azaion/ai-training
1
0
Fork 0
mirror of https://github.com/azaion/ai-training.git synced 2026-04-22 09:16:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add core functionality for API client, CDN management, and data augmentation

Browse Source 
- Introduced `ApiClient` for handling API interactions, including file uploads and downloads.
- Implemented `CDNManager` for managing CDN operations with AWS S3.
- Added `Augmentator` class for image augmentation, including bounding box corrections and transformations.
- Created utility functions for annotation conversion and dataset visualization.
- Established a new rules file for sound notifications during human input requests.

These additions enhance the system's capabilities for data handling and user interaction, laying the groundwork for future features.

Simplify autopilot state file to minimal current-step pointer; add execution safety rule to cursor-meta; remove Completed Steps/Key Decisions/Retry Log/Blockers from state template and all references.
This commit is contained in:
Oleksandr Bezdieniezhnykh
2026-03-28 00:12:54 +02:00
parent 142c6c4de8
commit c20018745b
31 changed files with 0 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.cursor/rules/human-attention-sound.mdc
+24
View File
@@ -0,0 +1,24 @@
---
description: "Play a notification sound whenever the AI agent needs human input, confirmation, or approval"
alwaysApply: true
---
# Sound Notification on Human Input
Whenever you are about to ask the user a question, request confirmation, present options for a decision, or otherwise pause and wait for human input, you MUST first run the appropriate shell command for the current OS:
- **macOS**: `afplay /System/Library/Sounds/Glass.aiff &`
- **Linux**: `paplay /usr/share/sounds/freedesktop/stereo/bell.oga 2>/dev/null || aplay /usr/share/sounds/freedesktop/stereo/bell.oga 2>/dev/null || echo -e '\a' &`
- **Windows (PowerShell)**: `[System.Media.SystemSounds]::Exclamation.Play()`
Detect the OS from the user's system info or by running `uname -s` if unknown.
This applies to:
- Asking clarifying questions
- Presenting choices (e.g. via AskQuestion tool)
- Requesting approval for destructive actions
- Reporting that you are blocked and need guidance
- Any situation where the conversation will stall without user response
Do NOT play the sound when:
- You are providing a final answer that doesn't require a response
- You are in the middle of executing a multi-step task and just providing a status update