文件列表:

CONTRIBUTING.md (1645, 2023-05-03)
chatgpt-down-messages.txt (9303, 2023-05-03)
client-side-js (0, 2023-05-03)
client-side-js\[Not used anymore] 113-23682f80a24dd00d.js (96679, 2023-05-03)
client-side-js\[Not used anymore] 264-13e92c51b0315184.js (17604, 2023-05-03)
fonts.txt (505, 2023-05-03)
images (0, 2023-05-03)
images\Getting-Conversation-ID.png (190939, 2023-05-03)
images\Markdown-in-code-block-rendered.gif (720444, 2023-05-03)
images\chatgpt-plus-login-link.gif (532003, 2023-05-03)
images\markdown.png (116318, 2023-05-03)
images\regenerated-response-feedback.png (7284, 2023-05-03)
markdown-support.csv (1355, 2023-05-03)
markdown-tester.txt (3985, 2023-05-03)
sample (0, 2023-05-03)
sample\chat.html (2407, 2023-05-03)
sample\conversations.json (1598, 2023-05-03)
sample\model_comparisons.json (2731, 2023-05-03)

## Table of Contents - [Fonts (fonts.txt)](#fonts-fontstxt) - [Application](#application) - [Data](#data) - [Session data](#session-data) - [User data](#user-data) - [User data (using ~~chat.json~~ [chatId].json)](#user-data-using-chatjson-chatidjson) - [Model data](#model-data) - [Disabling/Enabling "Chat History & Training"](#disablingenabling-chat-history--training) - [Data Export](#data-export) - [Conversation](#conversation) - [Conversation History](#conversation-history) - [Getting the Conversation ID](#getting-the-conversation-id) - [Loading a Past Conversation](#loading-a-past-conversation) - [The process of asking ChatGPT a question](#the-process-of-asking-chatgpt-a-question) - [(Soft)Deleting a conversation](#softdeleting-a-conversation) - [Can you revive a conversation?](#can-you-revive-a-conversation) - [Clearing Conversations](#clearing-conversations) - [Leaving Feedback on Messages (Thumbs Up/Thumbs Down)](#leaving-feedback-on-messages-thumbs-upthumbs-down) - [Leaving Feedback (on Regenerated Responses)](#leaving-feedback-on-regenerated-responses) - [Renaming Conversations](#renaming-conversations) - [Errors](#errors) - ["_Something went wrong, please try reloading the conversation._"](#something-went-wrong-please-try-reloading-the-conversation) - ["_The message you submitted was too long, please reload the conversation and submit something shorter._"](#the-message-you-submitted-was-too-long-please-reload-the-conversation-and-submit-something-shorter) - ["_Conversation not found_"](#conversation-not-found) - [Markdown rendering](#markdown-rendering) - [ChatGPT Plus](#chatgpt-plus) - [GPT-4 for Free Users? (nope)](#gpt-4-for-free-users-nope) - [Access ChatGPT when it's down](#access-chatgpt-when-its-down) - [Rendering Markdown _inside_ a code block](#rendering-markdown-inside-a-code-block) - [Minified client-side JS](#minified-client-side-js) - [Statsig Feature Gates](#statsig-feature-gates) ## Fonts _([fonts.txt](./fonts.txt))_ > **Warning** > **All fonts in the previous list are no longer accessible at the `https://chat.openai.com/fonts/[font]` endpoint. The new fonts.txt file assumes the prefix of the URLs to be `https://cdn.openai.com/common/fonts/`** **This is a _non exhaustive_ list of fonts that come from cdn.openai.com:** - [soehne-buch.woff2](https://cdn.openai.com/common/fonts/soehne/soehne-buch.woff2) - [soehne-halbfett.woff2](https://cdn.openai.com/common/fonts/soehne/soehne-halbfett.woff2) - [soehne-mono-buch.woff2](https://cdn.openai.com/common/fonts/soehne/soehne-mono-buch.woff2) - [soehne-mono-halbfett.woff2](https://cdn.openai.com/common/fonts/soehne/soehne-mono-halbfett.woff2) - [KaTeX_Main-Regular.woff2](https://cdn.openai.com/common/fonts/katex/KaTeX_Main-Regular.woff2) (+ Main-Bold, Main-Italic, Main-BoldItalic) - [KaTeX_Math-Italic.woff2](https://cdn.openai.com/common/fonts/katex/KaTeX_Math-Italic.woff2) (+ Math-BoldItalic) - [KaTeX_Size2-Regular.woff2](https://cdn.openai.com/common/fonts/katex/KaTeX_Size2-Regular.woff2) (+ Size1, Size3, Size4) - [KaTeX_Caligraphic-Regular.woff2](https://cdn.openai.com/common/fonts/katex/KaTeX_Caligraphic-Regular.woff2) (+ Caligraphic-Bold) **Earlier list of fonts that are no longer accessible:** - ~~[Signifier-Regular.otf](https://chat.openai.com/fonts/Signifier-Regular.otf)~~ - ~~[Sohne-Buch.otf](https://chat.openai.com/fonts/Sohne-Buch.otf)~~ - ~~[Sohne-Halbfett.otf](https://chat.openai.com/fonts/Sohne-Halbfett.otf)~~ - ~~[SohneMono-Buch.otf](https://chat.openai.com/fonts/SohneMono-Buch.otf)~~ - ~~[SohneMono-Halbfett.otf](https://chat.openai.com/fonts/SohneMono-Halbfett.otf)~~ - ~~[KaTeX_Caligraphic-Bold.woff](https://chat.openai.com/fonts/KaTeX_Caligraphic-Bold.woff) (_Caligraphic-Regular_ for Regular font)~~ - ~~[KaTeX_Fraktur-Bold.woff](https://chat.openai.com/fonts/KaTeX_Fraktur-Bold.woff) (_Fraktur-Regular_ for Regular font)~~ - ~~[KaTeX_Main-Bold.woff](https://chat.openai.com/fonts/KaTeX_Main-Bold.woff) (_BoldItalic_, _Italic_, _Regular_ for font weights you can probably guess)~~ - ~~[KaTeX_Math-Bold.woff](https://chat.openai.com/fonts/KaTeX_Math-Bold.woff) (_BoldItalic_, _Italic_, _Regular_ for font weights you can probably guess)~~ - ~~[KaTeX_SansSerif-Bold.woff](https://chat.openai.com/fonts/KaTeX_SansSerif-Bold.woff) (_Italic_, _Regular_ for font weights you can probably guess)~~ - ~~[KaTeX_Script-Regular.woff](https://chat.openai.com/fonts/KaTeX_Script-Regular.woff)~~ - ~~[KaTeX_Size1-Regular.woff](https://chat.openai.com/fonts/KaTeX_Size1-Regular.woff) (_Size1_, _Size2_, _Size3_, _Size4_)~~ - ~~[KaTeX_Typewriter-Regular.woff](https://chat.openai.com/fonts/KaTeX_Typewriter-Regular.woff)~~ ## Application ChatGPT is a NextJS application. Server information cannot be clearly found as the entirety of chat.openai.com is routed through Cloudflare. Sentry Analytics are requested ~~for the Thumbs Up/Thumbs Down feedback the user selects for a message~~ periodically. Statsig is attempted to be loaded but CORS blocks it due to the Same Origin Policy **(actually an effect of uBlock Origin)**. ## Data ### Session data A request can be made to `/api/auth/session` (literally, **in your browser**, however cannot work in an iframe or fetch because it doesn't have a `Access-Control-Allow-Origin` set up) to access data like the following: ``` user |__ id: user-[redacted] |__ name: [redacted]@[redacted].com (probably can be a user's name) |__ email: [redacted]@[redacted].com |__ image: https://s.gravatar.com/avatar/8cf[redacted in case of possible unique identifier]2c7?s=480&r=pg&d=https%3A%2F%2Fcdn.auth0.com%2Favatars%2F[first 2 letters of name].png |__ picture: https://s.gravatar.com/avatar/8cf[redacted in case of possible unique identifier]2c7?s=480&r=pg&d=https%3A%2F%2Fcdn.auth0.com%2Favatars%2F[first 2 letters of name].png |__ groups: [] expires: [date in the future] accessToken: ey[redacted] (base*** "{") ``` ### User data This requires an access token (which seems to be the ~~Authorization cookie, along with other factors~~ Authorization header), so this cannot be accessed using your browser directly, but here's what we have when we make a request to `/backend-api/accounts/check`: ``` account_plan |__ is_paid_subscription_active: false |__ subscription_plan: chatgptfreeplan |__ account_user_role: account-owner |__ was_paid_customer: false |__ has_customer_object: false user_country: [redacted two letter country code] features: ["system_message"] ``` (Note: false in the above does not include quotes, whereas other values are in quotes, removed in the above _schema?_) ### User data (using ~~chat.json~~ [chatId].json) When we make a request to `/_next/data/[build ID]/c/[conversation ID].json?chatId=[conversation ID]` (can be done in the browser, cannot be done without authentication), we get a response like this: ``` pageProps: |__ user (Object): |____ id: user-[redacted] |____ name: [redacted]@[redacted].com |____ email: [redacted]@[redacted].com |____ image: https://s.gravatar.com/avatar/8c[redacted in case of possible unique identifier]c7?s=480&r=pg&d=https%3A%2F%2Fcdn.auth0.com%2Favatars%2F[first two letters of email address].png |____ picture: https://s.gravatar.com/avatar/8c[redacted in case of possible unique identifier]c7?s=480&r=pg&d=https%3A%2F%2Fcdn.auth0.com%2Favatars%2F[first two letters of email address].png |____ groups: [] |__ serviceStatus: {} |__ userCountry: [redacted two letter country code] |__ geoOk: false |__ isUserInCanPayGroup: true |__ __N_SSP: true ``` This is the some of the same data (excluding accessToken and expires, both relevant to an access token) you get using the method in [Session data](#session-data) except you also get info about the country the user is located in and whether ChatGPT Plus is available in their location. **EDIT:** When ChatGPT returns a message like "_We're experiencing exceptionally high demand. Please hang tight as we work on scaling our systems._", `serviceStatus` looks like this: ``` type: warning message: We're experiencing exceptionally high demand. Please hang tight as we work on scaling our systems. oof: true ``` I didn't make up the `oof` variable, that is actually part of the response ### Model data What model does ChatGPT use? Well, just query `/backend-api/models`! ``` models |__ |____ slug: text-davinci-002-render-sha |____ max_tokens: 4097 |____ title: Turbo (Default for free users) |____ description: The standard ChatGPT model |____ tags: [] |____ qualitative_properties: {} ``` This means that ChatGPT can _remember context (based on what I can understand)_ for 16388 characters or 3072.75 words (or 2048.5 s). _* Approximation according to [OpenAI help article](https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them)_ ### Disabling/Enabling "Chat History & Training" When you click your name/email address in the bottom-left corner of the screen (on desktop) > Settings > Show (next to Data Controls) > toggle next to Chat History and Training, the following happens: First, [the list of conversations is requested](#conversation-history). Then we make a request to the same path as [Model data](#model-data), except a query parameter is added to the URL `?history_and_training_disabled=true` or `?history_and_training_disabled=false` depending on whether the setting is disabled or enabled respectively. Then, we request `/_next/data/[build ID]/index.json` (with the same data as [[chatId].json](#user-data-using-chatjson-chatidjson)). ### Data Export When you use the "Export data" feature to export your data, a POST request is made to `/backend-api/accounts/data_export` with no request body and the response of `status: "queued"`. As the name suggests, a data export is sent by email. The data export is a `.zip` file containing `user.json`, `conversations.json`, `message_feedback.json`, `model_comparisons.json`, `chat.html`. The data in `user.json` looks like this: ```json {"id": "user-[redacted]", "email": "[redacted]@[redacted].com", "chatgpt_plus_user": false, "phone_number": "+[redacted]"} ``` Sample data for `model_comparisons.json` is in [sample/model_comparisons.json](./sample/model_comparisons.json) Sample data for `message_feedback.json`: ```json [{"message_id": "[redacted]", "conversation_id": "[conversationidwithoutdashes]", "user_id": "user-[redacted]", "rating": "thumbsUp", "content": "{\"text\": \"This is a test.\"}"}] ``` Sample data for `conversations.json` is in [sample/conversations.json](./sample/conversations.json) `chat.html` is a page that dynamically (using client-side JS) displays entire chat history for every conversation saved using conversation data (stored in the file) similar to that from `conversations.json`. You can find a sample in [sample/chat.html](./sample/chat.html) ## Conversation ### Conversation History Conversation history can be accessed (again, requires an access token, which seems to be the Authorization header) at `/backend-api/conversations?offset=0&limit=20` (the web interface limits it to 20 chats) which returns something like this: ``` items: [] limit: 20 offset: 0 total: 0 ``` It doesn't work because ChatGPT is having some issues at the time of writing: > "_Not seeing what you expected here? Don't worry, your conversation data is preserved! Check back soon._" But this is probably what a person new to ChatGPT sees. **EDIT: If you log out and log back in, history works just fine. So, here's what I see** ``` items (array) |__ (each conversation is an object) |____ id: [redacted conversation ID] |____ title: [conversation title] |____ create_time: 2023-03-09THH:MM:SS.MILLIS |__... total: [number of conversations] (can be greater than 20) limit: 20 offset: 0 (can be set to a higher number and it returns the conversations after that index, starting from 0) ``` **After 20 conversations listed, the ChatGPT UI shows a `Show more` button which sends a request with `offset=20`** ### Getting the Conversation ID Speaking of ChatGPT conversation history not being available, we can get the Conversation ID pretty easily (to someone who is familiar with DevTools, that is) Why? Because ChatGPT forces you into a ~~/chat~~ `/` path for a new conversation, creates a conversation, **BUT DOESN'T CHANGE THE URL**. This is also helpful when chat history isn't available. 1. We get the Conversation ID using DevTools (this requires a message to be sent)  2. Then, we visit ~~`https://chat.openai.com/chat/`~~ `https://chat.openai.com/c/`. ### Loading a Past Conversation When the user clicks on a past conversation, a request is made (requiring an access token, ~~likely the cookie with other factors to ensure genuine requests~~ an Authorization header) to `/backend-api/conversation/` with a response like this: ``` title: