3 Commits

Include renames

Author	SHA1	Message	Date
Галингер Р.С.	d6c029f708	feat: preload Whisper model at startup with disk space check ... - Add WHISPER_MODEL_SIZE and WHISPER_MIN_FREE_SPACE_BYTES config options - voice.py now preloads/downloads the Whisper model at bot startup - Detailed logging for model presence, disk space, download progress and readiness - If model is already present locally, preload is skipped - If disk space is insufficient, bot fails fast with a clear error - main.py calls preload_model() after proxy setup and before polling - Document voice recognition model download behavior in README	2026-07-08 09:44:48 +07:00
Галингер Р.С.	0f674f8832	refactor: review fixes and code improvements ... - Add shared proxy module (bot/utils/proxy.py) to eliminate duplicate SOCKS5 parsing - Fix AI client: escape HTML before Markdown→HTML conversion, unify timeouts, make health check optional and disabled by default, handle 429 retries - Fix ai.py: correct forwarded message handling (aiogram 3.x forward_origin), pass relevant summaries via extra_system_content - Fix dialogue.py: only respond to Astra's messages, use system context instead of prompt injection, answer on the limit message before phase transition - Fix voice.py: load Whisper model in thread pool, safe WAV path generation - Improve database.py: composite indexes, Boolean is_active, upsert file_id cache, add context cleanup helper - Update weather.py and yadisk_download.py to use shared proxy connector - Update yadisk.py: validate URL before cache clear, add download size limit, wrap sync file ops in to_thread - Reuse S3 client via lru_cache - Update setup_commands with /aiclear and /aiuser - Update README, Dockerfile (Python 3.11), docker-compose (mount models) - Pin dependency versions, remove unused httpx[socks] - Add basic pytest tests for layout converter and voice normalization	2026-07-07 18:42:10 +07:00
Галингер Р.С.	76e5701eba	Initial commit: UMB Telegram Bot	2026-07-07 18:30:17 +07:00