056b4abe52
Plan 1 (Phase A, ~3000 lines): ml-alpha library scaffold, ISV bus, mapped-pinned slots, CUDA build.rs, six perception kernels with bit-equiv tests, AdamW + BCE, Graph A capture, Phase A trainer + binary, CfC-vs-Mamba2 gate. Bite-sized 5-step TDD across 18 tasks. Plan 2 (Phase B, ~780 lines): build_state, policy_forward (CfC actor+critic), sample_action, replay buffer, multi-env rollout, GAE, advantage_normalize, fused PPO loss, EWC, Graphs B+C, seven ISV controllers, kill-switch, atomic weights swap, walk-forward CV across 6 folds. 19 tasks; tasks 2+ use compressed Step 2-5 TDD cycle pending re-detail at the Plan 1 gate boundary. Plan 3 (live, ~560 lines): IBKR adapter audit, AlphaPpoStrategy in trading_agent_service, cold-start 4-state FSM, disconnect/failure handling, observability, alpha-control IPC + fxt CLI, restart semantics, paper trading harness (5 days), $1k live deploy with manual ack gate, 5-day live window. 10 tasks. Each plan has gate-pass criteria gating the next. On failure: post- mortem + spec delta, no advance. Co-Authored-By: Claude Opus 4.7 <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.