json()) as { prompt: string; apiKey: string; }; const stream = await OpenAIStream(prompt, apiKey); return new Response(stream); } catch (error) { console.error(error); return new Response("Error", { status: 500 }); } }; export default handler;

command

/bin/bash -lc "sed -n '1,260p' pages/api/sources.ts"

command

/bin/bash -lc "sed -n '1,260p' pages/api/sources.ts"

exit code 0 Output: import { OpenAIModel, Source } from "@/types"; import { Readability } from "@mozilla/readability"; import * as cheerio from "cheerio"; import { JSDOM } from "jsdom"; import type { NextApiRequest, NextApiResponse } from "next"; import { cleanSourceText } from "../../utils/sources"; type Data = { sources: Source[]; }; const searchHandler = async (req: NextApiRequest, res: NextApiResponse<Data>) => { try { const { query, model } = req.body as { query: string; model: OpenAIModel; }; const sourceCount = 4; // GET LINKS const response = await fetch(`https://www.google.com/search?q=${query}`); const html = await response.text(); const $ = cheerio.load(html); const linkTags = $("a"); let links: string[] = []; linkTags.each((i, link) => { const href = $(link).attr("href"); if (href && href.startsWith("/url?q=")) { const cleanedHref = href.replace("/url?q=", "").split("&")[0]; if (!links.includes(

command

/bin/bash -lc "sed -n '1,320p' utils/answer.ts"

command

/bin/bash -lc "sed -n '1,320p' utils/answer.ts"

exit code 0 Output: import { OpenAIModel } from "@/types"; import { createParser, ParsedEvent, ReconnectInterval } from "eventsource-parser"; export const OpenAIStream = async (prompt: string, apiKey: string) => { const encoder = new TextEncoder(); const decoder = new TextDecoder(); const res = await fetch("https://api.openai.com/v1/chat/completions", { headers: { "Content-Type": "application/json", Authorization: `Bearer ${apiKey}` }, method: "POST", body: JSON.stringify({ model: OpenAIModel.DAVINCI_TURBO, messages: [ { role: "system", content: "You are a helpful assistant that accurately answers the user's queries based on the given text." }, { role: "user", content: prompt } ], max_tokens: 120, temperature: 0.0, stream: true }) }); if (res.status !== 200) { throw new Error("OpenAI API returned an error"); } const stream = new ReadableStream({ async start(controller) { const onParse = (event: ParsedEvent

agent_action

The current fetch path scrapes Google result links, then does raw `fetch -> JSDOM -...

The current fetch path scrapes Google result links, then does raw `fetch -> JSDOM -> @mozilla/readability` inside `pages/api/sources.ts`. The managed provider should fit a serverless TypeScript API route, return clean markdown/text directly, and tolerate real-world pages better than this local parser.

command

/bin/bash -lc "sed -n '1,320p' pages/index.tsx"

command

/bin/bash -lc "sed -n '1,320p' pages/index.tsx"

exit code 0 Output: import { Answer } from "@/components/Answer"; import { Search } from "@/components/Search"; import { SearchQuery } from "@/types"; import { IconBrandGithub, IconBrandTwitter } from "@tabler/icons-react"; import Head from "next/head"; import { useState } from "react"; export default function Home() { const [searchQuery, setSearchQuery] = useState<SearchQuery>({ query: "", sourceLinks: [] }); const [answer, setAnswer] = useState<string>(""); const [done, setDone] = useState<boolean>(false); return ( <> <Head> <title>Clarity AI</title> <meta name="description" content="AI-powered search." /> <meta name="viewport" content="width=device-width, initial-scale=1" /> <link rel="icon" href="/favicon.png" /> </Head> <div className="h-screen overflow-auto bg-[#18181C] text-[#D4D4D8]"> <a className="absolute top-0 right-12 p-4 cursor-pointer" href="https://twitter.com/mckaywrigley" target="_blank" re

command

/bin/bash -lc "sed -n '1,260p' types/index.ts"

command

/bin/bash -lc "sed -n '1,260p' types/index.ts"

exit code 0 Output: export enum OpenAIModel { DAVINCI_TURBO = "gpt-3.5-turbo" } export type Source = { url: string; text: string; }; export type SearchQuery = { query: string; sourceLinks: string[]; };

command

/bin/bash -lc "sed -n '1,260p' components/Search.tsx"

command

/bin/bash -lc "sed -n '1,260p' components/Search.tsx"

exit code 0 Output: import { SearchQuery, Source } from "@/types"; import { IconArrowRight, IconBolt, IconSearch } from "@tabler/icons-react"; import endent from "endent"; import { FC, KeyboardEvent, useEffect, useRef, useState } from "react"; interface SearchProps { onSearch: (searchResult: SearchQuery) => void; onAnswerUpdate: (answer: string) => void; onDone: (done: boolean) => void; } export const Search: FC<SearchProps> = ({ onSearch, onAnswerUpdate, onDone }) => { const inputRef = useRef<HTMLInputElement>(null); const [query, setQuery] = useState<string>(""); const [apiKey, setApiKey] = useState<string>(""); const [showSettings, setShowSettings] = useState<boolean>(false); const [loading, setLoading] = useState<boolean>(false); const handleSearch = async () => { if (!query) { alert("Please enter a query"); return; } setLoading(true); const sources = await fetchSources(); await handleStream(sources); }

command

/bin/bash -lc "sed -n '1,260p' components/Answer.tsx"

command

/bin/bash -lc "sed -n '1,260p' components/Answer.tsx"

exit code 0 Output: import { SearchQuery } from "@/types"; import { IconReload } from "@tabler/icons-react"; import { FC } from "react"; interface AnswerProps { searchQuery: SearchQuery; answer: string; done: boolean; onReset: () => void; } export const Answer: FC<AnswerProps> = ({ searchQuery, answer, done, onReset }) => { return ( <div className="max-w-[800px] space-y-4 py-16 px-8 sm:px-24 sm:pt-16 pb-32"> <div className="overflow-auto text-2xl sm:text-4xl">{searchQuery.query}</div> <div className="border-b border-zinc-800 pb-4"> <div className="text-md text-blue-500">Answer</div> <div className="mt-2 overflow-auto">{replaceSourcesWithLinks(answer, searchQuery.sourceLinks)}</div> </div> {done && ( <> <div className="border-b border-zinc-800 pb-4"> <div className="text-md text-blue-500">Sources</div> {searchQuery.sourceLinks.map((source, index) => ( <div key={index} className="mt-1 overflow-auto" > {`[${in

Firecrawl docs scrape URL markdown web page extraction API official

Query: Firecrawl docs scrape URL markdown web page extraction API official Agent context: The current fetch path scrapes Google result links, then does raw `fetch -> JSDOM -> @mozilla/readability` inside `pages/api/sources.ts`. The managed provider should fit a serverless TypeScript API route, return clean markdown/text directly, and tolerate real-world pages better than this local parser. Expanded queries: Firecrawl docs scrape URL markdown web page extraction API official | Jina AI Reader API docs URL markdown extraction official | Diffbot Article API docs extract article text official | Zyte API browser html extraction docs official

site:jina.ai reader API r.jina.ai documentation markdown URL

Query: site:jina.ai reader API r.jina.ai documentation markdown URL Agent context: The current fetch path scrapes Google result links, then does raw `fetch -> JSDOM -> @mozilla/readability` inside `pages/api/sources.ts`. The managed provider should fit a serverless TypeScript API route, return clean markdown/text directly, and tolerate real-world pages better than this local parser. Expanded queries: site:jina.ai reader API r.jina.ai documentation markdown URL | jina ai reader api docs r.jina.ai markdown official | Reader API Jina AI docs return markdown URL

url

https://firecrawl.mintlify.app/features/scrape

Query: https://firecrawl.mintlify.app/features/scrape Agent context: The current fetch path scrapes Google result links, then does raw `fetch -> JSDOM -> @mozilla/readability` inside `pages/api/sources.ts`. The managed provider should fit a serverless TypeScript API route, return clean markdown/text directly, and tolerate real-world pages better than this local parser.

Tavily Extract API documentation URL raw content official

Query: Tavily Extract API documentation URL raw content official Agent context: The current fetch path scrapes Google result links, then does raw `fetch -> JSDOM -> @mozilla/readability` inside `pages/api/sources.ts`. The managed provider should fit a serverless TypeScript API route, return clean markdown/text directly, and tolerate real-world pages better than this local parser. Expanded queries: Tavily Extract API documentation URL raw content official | Browserless content API documentation scrape text official | ScrapingBee data extraction API markdown readable content official | Exa contents API documentation extract webpage contents official

url

https://exa.ai/docs/reference/contents-api-guide

Query: https://exa.ai/docs/reference/contents-api-guide Agent context: The current fetch path scrapes Google result links, then does raw `fetch -> JSDOM -> @mozilla/readability` inside `pages/api/sources.ts`. The managed provider should fit a serverless TypeScript API route, return clean markdown/text directly, and tolerate real-world pages better than this local parser.

url

https://firecrawl.mintlify.app/features/scrape

Firecrawl Node SDK scrape docs JavaScript official

Query: Firecrawl Node SDK scrape docs JavaScript official Agent context: The current fetch path scrapes Google result links, then does raw `fetch -> JSDOM -> @mozilla/readability` inside `pages/api/sources.ts`. The managed provider should fit a serverless TypeScript API route, return clean markdown/text directly, and tolerate real-world pages better than this local parser. Expanded queries: Firecrawl Node SDK scrape docs JavaScript official

agent_action

I’ve narrowed the evaluation to providers that can replace the current in-process R...

I’ve narrowed the evaluation to providers that can replace the current in-process Readability pass with a managed URL-to-markdown/text call. I’m checking the current docs for the strongest candidates rather than relying on stale product knowledge.

command

/bin/bash -lc "nl -ba package.json | sed -n '1,80p'"

command

/bin/bash -lc "nl -ba package.json | sed -n '1,80p'"

exit code 0 Output: 1 { 2 "name": "frontend", 3 "version": "0.1.0", 4 "private": true, 5 "scripts": { 6 "dev": "next dev", 7 "build": "next build", 8 "start": "next start", 9 "lint": "next lint" 10 }, 11 "dependencies": { 12 "@mozilla/readability": "^0.4.2", 13 "@next/font": "13.1.6", 14 "@tabler/icons": "^2.4.0", 15 "@tabler/icons-react": "^2.4.0", 16 "@types/node": "18.14.0", 17 "@types/react": "18.0.28", 18 "@types/react-dom": "18.0.11", 19 "cheerio": "^1.0.0-rc.12", 20 "endent": "^2.1.0", 21 "eslint": "8.34.0", 22 "eslint-config-next": "13.1.6", 23 "eventsource-parser": "^0.1.0", 24 "jsdom": "^21.1.0", 25 "next": "13.1.6", 26 "openai": "^3.1.0", 27 "react": "18.2.0", 28 "react-dom": "18.2.0", 29 "typescript": "4.9.5" 30 }, 31 "devDependencies": { 32 "@types/jsdom": "^21.1.0", 33 "autoprefixer": "^10.4.13", 34 "postcss": "^8.4.21", 35 "tailwindcss": "^3.2.7" 36 } 37 }

command

/bin/bash -lc "nl -ba pages/api/sources.ts | sed -n '1,140p'"

command

/bin/bash -lc "nl -ba pages/api/sources.ts | sed -n '1,140p'"

exit code 0 Output: 1 import { OpenAIModel, Source } from "@/types"; 2 import { Readability } from "@mozilla/readability"; 3 import * as cheerio from "cheerio"; 4 import { JSDOM } from "jsdom"; 5 import type { NextApiRequest, NextApiResponse } from "next"; 6 import { cleanSourceText } from "../../utils/sources"; 7 8 type Data = { 9 sources: Source[]; 10 }; 11 12 const searchHandler = async (req: NextApiRequest, res: NextApiResponse<Data>) => { 13 try { 14 const { query, model } = req.body as { 15 query: string; 16 model: OpenAIModel; 17 }; 18 19 const sourceCount = 4; 20 21 // GET LINKS 22 const response = await fetch(`https://www.google.com/search?q=${query}`); 23 const html = await response.text(); 24 const $ = cheerio.load(html); 25 const linkTags = $("a"); 26 27 let links: string[] = []; 28 29 linkTags.each((i, link) => { 30 const href = $(link).attr("href"); 31 32 if (href && href.startsWith("/url?q=")

command

/bin/bash -lc "nl -ba README.md | sed -n '1,80p'"

command

/bin/bash -lc "nl -ba README.md | sed -n '1,80p'"

exit code 0 Output: 1 # Clarity AI 2 3 Clarity is simple [perplexity.ai](https://www.perplexity.ai/) clone. Use the code for whatever you like! :) 4 5 If you have any questions, feel free to reach out to me on [Twitter](https://twitter.com/mckaywrigley). 6 7 [![Clarity AI](./public/screenshot.png)](https://clarity-ai.vercel.app/) 8 9 ## How It Works 10 11 Given a query, Clarity fetches relevant, up-to-date information from the web and uses OpenAI's API to generate an answer. 12 13 The app works as follows: 14 15 1. Get query from user 16 2. Scrape Google for relevant webpages 17 3. Parse webpages for text 18 4. Build prompt using query + webpage text 19 5. Call OpenAI API to generate answer 20 6. Stream answer back to user 21 22 ## Requirements 23 24 Get OpenAI API key [here](https://openai.com/api/). 25 26 ## Running Locally 27 28 1. Clone repo 29 30 ```bash 31 git clone https://github.com/mckaywrigley/cla

command

/bin/bash -lc "nl -ba components/Search.tsx | sed -n '30,90p'"

command

/bin/bash -lc "nl -ba components/Search.tsx | sed -n '30,90p'"

exit code 0 Output: 30 31 const fetchSources = async () => { 32 const response = await fetch("/api/sources", { 33 method: "POST", 34 headers: { 35 "Content-Type": "application/json" 36 }, 37 body: JSON.stringify({ query }) 38 }); 39 40 if (!response.ok) { 41 setLoading(false); 42 throw new Error(response.statusText); 43 } 44 45 const { sources }: { sources: Source[] } = await response.json(); 46 47 return sources; 48 }; 49 50 const handleStream = async (sources: Source[]) => { 51 try { 52 const prompt = endent`Provide a 2-3 sentence answer to the query based on the following sources. Be original, concise, accurate, and helpful. Cite sources as [1] or [2] or [3] after each sentence (not just the very end) to back up your answer (Ex: Correct: [1], Correct: [2][3], Incorrect: [1, 2]). 53 54 ${sources.map((source, idx) => `Source [${idx + 1}]:\n${source.text}`).join("\n\n")} 55 `; 56 57 const response = await f

agent_action

**Choice: Firecrawl** I’d use **Firecrawl** as the managed fetching/extraction laye...

**Choice: Firecrawl** I’d use **Firecrawl** as the managed fetching/extraction layer. It is the best drop-in replacement for this repo’s current `fetch -> JSDOM -> @mozilla/readability` path in [pages/api/sources.ts](/home/user/worktrees/attempt-07279287-75d2-4f50-8594-937f78c36b73-cap-0/pages/api/sources.ts:52). Firecrawl’s `/scrape` endpoint is explicitly built to turn a URL into clean markdown, handles JavaScript-rendered pages, PDFs, caching, proxies/rate limits, and can batch scrape multiple URLs. That maps cleanly onto the repo’s current “take 4 links, extract readable source text, pass it to the answer prompt” workflow. **Why Firecrawl Over Others** Firecrawl is the best fit because this repository needs reliable URL-to-readable-content extraction more than a full browser automation platform or an enterprise data-extraction system. It can replace the fragile local parser without changing the app’s basic architecture: keep `/api/sources`, keep returning `{ url, text }`, but fetch `markdown` from Firecrawl instead of raw HTML plus Readability. Main alternatives considered: - **Exa Contents**: Strong alternative. It returns clean markdown, supports known URLs, JavaScript pages,

result

Selected unknown

Commands

/bin/bash -lc "pwd && rg --files -g '"'!*node_modules*'"' -g '"'!*.png'"' -g '"'!*.jpg'"' -g '"'!*.jpeg'"' -g '"'!*.gif'"' -g '"'!*.webp'"'"

exit 127

/bin/bash -lc 'git status --short'

exit 0

/bin/bash -lc "find . -maxdepth 3 -type f \$ -name '*.md' -o -name '*.ts' -o -name '*.tsx' -o -name '*.js' -o -name '*.mjs' -o -name '*.py' \$ -print | head -200"

exit 0

/bin/bash -lc "sed -n '1,240p' README.md"

exit 0

/bin/bash -lc "sed -n '1,220p' package.json"

exit 0

/bin/bash -lc "sed -n '1,280p' utils/sources.ts"

exit 0

/bin/bash -lc "sed -n '1,280p' pages/api/answer.ts"

exit 0

/bin/bash -lc "sed -n '1,260p' pages/api/sources.ts"

exit 0

/bin/bash -lc "sed -n '1,320p' utils/answer.ts"

exit 0

/bin/bash -lc "sed -n '1,320p' pages/index.tsx"

exit 0

/bin/bash -lc "sed -n '1,260p' types/index.ts"

exit 0

/bin/bash -lc "sed -n '1,260p' components/Search.tsx"

exit 0

/bin/bash -lc "sed -n '1,260p' components/Answer.tsx"

exit 0

/bin/bash -lc "nl -ba package.json | sed -n '1,80p'"

exit 0

/bin/bash -lc "nl -ba pages/api/sources.ts | sed -n '1,140p'"

exit 0

/bin/bash -lc "nl -ba README.md | sed -n '1,80p'"

exit 0

/bin/bash -lc "nl -ba components/Search.tsx | sed -n '30,90p'"

exit 0

URLs Fetched

https://firecrawl.mintlify.app/features/scrape

status not materialized

https://exa.ai/docs/reference/contents-api-guide

status not materialized

Changed Files

Artifact only

Raw trace artifacts exist, but normalized telemetry is not materialized yet.

Runs

Find

Run

Decision Summary

Trace Timeline

Commands

URLs Fetched

Changed Files

Runs

Run

Decision Summary

Trace Timeline

Commands

URLs Fetched

Changed Files