add the 'improvements and notes' section for the instruction/prompt files

Author: legomushroom

release-notes/v1_100.md

@@ -141,6 +141,7 @@ Instruction files use the `.instructions.md` file suffix. They can be located in
 Instructions files can be added manually or automatically to chat requests.
 - To add them manually, use the `Add Context ` button in the chat view and select `Instructions...`. Alternatively use the `Chat: Attach Instructions File...` command from the command palette. This brings aup a picker that lets you select existing instructions files or create a new one to attach.
 - To have them added automatically, add the `applyTo` header to the instructions file. If a chat request contains a file that matches the given pattern, the instructions file will be attached.
+
 ````md
 ---
 applyTo: '**/*.ts'
@@ -156,12 +157,12 @@ else
 }
 ````
 
+Similarly to the prompt files, the instruction files can now be created with the `> Chat: New Instructions File...` command. Moreover, the files created in the *user data* folder can be automatically synchronized across multiple user machines through the `Settings Sync` service. Note that the synchronization is required to be explicitly enabled by checking the `Prompts and Instructions` checkbox in the `Backup and Sync Settings...` dialog.
 
 **Prompt files** describe a complete chat request, including the user query, mode and tools to use.
 
 Prompt files use the `.prompt.md` file suffix. They can be located in your user data folder or in the workspace. The `setting(chat.promptFilesLocations)` setting lists the folder where prompt files are looked for.
 
-
 To run a prompt file, you can
 - type `/` in the chat input field and select your prompt file
 ![Run prompt as slash command](images/1_100/run-prompt-as-slash-command.png)
@@ -181,6 +182,16 @@ tools: ['getCurrentMilestone', 'getReleaseFeatures', 'file_search', 'semantic_se
 Generate release notes for the features I worked in the current release and update them in the release notes file. Use [release notes writing instructions file](.github/instructions/release-notes-writing.instructions.md) as a guide.
 ```
 
+#### Improvements and notes
+
+- instructions/prompt files that are open in active editor are now correctly treated as "prompt file" attachments (e.g., nested file references are resolved properly, etc.); this allows to iterate on the instructions/prompt files quickly while keep tunning them in the file editor
+- instructions and prompt files now have their own language IDs, configurable in the *language mode* dialog for any file open document ("Prompt" and "Instructions" appropriately); this allows, for instance, using untitled documents as temporary prompt files before saving them as files to the disk
+- the '> Chat: Use Prompt...' command is now accessible as '> Chat: Run Prompt...' in the command palette; furthermore, the command now runs the selected prompt *immediately*, as opposed to merely attaching it to the chat context as it did before
+- both file types now also support the `description` metadata in their headers, providing a common place for short and user-friendly prompt summaries; in the future, this header is planned to be used along with the `applyTo` header as the rule that determines if the file needs to be auto-included with chat requests (e.g., `description: 'Code style rules for front-end components written in TypeScript.'`)
+- the `applyTo` header is currently supported only in the instruction files, and is considered invalid in the prompt files
+- the new `/save` chat command lets you quickly store chat history as a reusable prompt file; if the `agent` mode is used, any tools invoked during the session are automatically summarized into `tools` metadata in the file header and represents the minimal set of tools required for the stored reusable prompt to work
+
+
 ### MCP Support for Streamable HTTP
 
 This release adds support for the new Streamable HTTP transport for Model Context Protocol servers. Streamable HTTP servers are configured just like existing SSE servers, and our implementation is backwards-compatible with SSE servers: