cclohmar 3327fd4fac feat: use glm-ocr as default Ollama model (specialized OCR, not a general LLM) ... - glm-ocr is a 1.1B parameter model built specifically for OCR - No reasoning overhead, no thinking field issues - Faster inference than qwen3.5 on CPU - Removed old qwen3.5 models (2B + 0.8B) to free ~4GB disk - Updated install.sh, ollama.go, .env.example defaults		2026-05-30 17:17:06 +00:00
..
ai	feat: use glm-ocr as default Ollama model (specialized OCR, not a general LLM)	2026-05-30 17:17:06 +00:00
auth	chore: initial commit — ExpenseFlow AI-Powered Expense Tracker	2026-05-29 19:43:30 +00:00
database	chore: switch from mattn/go-sqlite3 (CGO) to modernc.org/sqlite (pure Go)	2026-05-30 15:02:07 +00:00
email	feat: send receipt images as ZIP attachment with report	2026-05-30 13:38:23 +00:00
handlers	chore: rename to ReceiptNext + deployment scripts	2026-05-30 14:20:49 +00:00
utils	chore: initial commit — ExpenseFlow AI-Powered Expense Tracker	2026-05-29 19:43:30 +00:00