jgrusewski 85c0200fd7 feat(trading_agent): wire ML confidence to ensemble GetEnsembleVote with fallback ...

Replace the liquidity heuristic in score_symbols with a real
GetEnsembleVote gRPC call to trading-service. Each symbol gets a
concurrent RPC; on failure the original liquidity*0.9+0.1 heuristic
is used as fallback. The ML client is lazily initialized via OnceCell
and the service URL is configurable via ML_SERVICE_URL env var.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-01 22:04:09 +01:00

..

api_gateway

feat(services): wire gRPC metrics Tower layer into all 7 gRPC services

2026-03-01 02:30:23 +01:00

backtesting_service

feat(ml): add EnsembleModelAdapter + build_production_strategy(), harden metrics server

2026-03-01 18:55:56 +01:00

broker_gateway_service

feat(services): wire gRPC metrics Tower layer into all 7 gRPC services

2026-03-01 02:30:23 +01:00

data_acquisition_service

feat(infra): enable MinIO TLS with self-signed CA for in-cluster HTTPS

2026-03-01 11:56:06 +01:00

ml_training_service

proto(ml_training): add TrainingMode enum for fine-tune support

2026-03-01 21:32:01 +01:00

tests

✅ Wave 33-3: 12 Agents Final Cleanup - Production Ready

2025-10-01 22:17:41 +02:00

trading_agent_service

feat(trading_agent): wire ML confidence to ensemble GetEnsembleVote with fallback

2026-03-01 22:04:09 +01:00

trading_service

feat(trading_service): wire retrain_model to ml_training_service via gRPC

2026-03-01 21:46:18 +01:00