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>
