Store previous analysis before regeneration and show comparison table
with priority breakdown, new/removed actions diff.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Instead of requiring users to click "Wygeneruj analize AI" every time,
the audit pages now automatically fetch cached analysis on DOMContentLoaded.
If cache exists, results render instantly; if not, the generate button remains.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Cache: exclude volatile citations fields from hash for better hit rate
- Thinking level: reduce from 'high' to 'low' for faster responses (13-24s → ~5-10s)
- UTF-8: html.unescape() on meta_title, meta_description, h1_text
- SEO score: add "(Google Lighthouse)" label and explanatory note
- Spinner: update text to "15-30 seconds" with live timer counter
- Auto-scroll: smooth scroll to results after AI analysis and content generation
- Cache info: show generation date with "Wygeneruj ponownie" link
- Markdown: render non-code AI content with basic markdown formatting
- Error feedback: inline error display with retry button instead of modal
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add Gemini AI integration to SEO, GBP, and Social Media audits that
generates contextual analysis summaries and prioritized action items
with ready-to-use content (Schema.org, meta descriptions, social posts,
GBP descriptions, review responses, content calendars).
New files:
- audit_ai_service.py: Central AI service with caching (7-day TTL)
- blueprints/api/routes_audit_actions.py: 4 API endpoints
- database/migrations/056_audit_actions.sql: 3 new tables
- templates/partials/audit_ai_actions.html: Reusable UI component
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
