Router (main.py):
- When DSML detected in 2nd LLM response after tool execution,
make a 3rd LLM call with explicit synthesis prompt instead of
returning raw tool results to the user
- Falls back to format_tool_calls_for_response only if 3rd call fails
Router (tool_manager.py):
- Added _strip_think_tags() helper for <think>...</think> removal
from DeepSeek reasoning artifacts
Gateway (http_api.py):
- Strip <think>...</think> tags before sending to Telegram
- Strip DSML/XML-like markup (function_calls, invoke, parameter tags)
- Ensure empty text after stripping gets "..." fallback
Deployed to NODE1 and verified services running.
Co-authored-by: Cursor <cursoragent@cursor.com>
Brand commands (~290 lines):
- Code was trapped inside `if reply_to_message:` block (unreachable)
- Moved to feature flag: ENABLE_BRAND_COMMANDS=true to activate
- Zero re-indentation: 8sp code naturally fits as feature flag body
- Helper functions (_brand_*, _artifact_*) unchanged
Memory LLM Summary:
- Replace placeholder with real DeepSeek API integration
- Structured output: summary, goals, decisions, open_questions, next_steps, key_facts
- Graceful fallback if API key not set or call fails
- Added MEMORY_DEEPSEEK_API_KEY config
- Ukrainian output language
Deployed and verified on NODE1.
Co-authored-by: Cursor <cursoragent@cursor.com>
1. thread_has_agent_participation (SOWA Priority 11):
- New function has_agent_chat_participation() in behavior_policy.py
- Checks if agent responded to ANY user in this chat within 30min
- When active + user asks question/imperative → agent responds
- Different from per-user conversation_context (Priority 12)
- Wired into both detect_explicit_request() and analyze_message()
2. ACK reply_to_message_id:
- When SOWA sends ACK ("NUTRA тут"), it now replies to the user's
message instead of sending a standalone message
- Better UX: visually linked to what the user wrote
- Uses allow_sending_without_reply=True for safety
Known issue (not fixed - too risky):
- Lines 1368-1639 in http_api.py are dead code (brand commands /бренд)
at incorrect indentation level (8 spaces, inside unreachable block)
- These commands never worked on NODE1, fixing 260 lines of indentation
carries regression risk — deferred to separate cleanup PR
Co-authored-by: Cursor <cursoragent@cursor.com>
When a user replies to an agent's message in Telegram groups,
it is now treated as a direct mention (SOWA FULL response).
Implementation:
- Detect reply_to_message.from.is_bot in Gateway webhook handler
- Verify bot_id matches this agent's token (multi-agent safe)
- Pass is_reply_to_agent=True to detect_explicit_request() and
analyze_message() (SOWA v2.2)
- Add is_reply_to_agent to Router metadata for analytics
SOWA already had Priority 3 logic for reply_to_agent → FULL,
it was just never wired up (had TODO placeholders with False).
Edge cases handled:
- Only triggers when reply is to THIS agent's bot (not other bots)
- Reply to forwarded messages: won't trigger (from.is_bot would be
the original sender, not the bot)
- Works alongside existing DM, mention, and training group rules
Co-authored-by: Cursor <cursoragent@cursor.com>
SOWA fixes:
- Add Russian variants for all agents (сэнпай, хелион, друид, etc.)
- Add missing sofiia agent to AGENT_NAME_VARIANTS
- Add /senpai, /sofiia command prefixes
Vision denial fix (all 13 agents):
- Add explicit rule: "Never say you can't see/analyze images"
- Agents have Vision API via Swapper (qwen3-vl-8b)
- When vision model describes a photo, the follow-up text model (DeepSeek)
must not deny having seen it
Root cause: NUTRA correctly analyzed a photo via vision model, but when
asked a follow-up question, DeepSeek (text model) responded "I cannot
see images" because the system prompt lacked the denial prevention rule.
Co-authored-by: Cursor <cursoragent@cursor.com>
Complete snapshot of /opt/microdao-daarion/ from NODE1 (144.76.224.179).
This represents the actual running production code that has diverged
significantly from the previous main branch.
Key changes from old main:
- Gateway (http_api.py): expanded from ~40KB to 164KB with full agent support
- Router: new /v1/agents/{id}/infer endpoint with vision + DeepSeek routing
- Behavior Policy: SOWA v2.2 (3-level: FULL/ACK/SILENT)
- Agent Registry: config/agent_registry.yml as single source of truth
- 13 agents configured (was 3)
- Memory service integration
- CrewAI teams and roles
Excluded from snapshot: venv/, .env, data/, backups, .tgz archives
Co-authored-by: Cursor <cursoragent@cursor.com>
NODA1 agents now:
- Don't respond to broadcasts/posters/announcements without direct mention
- Don't respond to media (photo/link) without explicit question
- Keep responses short (1-2 sentences by default)
- No emoji, no "ready to help", no self-promotion
Added:
- behavior_policy.py: detect_directed_to_agent(), detect_broadcast_intent(), should_respond()
- behavior_policy_v1.txt: unified policy block for all prompts
- Pre-LLM check in http_api.py: skip Router call if should_respond=False
- NO_OUTPUT handling: don't send to Telegram if LLM returns empty
- Updated all 9 agent prompts with Behavior Policy v1
- Unit and E2E tests for 5 acceptance cases
- Added TRAINING_GROUP_IDS constant for Agent Preschool group
- Gateway now adds "[РЕЖИМ НАВЧАННЯ]" prefix for training groups
- Agents will respond to all messages in training groups
Co-authored-by: Cursor <cursoragent@cursor.com>
All agents now respond to all messages in the training group
"Agent Preschool Daarion.city" without requiring mentions.
Updated prompts: helion, daarwizz, greenfood, nutra, agromatrix, druid
Co-authored-by: Cursor <cursoragent@cursor.com>
Helion now only responds in groups when:
- Mentioned by name/username
- Direct question about Energy Union
- Previously was responding to all messages in groups
Co-authored-by: Cursor <cursoragent@cursor.com>
- matrix-gateway: POST /internal/matrix/presence/online endpoint
- usePresenceHeartbeat hook with activity tracking
- Auto away after 5 min inactivity
- Offline on page close/visibility change
- Integrated in MatrixChatRoom component
- Commented out early 'if not update.message' validation at line 723
- This was preventing photo and voice messages from being processed
- process_photo() and process_voice() functions are already implemented
- Now photo/voice updates can reach multimodal handlers before text validation
- Fixes issue where bots showed placeholder messages instead of processing media
- Telegram API returns 400 Bad Request with invalid Markdown characters
- Switched to plain text mode (no parse_mode) to prevent errors
- Photo and voice processing now work correctly
- Fixes issue where vision-8b responses couldn't be sent to users
- Add auto_complex logic: if needs_complex_reasoning, set metadata["provider"] = "cloud_deepseek"
- Add context caching in MemoryClient with 5s TTL
- Add GREENFOOD agent configuration
- This enables automatic routing of complex queries to DeepSeek via explicit_provider_override rule
- Створено AgentConfig для уніфікації конфігурації агентів
- Додано універсальні функції: process_photo(), process_document(), process_voice()
- Створено handle_telegram_webhook() для будь-якого агента
- Рефакторинг telegram_webhook() та helion_telegram_webhook()
- Оновлено process_voice() для використання STT Service
- Додано реєстр агентів AGENT_REGISTRY
- Оновлено health endpoint для показу всіх агентів
- Додано інструкції для додавання нових агентів
- Modified send_telegram_message() to accept bot_token parameter
- DAARWIZZ webhook now uses DAARWIZZ_TELEGRAM_BOT_TOKEN
- Helion webhook now uses HELION_TELEGRAM_BOT_TOKEN
- Fixes issue where DAARWIZZ messages were sent via Helion bot
- Add Helion system prompt with 9 user modes
- Add /helion/telegram/webhook endpoint
- Add Helion configuration to docker-compose.yml
- Add HELION-QUICKSTART.md documentation
- Update .env.example with Helion variables
Helion provides technical support for EcoMiner/BioMiner, tokenomics (ENERGY, 1T, kWt), and DAO governance with RAG verification and 4-level compliance.
- Add STT service with Whisper support (faster-whisper, whisper CLI, OpenAI API)
- Update Gateway to handle Telegram voice/audio/video_note messages
- Add STT service to docker-compose.yml
- Gateway now converts voice → text → DAGI Router → text response
- Fixed Gateway to extract response from data.text field
- GPU working: RTX 4000 Ada, response time 7-10s (was 30-40s)
- DAARWIZZ now responds correctly with full personality
- Started Memory Service structure
- Fixed Gateway: 'prompt' → 'message' field name
- Increased LLM provider timeout from 30s to 60s
- Added OLLAMA-OPTIMIZATION.md with performance tips
- DAARWIZZ now responds (slowly but works)
- Updated gateway-bot/daarwizz_prompt.txt with v3 system prompt
- Created docs/daarwizz/PROFILE.md with complete agent profile
- Defines DAARWIZZ as digital mayor and MoE coordinator
- Specifies communication style, roles, security policies
- Integration with full DAGI Stack (Router, DevTools, CrewAI, RBAC)
- Knowledge base references to official DAARION.city docs
DAARWIZZ - Official AI agent for DAARION.city ecosystem
Changes:
- gateway-bot/daarwizz_prompt.txt: System prompt defining DAARWIZZ personality
- gateway-bot/http_api.py: Load and inject DAARWIZZ context into Router requests
- gateway-bot/Dockerfile: Copy DAARWIZZ prompt file to container
- providers/llm_provider.py: Support context.system_prompt from Gateway
Features:
- Telegram webhook sends agent='daarwizz' to Router
- System prompt loaded from file (customizable)
- LLM receives full DAARWIZZ context + RBAC
- Discord support included
Usage:
- User messages DAARWIZZ in Telegram
- Gateway enriches with system prompt + RBAC
- Router routes to LLM with full context
- DAARWIZZ responds with DAO-aware answers
Next: Set TELEGRAM_BOT_TOKEN and test first dialog
