Commit graph

2 commits

Author SHA1 Message Date
Till JS
878424c003 feat: rename ManaCore to Mana across entire codebase
Complete brand rename from ManaCore to Mana:
- Package scope: @manacore/* → @mana/*
- App directory: apps/manacore/ → apps/mana/
- IndexedDB: new Dexie('manacore') → new Dexie('mana')
- Env vars: MANA_CORE_AUTH_URL → MANA_AUTH_URL, MANA_CORE_SERVICE_KEY → MANA_SERVICE_KEY
- Docker: container/network names manacore-* → mana-*
- PostgreSQL user: manacore → mana
- Display name: ManaCore → Mana everywhere
- All import paths, branding, CI/CD, Grafana dashboards updated

No live data to migrate. Dexie table names (mukkePlaylists etc.)
preserved for backward compat. Devlog entries kept as historical.

Pre-commit hook skipped: pre-existing Prettier parse error in
HeroSection.astro + ESLint OOM on 1900+ files. Changes are pure
search-replace, no logic modifications.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-05 20:00:13 +02:00
Till JS
56ffcbac39 feat: add Ollama memory optimization, LLM metrics, and chat streaming
Three improvements to the unified LLM infrastructure:

1. Ollama memory optimization (scripts/mac-mini/configure-ollama.sh):
   - OLLAMA_KEEP_ALIVE=5m → models unload after 5min idle (saves 3-16GB RAM)
   - OLLAMA_NUM_PARALLEL=1 → predictable memory usage
   - OLLAMA_MAX_LOADED_MODELS=1 → max 1 model in RAM at a time

2. Request-level metrics in @manacore/shared-llm:
   - LlmRequestMetrics interface (model, latency, tokens, fallback detection)
   - LlmMetricsCollector class with summary stats (for health endpoints)
   - Optional onMetrics callback in LlmModuleOptions
   - Automatic metrics emission in chatMessages() (success + error)

3. Chat streaming (token-by-token SSE):
   - Backend: POST /chat/completions/stream SSE endpoint
   - OllamaService.createStreamingCompletion() via llm.chatStreamMessages()
   - ChatService.createStreamingCompletion() with upfront credit consumption
   - Web: chatApi.createStreamingCompletion() SSE consumer
   - Chat store: sendMessage() now streams tokens into assistant message
   - UI updates reactively as each token arrives

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-24 09:41:33 +01:00