mirror of
https://github.com/Memo-2023/mana-monorepo.git
synced 2026-05-14 21:01:08 +02:00
Mirror sibling to firsts: das *letzte* Mal, das du etwas getan hast — markiert oder rückwirkend erkannt. Plan: docs/plans/lasts-module.md. M1 Skelett — Dexie v51 lasts-Tabelle, Encryption-Registry, Per-Space- Welcome-Seed, Empty-State ListView. Kategorien aus firsts/types.ts nach \$lib/data/milestones/categories.ts extrahiert (Re-Exports halten firsts-API stabil). M2 CRUD + DetailView — StatusTabs (Vermutet/Bestätigt/Aufgehoben), Quick-Add mit Mode-Toggle, always-editable DetailView mit Lifecycle- Buttons (Bestätigen, Aufheben mit Inline-Note), 44 i18n-Keys × 5 Locales. M3 Inbox + Inferenz — Dexie v52 lastsCooldown (12-Monate-Cooldown, deterministische ID), Source-Registry-Pattern in inference/, places- Source mit Heuristik visitCount>=5 Span>=180d Silence>=365d. InboxView mit Akzeptieren/Verwerfen + manueller Scan. contacts/habits → M3.b sobald jeweilige Frequenz-Felder existieren. M4 AI-Tools — 5 Tools im AI_TOOL_CATALOG (create_last, confirm_last, reclaim_last, list_lasts, suggest_lasts), Webapp-Executor mit Vault- Locked-Handling. Server-Drift-Test 4/4, Schema-Test 6/6. M5 Reminders + Settings — Pivot zu In-App-DueBanner statt OS-Push (kein PWA-Push-System im Repo). Pure date-math (12 Vitest cases), Settings- Store mit 4 Toggles, DueBanner mit max-N rendering, Test-Banner-Knopf. M6 Visibility + Unlisted-Sharing — VisibilityPicker + SharedLinkControls in DetailView, buildLastBlob mit reflective-core whitelist (reclaimed Lasts gehärtet ausgeblockt), SharedLastView public-render, Share- Dispatcher kennt 'lasts'. M7 Meilensteine-Aggregator — Cross-modul firsts vereinigt mit lasts Timeline + Year-Recap. Pure aggregator (mergeMilestones, buildMilestonesRecap), 12 Vitest cases. /milestones und /milestones/recap/[year] Routes, Cross-Link in lasts/ListView. Validation: 0 errors / 0 warnings (svelte-check 7645 files), 24/24 tests, i18n-parity 39x5 aligned (+2 namespaces), i18n-keys baseline- equal, crypto 211 tables. LOCAL TIER PATCH: lasts ist 'guest' für Testing — vor Release auf 'beta' setzen (packages/shared-branding/src/mana-apps.ts). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| agent-loop-improvements-m1.md | ||
| ai-mission-key-grant.md | ||
| articles-homepage.md | ||
| articles-module.md | ||
| augur-module.md | ||
| broadcast-module.md | ||
| comic-module.md | ||
| data-export-v2.md | ||
| destructive-tools-opt-in.md | ||
| event-discovery.md | ||
| invoices-module.md | ||
| lasts-module.md | ||
| library-module.md | ||
| llm-fallback-aliases.md | ||
| mail-module-plan.md | ||
| mana-mcp-and-personas.md | ||
| mana-research-service.md | ||
| me-images-and-reference-generation.md | ||
| me-images-space-scope-migration.md | ||
| multi-agent-workbench.md | ||
| news-research-module.md | ||
| onboarding-flow.md | ||
| per-space-vs-user-global-tags.md | ||
| planner-function-calling.md | ||
| README.md | ||
| scene-scope-empty-state.md | ||
| shared-space-smoketest.md | ||
| social-relay-module.md | ||
| space-scoped-data-model.md | ||
| spaces-foundation.md | ||
| sync-field-meta-overhaul.md | ||
| team-workbench.md | ||
| tipps-module.md | ||
| unlisted-sharing.md | ||
| visibility-system.md | ||
| wardrobe-module.md | ||
| website-builder-smoketest.md | ||
| website-builder.md | ||
| workbench-cards-migration.md | ||
| workbench-seeding-cleanup.md | ||
| workbench-templates.md | ||
| writing-module.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 |