d501d53c9d
- Delete infra/modules/cockpit/ and infra/live/production/cockpit/ (Scaleway Cockpit replaced by self-hosted Grafana+Prometheus+Loki+Tempo) - Delete CI-CD dashboards (foxhunt-ci-pipelines, gitlab-services) and grafana-dashboards-cicd ConfigMap from K8s - Delete config/grafana/ — unreferenced old dashboards (15 files) - Delete config/monitoring/grafana/ — unreferenced DQN staging dashboard - Delete crates/ml/grafana/ — unreferenced ML performance dashboard - Delete services/broker_gateway_service/grafana/ — unreferenced - Delete .claude/agents/devops/ci-cd/ — GitHub Actions agent (we use GitLab CI) - Fix grafana-values.yaml: dashboard folder GitLab → Foxhunt, hardcoded adminPassword → K8s secret (grafana-admin), gitlab-overview → node-exporter (correct name for gnetId 1860) - Remove CI-CD group from import.sh ConfigMap groups and API fallback Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
ml
10-model ML ensemble for the Foxhunt HFT system, built on Candle v0.9.1.
Models
- DQN (Rainbow) — deep Q-network with prioritized replay, dueling heads, noisy nets
- PPO — proximal policy optimization with GAE, LSTM policies, clip-higher
- TFT — temporal fusion transformer for multi-horizon forecasting
- Mamba2 — state space model for sequence prediction
- Liquid Networks — biologically inspired networks for non-stationary data
- TLOB — transformer-based limit order book analysis
- KAN — Kolmogorov-Arnold networks
- xLSTM — extended LSTM architecture
- TGGN — temporal graph neural network
- Diffusion — diffusion-based generative model
Key Modules
ensemble— model ensemble coordination and confidence aggregationhyperopt— PSO-based hyperparameter optimization with per-model adapterstrainers— unified training loops (DQN, PPO, supervised)inference—InferenceAdaptertrait for predictioncheckpoint— model checkpointing and restorationevaluation— walk-forward evaluation pipeline
Usage
use ml::dqn::DQN;
use ml::ppo::PpoTrainer;