mirror of
https://github.com/Memo-2023/mana-monorepo.git
synced 2026-05-15 01:01:09 +02:00
Phase 1: Manual iCal feeds + Discovery tab - 5 new DB tables in event_discovery schema (regions, interests, sources, discovered_events, user_actions) - iCal parser (node-ical) with deduplication (SHA-256 hash) - Crawl scheduler (15-min interval, auto-deactivate after 5 errors) - CRUD routes for regions, interests, sources + paginated feed endpoint - Frontend: "Meine Events" / "Entdecken" tab navigation in ListView - Discovery setup wizard (regions via mana-geocoding + interests) - DiscoveredEventCard with save/dismiss, SourceManager for iCal feeds - "Merken" creates a local socialEvent from discovered event Phase 2: Auto source discovery + LLM extraction + relevance scoring - Source discoverer: web search via mana-research to auto-find iCal feeds and venue websites for a region - Website extractor: crawl via mana-research /extract, then LLM-based event extraction via mana-llm with structured JSON output - Flexible date parsing (ISO, DD.MM.YYYY), markdown fence stripping - Relevance scorer: category match, freetext match, haversine distance, time proximity, weekend bonus (0-100 clamped) - Routes: POST regions/:id/discover-sources, PUT/DELETE sources/:id/activate|reject - Frontend: "Automatisch finden" button, suggested vs active sources UI 107 tests (all passing), no regressions. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| ai-mission-key-grant.md | ||
| event-discovery.md | ||
| library-module.md | ||
| mail-module-plan.md | ||
| mana-research-service.md | ||
| multi-agent-workbench.md | ||
| news-research-module.md | ||
| README.md | ||
| team-workbench.md | ||
| workbench-templates.md | ||
Plans
Design + rollout plans, grouped by topic. Plans are long-form docs with baked-in decisions, phasing, open questions, and (when shipped) a history section with commit refs.
AI / Workbench roadmap
The Mana AI Workbench has evolved in three successive planned waves — each one laying foundations the next one relies on:
User hat einen Companion (v0 — shipped before these docs)
│
▼
AI Missions + Proposals + Policy + Revert
│
▼
Mission Key-Grants ← ai-mission-key-grant.md ✅
(encrypted inputs decryptable by the server runner)
│
▼
Multi-Agent Workbench ← multi-agent-workbench.md ✅
(named agents, per-agent policy/memory/budget,
identity-aware Actor, scene→agent lens)
│
▼
Team Workbench ← team-workbench.md 📝 (not started)
(multi-user + shared AI context,
admin lens on team members)
| Plan | Status | Scope |
|---|---|---|
ai-mission-key-grant.md |
✅ Shipped | Per-mission RSA-wrapped key grant so mana-ai can decrypt allowlisted encrypted records when user opts in. |
multi-agent-workbench.md |
✅ Shipped | Identity-aware Actor + named AI agents owning missions + per-agent policy + scene lens. 28 tools across 11 modules including server-side web-research. |
workbench-templates.md |
✅ T1 Shipped | Generalised templates: 3 agent-templates + 3 non-AI workbench starter-kits. Seed-handler registry for per-module data seeding. |
team-workbench.md |
📝 Forward-looking | TeamSpace with membership, team-encrypted records, admin lens on team members. Reuses Actor.principalId + key-wrapping patterns from the two above. |
Cross-references:
- Architecture narrative:
docs/architecture/COMPANION_BRAIN_ARCHITECTURE.md§20 (AI Workbench base), §21 (Mission Grants), §22 (Multi-Agent), §23 (Reasoning Loop + Research + Debug) - Non-plan ideas backlog:
docs/future/AI_AGENTS_IDEAS.md - Service-internal notes:
services/mana-ai/CLAUDE.md - Webapp-internal notes:
apps/mana/CLAUDE.md→ "AI Workbench" section
Other plans
| Plan | Topic |
|---|---|
mail-module-plan.md |
Mail module — IMAP/SMTP integration |
news-research-module.md |
News + research pipeline |