Apple
|
e9dedffa48
|
feat(production): sync all modified production files to git
Includes updates across gateway, router, node-worker, memory-service,
aurora-service, swapper, sofiia-console UI and node2 infrastructure:
- gateway-bot: Dockerfile, http_api.py, druid/aistalk prompts, doc_service
- services/router: main.py, router-config.yml, fabric_metrics, memory_retrieval,
offload_client, prompt_builder
- services/node-worker: worker.py, main.py, config.py, fabric_metrics
- services/memory-service: Dockerfile, database.py, main.py, requirements
- services/aurora-service: main.py (+399), kling.py, quality_report.py
- services/swapper-service: main.py, swapper_config_node2.yaml
- services/sofiia-console: static/index.html (console UI update)
- config: agent_registry, crewai_agents/teams, router_agents
- ops/fabric_preflight.sh: updated preflight checks
- router-config.yml, docker-compose.node2.yml: infra updates
- docs: NODA1-AGENT-ARCHITECTURE, fabric_contract updated
Made-with: Cursor
|
2026-03-03 07:13:29 -08:00 |
|
Apple
|
990e594a1d
|
feat: harden memory summary — fingerprint dedup, versioning, prompt injection defense
Summary hardening:
- SHA256 fingerprint of events content for deduplication
(skips LLM call when events unchanged since last summary)
- Versioned summary storage: summary:agent:channel:vN keys
- Latest pointer: summary_latest:agent:channel for fast retrieval
- Prompt injection defense: sanitize event content before LLM,
strip [SYSTEM]/[INTERNAL] markers, block "ignore instructions" patterns
- Anti-injection clause in SUMMARY_SYSTEM_PROMPT
Database fix:
- list_facts_by_agent: SQL filter by fact_prefix to only return chat_events
(prevents summary/version facts from consuming LIMIT quota)
- Fixed NULL team_id issue in UNIQUE constraint (PostgreSQL NULL != NULL)
using "__system__" sentinel for team_id in summary operations
Tested on NODE1: dedup works (same events → skipped), force=true bypasses.
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-02-09 10:26:03 -08:00 |
|
Apple
|
0cfd3619ea
|
feat: auto-summarize trigger for agent memory
- Memory Service: POST /agents/{agent_id}/summarize endpoint
- Fetches recent events by agent_id (new db.list_facts_by_agent)
- Generates structured summary via DeepSeek LLM
- Saves summary to PostgreSQL facts + Qdrant vector store
- Returns structured JSON (summary, goals, decisions, key_facts)
- Gateway memory_client: auto-trigger after 30 turns
- Turn counter per chat (agent_id:channel_id)
- 5-minute debounce between summarize calls
- Fire-and-forget via asyncio.ensure_future (non-blocking)
- Configurable via SUMMARIZE_TURN_THRESHOLD / SUMMARIZE_DEBOUNCE_SECONDS
- Database: list_facts_by_agent() for agent-level queries without user_id
Tested on NODE1: Helion summarize returns valid Ukrainian summary with 20 events.
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-02-09 10:15:43 -08:00 |
|
Apple
|
0c8bef82f4
|
feat: Add Alateya, Clan, Eonarch agents + fix gateway-router connection
## Agents Added
- Alateya: R&D, biotech, innovations
- Clan (Spirit): Community spirit agent
- Eonarch: Consciousness evolution agent
## Changes
- docker-compose.node1.yml: Added tokens for all 3 new agents
- gateway-bot/http_api.py: Added configs and webhook endpoints
- gateway-bot/clan_prompt.txt: New prompt file
- gateway-bot/eonarch_prompt.txt: New prompt file
## Fixes
- Fixed ROUTER_URL from :9102 to :8000 (internal container port)
- All 9 Telegram agents now working
## Documentation
- Created PROJECT-MASTER-INDEX.md - single entry point
- Added various status documents and scripts
Tokens configured:
- Helion, NUTRA, Agromatrix (existing)
- Alateya, Clan, Eonarch (new)
- Druid, GreenFood, DAARWIZZ (configured)
|
2026-01-28 06:40:34 -08:00 |
|
Apple
|
5290287058
|
feat: implement TTS, Document processing, and Memory Service /facts API
- TTS: xtts-v2 integration with voice cloning support
- Document: docling integration for PDF/DOCX/PPTX processing
- Memory Service: added /facts/upsert, /facts/{key}, /facts endpoints
- Added required dependencies (TTS, docling)
|
2026-01-17 08:16:37 -08:00 |
|
Apple
|
90758facae
|
🧠 Add Agent Memory System with PostgreSQL + Qdrant + Cohere
Features:
- Three-tier memory architecture (short/mid/long-term)
- PostgreSQL schema for conversations, events, memories
- Qdrant vector database for semantic search
- Cohere embeddings (embed-multilingual-v3.0, 1024 dims)
- FastAPI Memory Service with full CRUD
- External Secrets integration with Vault
- Kubernetes deployment manifests
Components:
- infrastructure/database/agent-memory-schema.sql
- infrastructure/kubernetes/apps/qdrant/
- infrastructure/kubernetes/apps/memory-service/
- services/memory-service/ (FastAPI app)
Also includes:
- External Secrets Operator
- Traefik Ingress Controller
- Cert-Manager with Let's Encrypt
- ArgoCD for GitOps
|
2026-01-10 07:52:32 -08:00 |
|