The Matrix Media API now requires authentication (spec v1.11+). Updated
all 5 affected bots to use downloadMedia() from BaseMatrixService which
handles authenticated downloads via /_matrix/client/v1/media/download/.
Affected bots:
- matrix-nutriphi-bot (images + audio)
- matrix-zitare-bot (audio)
- matrix-todo-bot (audio)
- matrix-ollama-bot (images)
- matrix-project-doc-bot (images + audio)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
All 19 Matrix bots now use SessionModule.forRoot({ storageMode: 'redis' })
to share user sessions across all bots via Redis. Users only need to
login once with any bot to be authenticated with all bots.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add loginWithLoginToken function to exchange Matrix SSO loginToken for credentials.
The app layout now detects the loginToken URL parameter and completes the SSO flow.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add TranscriptionModule and handleAudioMessage to enable voice message
transcription across all Matrix bots. Users can now send voice messages
which are automatically transcribed and processed as text commands.
Affected bots:
- matrix-calendar-bot
- matrix-chat-bot
- matrix-contacts-bot
- matrix-manadeck-bot
- matrix-ollama-bot
- matrix-picture-bot
- matrix-planta-bot
- matrix-presi-bot
- matrix-questions-bot
- matrix-skilltree-bot
- matrix-stats-bot
- matrix-storage-bot
- matrix-tts-bot
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- All bots now use HealthController from @manacore/matrix-bot-common
- Deleted 19 duplicate health.controller.ts files
- Added IConfigService interface for @nestjs/config v3/v4 compatibility
- matrix-stats-bot migrated to use BaseMatrixService as example
- All 19 bots pass type-check
This consolidation eliminates ~400 lines of duplicate health check code.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Migrate all LLM consumers from direct Ollama calls to centralized
mana-llm service with OpenAI-compatible API.
Migrated services:
- matrix-ollama-bot
- telegram-ollama-bot
- chat-backend
- telegram-project-doc-bot
New env vars: MANA_LLM_URL, LLM_MODEL, LLM_TIMEOUT
Replaces: OLLAMA_URL, OLLAMA_MODEL, OLLAMA_TIMEOUT
- Add keyword detection for German/English commands (hilfe, modelle, status)
- Send welcome message when users join the room
- Send bot introduction when invited to new rooms
- Add !pin command to pin help message
- Auto-pin help when joining new rooms
- Update help text with simpler command overview
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add !vision command to analyze images with vision models
- Add !vision:all command to compare all vision models
- Filter out specialized models (deepseek-r1) from !all comparison
- Add chatWithImage method to OllamaService for vision requests
- Switch Dockerfile from pnpm to npm for better compatibility
- Add .dockerignore and tsconfig.build.json
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add !all [question] command to query all models and compare responses
- Show response times for each model
- Update help text with new command and rename to Mana Chat
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Import LogLevel separately instead of LogService.LogLevel
- Change sendTyping to setTyping
- Use any type for event handler to avoid generic type issues
- Fix Buffer to Uint8Array conversion for OpenAI File API
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
