81e9970d4c
Renames all *_h6000 references to *_h1000 (new longest horizon): - AlphaTrainSummary struct fields: best_auc_h6000_* → best_auc_h1000_*, best_h6000_ckpt_path → best_h1000_ckpt_path - State vars: best_auc_h6000*, h6000_no_improvement → h1000 equivalents - Checkpoint filename: trunk_best_h6000.bin → trunk_best_h1000.bin - CLI early-stop metric: "auc_h6000" → "auc_h1000" - Tracing log fields: w_h30..w_h6000 → w_h10/w_h100/w_h1000 - 4 hardcoded [seq.labels[0..4][k]] literals → std::array::from_fn - MultiHorizonLoaderConfig.horizons + AlphaTrainSummary.horizons: literal [30,100,300,1000,6000] → HORIZONS constant - Doc comments: "5 horizons", "h6000-snapshot" → "N_HORIZONS", "longest-horizon" KNOWN FOLLOW-UP (Task 7): 5 sweep YAMLs reference trunk_best_h6000.bin filename — must update atomically when applying workflow template changes. KNOWN FOLLOW-UP (Task 8): crates/ml-alpha/src/gpu_log.rs:176-192 still decodes 5-horizon JSON fields (raw_h30..h6000, ema_h30..h6000, etc.). cargo check --example alpha_train: PASS. Co-Authored-By: Claude Opus 4.7 (1M context) <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.