Replaces unused Prophet dependency (unrunnable without cmdstan) with
SARIMA (statsmodels SARIMAX) as the primary spending forecast algorithm.
Strategy: SARIMA(1,1,1)(1,0,1,12) for 12+ months of data, ARIMA(1,1,1)
for 6-11 months, Holt-Winters for 3-5 months, simple average below that.
Adds 95% confidence bands (1.96σ) alongside existing 80% (1.28σ).
Extends forecast horizon from 3 to 6 months and actuals display from
6 to 12 months. Each category now carries an algorithm field surfaced
as a badge in the UI. Frontend chart shows both confidence tiers as
stacked bar overlays with a 3-month summary grid below.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- OCR pipeline: Tesseract (images) + pdfplumber (PDFs) → AI text prompt →
rule-based regex fallback; works with any text model, not just vision models
- Scan Receipt toolbar button parses a photo and pre-fills the transaction form;
receipt image is automatically attached to the created transaction
- AI settings page: provider, API key (AES-256-GCM encrypted), custom URL,
model, and per-user debug toggle that gates the OCR/AI debug panel
- Fix CSRF cookie secure=False so HTTP deployments work; add 7-day max_age
- Fix attachment_refs missing from _to_response (attachments never appeared in UI)
- Fix multipart boundary lost when Content-Type was set manually in axios calls
- nginx: raise client_max_body_size to 15 MB, add 120s proxy timeout for OCR
- Migration 0005: add ai_debug boolean to users table
- Update README and CLAUDE.md with AI scanning docs and architecture notes
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
