c6c550a2be
Wire Databento Schema::Trades into OFI feature extraction so VPIN and Kyle's Lambda use real buy/sell classification instead of tick-rule proxy. Trade data pipeline: - trades_loader.rs: DbnTrade struct, load_trades_sync(), binary-search get_trades_for_bar() for O(log n) time-aligned trade windowing - ofi_calculator.rs: feed_trade() accumulates real buy/sell pressure into VPIN, Kyle's Lambda, and trade imbalance calculators - data_loading.rs: loads trades from --trades-data-dir, feeds per-bar trades to OFI calculator before calculate() - download-trades-job.yaml: K8s job for ES.FUT trades from Databento - job-template.yaml: sync trades data from MinIO + --trades-data-dir arg Offline RL (CQL/IQL): - experience_dataset.rs: bincode save/load for pre-collected datasets - iql.rs: Implicit Q-Learning (Kostrikov 2021) — expectile value network, advantage-weighted action extraction - CLI: --offline, --dataset-path, --collect-dataset flags Cleanup: - Remove FeatureVector51/MarketFeatureVector type aliases → FeatureVector - Fix stale dimension comments across 18 files (54→43/51) - Fix feature_dim default (54→43) 2758 tests pass, 0 compile errors, 0 clippy warnings. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Foxhunt
Production HFT trading system in Rust.
Architecture
The workspace contains 32 crates organized as follows:
Core Libraries (16)
| Crate | Purpose |
|---|---|
trading_engine |
Order processing, FIX 4.4, IB TWS, SIMD, RDTSC timing |
risk |
VaR, Kelly, circuit breakers, kill switches, compliance |
risk-data |
Risk data types and shared structures |
trading-data |
Trading data types |
ml |
DQN Rainbow, PPO, TFT, Mamba2, ensemble inference |
ml-data |
ML data types and feature definitions |
data |
Market data ingestion and storage |
backtesting |
Replay engine, strategy tester |
adaptive-strategy |
Ensemble execution, microstructure analysis |
common |
Shared types, resilience, error handling |
storage |
S3 and local model storage |
model_loader |
Model serialization and loading |
market-data |
Market data feed handlers |
database |
PostgreSQL access layer (SQLx) |
config |
Configuration management |
tli |
CLI commands and tooling |
Services (8)
| Service | Purpose |
|---|---|
backtesting_service |
gRPC backtesting service |
broker_gateway_service |
FIX routing, broker connectivity |
trading_service |
Core trading operations |
ml_training_service |
Model training orchestration |
data_acquisition_service |
Market data acquisition |
trading_agent_service |
Autonomous trading agents |
api_gateway |
gRPC API gateway with auth |
web-gateway |
Axum REST + WebSocket gateway |
Frontend
web-dashboard/ -- React 19 + TypeScript + Vite + TradingView charts.
Building
# Check compilation (no PostgreSQL required)
SQLX_OFFLINE=true cargo check --workspace
# Run tests for a specific crate
SQLX_OFFLINE=true cargo test -p <crate> --lib
# Clippy
SQLX_OFFLINE=true cargo clippy --workspace
ML Models
Four production model architectures on Candle v0.9.1 with CUDA:
- DQN Rainbow -- Deep Q-Network with prioritized replay, dueling heads, noisy nets
- PPO -- Proximal Policy Optimization with GAE and LSTM policies
- TFT -- Temporal Fusion Transformer for multi-horizon forecasting
- Mamba2 -- State space model for sequence prediction
Each model has a standalone trainer and a UnifiedTrainable adapter for the hyperopt pipeline.
Infrastructure
- Git: Gitea at
git.fxhnt.ai(Tailscale-only), Scaleway DEV1-S - Observability: OpenTelemetry OTLP (env
OTEL_EXPORTER_OTLP_ENDPOINT) - Database: PostgreSQL with SQLx offline mode for CI
License
Proprietary. All rights reserved.