e47d067390
Updates the supervised → DQN concept audit doc to its terminal state per Plan 4 Task 7. Every Part E row + the cross-Plan-2 D.1/D.8 rows now cite the commit SHA in which they landed; xLSTM/KAN remain OUT-intentional (redundant with Mamba2+TLOB and not a bottleneck respectively); Liquid is AUDITED-LANDED (deleted from DQN per D.7's identity-at-fixed-point finding). Landed SHAs: - E.1 (TFT VSN):31e0f219a(Plan 4 Task 1B chain final) - E.2 (GRN ADOPT):f94d857eb(Plan 4 Task 2c.3c.4 backward wire-up) - E.3 (Multi-quantile IQN):005ed3a4f(fixed-τ {0.05,0.25,0.50,0.75,0.95}) - E.4 (encoder/decoder split):fbc299fa2(Rust API split, additive) - E.5 (attention-focus ISV Mode A):cfc4ccb72- E.6 (multi-task aux heads):5478e7c82(Commit A) +647f15f9d(Commit B) - D.1 (Mamba2 backward, Plan 2):345867c59- D.8 (TLOB, Plan 2):3c18ebd63Pre-commit check passes: - No row marked TBD or evaluate - No row still marked pending Per Invariant 9 (no deferred work): every entry is now IN, OUT, or AUDITED-LANDED. Part E is closed. Note: E.5 Mode B (full per-feature-group VSN attention ISV expose) was blocked on E.1 in the original spec; with E.1 now LANDED, Mode B unblocks as a follow-up but is OUT of Plan 4 scope (Mode A is sufficient for the Plan 4 retention check). 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.