build-app.sh now checks available RAM before builds and only stops
monitoring containers when free memory is below 3 GB threshold.
New memory-baseline.sh script measures per-container and per-category
RAM usage for capacity planning.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Deactivate Ollama, FLUX.2, and Telegram Bot LaunchAgents on Mac Mini
- Remove extra_hosts from mana-llm (no longer needs host.docker.internal)
- Update health-check.sh to monitor GPU server services instead of local
- Update status.sh to show GPU server status instead of native services
- Rewrite MAC_MINI_SERVER.md: remove ~400 lines of Ollama/FLUX/Bot docs,
add GPU server architecture diagram and deactivation notes
- Update CAPACITY_PLANNING.md with post-offload numbers (~80-150 peak users)
Mac Mini is now a pure hosting server (Web, API, DB, Sync).
All AI workloads run on GPU server (RTX 3090) via LAN.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Document sveltekit-base/nestjs-base Docker images and the build-app.sh
script in both CLAUDE.md and MAC_MINI_SERVER.md.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add mediaSrc option to shared security headers and configure mukke
to allow audio loading from minio.mana.how (S3 presigned URLs).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Update runner setup guide to reflect completed installation status
- Simplify docs: runner is active, show maintenance commands instead of install steps
- Fix SSH config in server docs (user mana, local IP, add CI/CD section)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add Docker Desktop relocation to external SSD via symlink
- Document ~80GB freed on internal SSD
- Add Matrix Bots section with all 10 bots and ports
- Include health check, logs, and management commands
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add MODEL_METADATA config for Ollama models with descriptions and modality
- Update default model to gemma3:4b
- Show model descriptions in ModelSelector and ComparisonSelector
- Add docs/OLLAMA_MODELS.md with instructions for adding new models
- Document external 4TB SSD setup in MAC_MINI_SERVER.md
- Add gemma3:12b, gemma3:27b, qwen2.5-coder:14b to model registry
Move queue name constants to separate file (queue-names.ts) to avoid
circular dependency between queue.module.ts and processor files.
The @Processor decorator evaluates at module load time, and importing
constants from queue.module.ts created a circular dependency that
resulted in undefined queue names.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- NestJS-based Telegram bot with nestjs-telegraf
- Ollama service for API communication with Gemma 3 4B
- Commands: /start, /help, /models, /model, /mode, /clear, /status
- Multiple modes: default, classify, summarize, translate, code
- Chat history with context (last 10 messages)
- User access control via TELEGRAM_ALLOWED_USERS
- Health endpoint for monitoring
- Updated MAC_MINI_SERVER.md with Ollama documentation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
