Catches up all docs with the current state of the AI tool system.
services/mana-ai/CLAUDE.md:
- New v0.6 status section documenting NewsResearchClient,
pre-planning research injection, config.manaApiUrl, and the full
28-tool / 11-module inventory (17 propose + 11 auto).
apps/mana/CLAUDE.md:
- New "Tool Coverage" table in the AI Workbench section listing all
tools per module with their policy (propose vs auto).
- New "Templates" subsection documenting the two-section gallery
(agent vs workbench templates), the seed-handler registry, and
the current handlers (meditate, habits, goals).
- Architecture cross-reference updated to include §23.
docs/architecture/COMPANION_BRAIN_ARCHITECTURE.md:
- §23.2 gains a "Server-Side Research (mana-ai, ab v0.6)" subsection
explaining how NewsResearchClient mirrors the client-side research
pre-step: same endpoints, same trigger regex, but HTTP-direct from
the Docker network instead of SvelteKit-internal.
docs/plans/README.md:
- workbench-templates.md added to the roadmap table (T1 shipped).
- Multi-agent description updated to mention 28 tools + server-side
web-research.
- Architecture cross-reference includes §23.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Phase 6 — Multi-Agent observability:
- AI Workbench timeline gets a per-agent filter (dropdown with avatars)
alongside module + mission. TimelineBucket gains agentId +
agentDisplayName, projected off the bucket's first AI actor.
- Bucket header now leads with the agent's avatar + name (lookup via
the live useAgents query so renamed agents reflect instantly) and
falls back to Actor.displayName for deleted agents.
- AiProposalInbox card header replaces the generic Sparkle + "KI
schlägt vor" with an agent chip "🤖 Cashflow Watcher schlägt vor"
using the cached Actor.displayName. Ghost-agent label preserved
via the cached displayName even when the agent record is gone.
Phase 7 — Docs:
- docs/architecture/COMPANION_BRAIN_ARCHITECTURE.md §22 added:
data model, identity flow, tick gate order, Scene-Agent binding
semantics, non-goals.
- services/mana-ai/CLAUDE.md status bumped to v0.5 (Multi-Agent
Workbench) with the per-agent runner features + metrics listed.
- apps/mana/CLAUDE.md AI Workbench section rewritten to cover the
Agent primitive, per-agent policy, scene lens, and the updated
timeline header.
Multi-Agent rollout is code-complete end-to-end:
Phase 0 Plan ✓ Phase 4 Policy-per-agent ✓
Phase 1 Actor identity ✓ Phase 5 Agent UI + Scene lens ✓
Phase 2 Agent CRUD ✓ Phase 6 Observability ✓
Phase 3 Tick agent-aware ✓ Phase 7 Docs ✓
Tests: webapp svelte-check 0 errors, 0 warnings.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Foundation for Phase 2+ of the Mission Key-Grant flow: lets mana-ai
execute missions that depend on encrypted inputs (notes/tasks/events/
journal/kontext) without needing an open browser tab. Opt-in per
mission, Zero-Knowledge users excluded.
- Canonical HKDF-SHA256 derivation (scope-bound via tables + recordIds
in the HKDF info string → scope changes invalidate the grant
cryptographically, not just via a runtime check)
- Mission.grant field on the shared Mission type
- Golden snapshot + drift-guard test so webapp wrap path and mana-auth
wrap endpoint can't silently diverge
- Ideas backlog at docs/future/AI_AGENTS_IDEAS.md
- Full rollout plan at docs/plans/ai-mission-key-grant.md
- COMPANION_BRAIN_ARCHITECTURE.md §21 captures the flow + privacy
guarantees + non-goals
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- COMPANION_BRAIN_ARCHITECTURE §20: Actor model, policy layer,
pendingProposals lifecycle, ghost-UI pilot, roadmap, open follow-ups,
manual test snippet
- DATA_LAYER_AUDIT §9: new Actor columns on records
(`__lastActor`, `__fieldActors`), `pendingProposals` table, write-path
diagrams for user / AI / approval, open mana-sync Go + Postgres work
- apps/mana/CLAUDE.md: short AI Workbench section with pointers + Dexie
hook now lists actor stamping
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
eventstream was confusingly branded "Events" in the app registry,
colliding with the real events calendar module. Renamed to activity
(DE: Aktivität) since it's a live activity feed across all modules.
cycles -> period (DE: Periode) makes the menstrual-tracking module
self-describing. Tables cycles/cycleDayLogs/cycleSymptoms renamed to
periods/periodDayLogs/periodSymptoms; field cycleId -> periodId;
TimeBlockType 'cycle' -> 'period'; domain event CycleDayLogged ->
PeriodDayLogged. Generic "cycle" usages (billing, lifecycle, breath,
bicycle, import cycles) left untouched.
Constant disambiguation: prior DEFAULT_PERIOD_LENGTH (bleeding days)
renamed to DEFAULT_BLEEDING_DAYS; prior DEFAULT_CYCLE_LENGTH (28d full
cycle) is now DEFAULT_PERIOD_LENGTH.
Pre-launch, no data migration needed.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Phase 1-3 of BYOK support. Introduces a 5th LLM tier 'byok' that
routes to user-provided API keys via direct browser fetches.
shared-llm additions:
- LlmTier extended with 'byok' (rank 3, between mana-server and cloud)
- ByokBackend: LlmBackend implementation that delegates key lookup
to an app-provided resolver callback, then dispatches to the right
provider adapter
- 4 provider adapters:
- OpenAI (gpt-5, gpt-4o, o1 family)
- Anthropic (Claude Opus/Sonnet/Haiku 4.6) with CORS header
- Gemini (2.5 Pro/Flash) — REST API with different message format
- Mistral — OpenAI-compatible, reuses shared openai-compat adapter
- Pricing table for 20+ models with USD per 1M tokens
- estimateCost() + formatCost() helpers
Keys stay device-local (IndexedDB in next phase). Browser-direct
fetches mean keys never touch Mana's server.
Updates two existing tier maps (memoro DetailView, SourceBadge) to
include the new tier.
Planning doc at docs/architecture/BYOK_PLAN.md.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Updates the architecture doc with:
- Full module rollout table (29 modules with event/tool counts)
- List of 11 remaining modules with priority assessment
- Known technical debt: _activity table duplication, old trigger
system overlap, streak query performance
- Optimization opportunities: parallel DaySnapshot queries,
streak caching, Context Document expansion
- Feature gaps: no Goal editor UI, no in-app Nudge display,
no WebGPU fallback for Companion Chat
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Marks all 7 phases as completed with commit hashes, implementation
notes, and decisions made during implementation. Adds comprehensive
manual testing section covering Event Bus, Projections, Companion Chat,
Rituals, Goals, Memory, Correlations, and Pulse Rules — with code
snippets for DevTools Console and IndexedDB inspection.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Phase 5 of the Companion Brain. Introduces the Companion Chat that
ties together all previous phases into a conversational interface.
Module (modules/companion/):
- types.ts: LocalConversation + LocalMessage with tool call/result fields
- collections.ts: companionConversations + companionMessages tables
- stores/chat.svelte.ts: conversation + message CRUD
- queries.ts: reactive useConversations() + useMessages()
- engine.ts: chat orchestration — builds system prompt from Context
Document, sends to local LLM (Gemma via @mana/local-llm), handles
tool calls via JSON extraction + executeTool(), supports multi-round
tool calling (max 3 rounds)
UI:
- CompanionChat.svelte: message list, streaming output, tool result
display, keyboard submit (Enter)
- /companion route: sidebar with conversation list + chat area
Also updates the architecture plan with Phase 1-4 completion status.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Phase 1 of the Companion Brain architecture. Introduces a typed,
synchronous event bus with microtask-scheduled handlers, an append-only
event store persisted to IndexedDB (_events table, v10 schema), and
semantic domain events emitted from module stores.
Pilot modules with emit() calls:
- Todo: TaskCreated, TaskCompleted, TaskUncompleted, TaskDeleted, SubtasksUpdated
- Calendar: CalendarEventCreated, CalendarEventUpdated, CalendarEventDeleted
- Drink: DrinkLogged, DrinkEntryDeleted, DrinkEntryUndone
- Nutriphi: MealLogged, MealFromPhotoLogged, MealDeleted
- Places: PlaceCreated, PlaceDeleted, PlaceVisited, LocationLogged,
TrackingStarted, TrackingStopped
Also includes the full architecture plan at
docs/architecture/COMPANION_BRAIN_ARCHITECTURE.md.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The production domain is mana.how, not manacore.app. Updated all
references across shared-branding APP_URLS, app configs, landing pages,
docs, help content, calendar iCal UIDs, and deploy scripts.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Document the architecture decision for a modular multi-app system with:
- Split-screen functionality between apps
- Cross-app drag & drop support
- Flexible deployment configurations
- Scalability for 20+ apps
Evaluates 5 approaches and explains why Micro-Frontend Orchestrator
was chosen over monolith and other alternatives.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
