99332003a4
Implements the spec at docs/superpowers/specs/2026-05-09-sp19-20-wr-first-design.md
(commit 9d9ca3e6e). 38 top-level tasks across 8 phases:
- Pre-Phase: branch + worktree + 10 ISV slot reservations
- Phase 0: 7 behavioral test stubs (failing scaffold)
- Phase 1: 3 ISV producer kernels (stats, EMAs, controllers)
- Phase 2: Reward kernel + atomic SP18 D-leg / SP12 v3 replacement
- Phase 3: Hold opp-cost dual emission + replay buffer schema
- Phase 4: n-step credit distributor + SP18 B-leg trace reset fix
- Phase 5: Aux→Q confidence gate at Bellman target
- Phase 6: 7 behavioral tests pass — L40S deployment gate
- Phase 7: L40S smoke + 50e×3s×3f full validation + close-out
Plan follows TDD discipline (write failing test → run-fail → implement →
run-pass → commit) with bite-sized 2-5 minute steps. All file paths
exact, all kernel code complete, no placeholders.
Self-review confirmed: spec coverage complete, no placeholders, type
consistency across phases (Sp20EmasInputs, ISV slot constants, aux_conf
schema field).
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.