Initial work on Vision support in text conversations and Image Editing

This is a huge patch which does some major refactoring like:

- renaming "Image Generation" to "Image Creation" in most places,
  to better match its new command (`!bai image create`)

- relocating image creation command (`!bai image` -> `!bai image create`),
  so it wouldn't conflict with the new image editing command (`!bai image edit`)

- introducing a new image editing command (`!bai image edit`), which
  is meant to work only with the OpenAI provider, but doesn't fully work yet
  due to https://github.com/64bit/async-openai/issues/364, though a next patch will fix it

- adding support for reading images off of Matrix conversations and forwarding them to
  text conversations. Works for OpenAI, but not for Anthropic yet
  (requires custom patches) and not for OpenAI-Compat (no support for
  images there)

- relocating some utils around (base64, mime)

src/strings/help/usage.rs

@@ -3,5 +3,5 @@ pub fn heading() -> &'static str {
 }
 
 pub fn intro() -> &'static str {
-    "The bot can perform various tasks, such as 💬 Text Generation, 🗣️ Text-to-Speech, 🦻 Speech-to-Text, 🖌️ Image Generation, and more."
+    "The bot can perform various tasks, such as 💬 Text Generation, 🗣️ Text-to-Speech, 🦻 Speech-to-Text, 🖌️ Image Creation, and more."
 }

src/strings/image_edit.rs

@@ -0,0 +1,15 @@
+pub fn guide_how_to_proceed() -> String {
+    let mut message = String::new();
+
+    message.push_str("💡 Respond in this thread (in any order) with:\n");
+    message.push_str("- one or more images: to use the given images for creating an edit\n");
+    message.push_str("- more messages: to expand on your original prompt\n");
+    message.push_str(
+        "- a message saying `go`: to generate an edit with the current prompt\n",
+    );
+    message.push_str(
+        "- a message saying `again`: to generate one more image edit with the current prompt\n",
+    );
+
+    message
+}

src/strings/image_generation.rs

@@ -8,7 +8,7 @@ pub fn guide_how_to_proceed() -> String {
     message.push_str("💡 Respond in this thread with:\n");
     message.push_str("- more messages: to expand on your original prompt\n");
     message.push_str(
-        "- a message saying `again`: to generate one more image with the current prompt.\n",
+        "- a message saying `again`: to generate one more image with the current prompt\n",
     );
 
     message

src/strings/mod.rs

@@ -5,6 +5,7 @@ pub mod error;
 pub mod global_config;
 pub mod help;
 pub mod image_generation;
+pub mod image_edit;
 pub mod introduction;
 pub mod provider;
 pub mod room_config;

src/strings/usage.rs

@@ -34,26 +34,26 @@ By default, the bot will also perform 💬 Text Generation on the text. This is
 If all your messages are in the same language, you can improve accuracy & latency by configuring the language via the **🦻 Speech-to-Text / 🔤 Language** setting.
 
 
-### 🖌️ Image Generation
+### 🖌️ Image Creation
 
-#### Generating images
+#### Creating images
 
-Simply send a command like `%command_prefix% image A beautiful sunset over the ocean` and the bot will start a threaded conversation and post an image based on your prompt.
+Simply send a command like `%command_prefix% image create A beautiful sunset over the ocean` and the bot will start a threaded conversation and post an image based on your prompt.
 
 You can then, respond in the same message thread with:
 
 - more messages, to add more criteria to your prompt.
 - a message saying `again`, to generate one more image with the current prompt.
 
-#### Generating stickers
+#### Creating stickers
 
-A variation of **generating images** is to generate "sticker images".
+A variation of **creating images** is to create "sticker images".
 
-To generate a sticker, send a command like `%command_prefix% sticker A huge bowl of steaming ramen with a mountain of beansprouts on top`.
+To create a sticker, send a command like `%command_prefix% sticker A huge bowl of steaming ramen with a mountain of beansprouts on top`.
 
-The difference from **generating images** is that the bot will:
+The difference from **creating images** is that the bot will:
 
-- generate a smaller-resolution image (`256x256`) - smaller/quicker, but still good enough for a sticker
+- create a smaller-resolution image (`256x256`) - smaller/quicker, but still good enough for a sticker
 - potentially switch to a different (cheaper or otherwise more suitable) model, if available
 - post the image directly to the room (as a reply to your message), without starting a threaded conversation
 "#;