Multi_Swarm_Coevolutive

Proof-of-concept di sistema co-evolutivo multi-agente per trading quantitativo. Un genetic algorithm fa evolvere una popolazione di agenti LLM (Hypothesis swarm) che generano strategie di trading espresse in JSON strutturato; un layer Falsification deterministico le backtesta su dati storici (default BTC-PERPETUAL Deribit) via Cerbero MCP; un layer Adversarial euristico le sottopone a red-team checks; la fitness combina Deflated Sharpe Ratio (Bailey & López 2014), Sharpe normalizzato e penalizzazione di drawdown, con opzioni v2 soft-kill e combined IS/OOS per Walk-Forward Validation.

Repository

Gitea Tielogic (privato, accesso SSH):

git clone ssh://git@git.tielogic.xyz:222/Adriano/Multi_Swarm_Coevolutive.git

Layout monorepo (uv workspace)

Il repo è un workspace uv con due member packages indipendenti:

multi_swarm_coevolutive/             repo root (workspace coordinator)
├── pyproject.toml                    workspace + dev deps + ruff/mypy/pytest
├── docker-compose.yml                strategy-crypto-paper + strategy-crypto-gui
├── Dockerfile                        immagine multi-swarm-coevolutive:dev
├── uv.lock                           lock unico del workspace
├── data/, series/, state/            cache OHLCV + DB (runtime, gitignored)
├── scripts/                          CLI entrypoints (run_phase1, run_paper_trading, ...)
└── src/
    ├── multi_swarm_core/             WORKSPACE MEMBER (wheel: multi-swarm-core)
    │   ├── pyproject.toml             deps: pandas, numpy, openai, pydantic, ...
    │   ├── multi_swarm_core/          GA + genome + protocol + backtest + cerbero +
    │   │                              data + llm + agents + ga + orchestrator +
    │   │                              metrics + persistence + config
    │   ├── tests/                     unit + integration (182 test)
    │   └── docs/                      design/ + decisions/ + reports/
    │
    └── strategy_crypto/              WORKSPACE MEMBER (wheel: strategy-crypto)
        ├── pyproject.toml             deps: multi-swarm-core (workspace) + nicegui + plotly
        ├── README.md                  overview strategia + pattern per nuove strategie
        ├── strategy_crypto/
        │   ├── backend/               paper-trading (executor, portfolio, persistence, schema)
        │   ├── frontend/               NiceGUI dashboard dual-DB
        │   └── strategies/             JSON freezate (btc_*.json, eth_*.json)
        └── tests/                      smoke regression (import + json + schema)

DB separati per dominio: state/runs.db (GA core universale) + state/strategy_crypto.db (paper della strategia crypto). Pattern scala a N strategie senza naming collision.

Pattern N strategie future: aggiungere src/strategy_<asset>/ con lo stesso scheletro (backend/, frontend/, strategies/, tests/), DB dedicato state/strategy_<asset>.db, servizi Docker strategy-<asset>-paper + strategy-<asset>-gui, GUI su /strategy_<asset>_gui.

Stato del progetto

Phase 3 (paper-trading forward-test) in corso dal 13 maggio 2026 su VPS. Runner scripts/run_paper_trading.py long-running in Docker, dashboard NiceGUI su https://swarm.tielogic.xyz/strategy_crypto_gui/. Due strategie freezate:

• strategy_crypto/strategies/btc_fb63e851.json — BTC-PERPETUAL, RSI estremi + ATR vs SMA + filtro orario 9-17 (Sharpe OOS +0,26 su 7,33 anni).
• strategy_crypto/strategies/eth_facd6af85d5d.json — ETH-PERPETUAL, regime-based (Sharpe OOS +0,19 su 6,75 anni).

Phase 1 → 2.7 chiuse (30 run GA, $3.74 cumulato LLM).

• Stato progetto e roadmap (14 maggio 2026) — riepilogo fasi, decisioni, caveat, roadmap.
• Decision log: src/multi_swarm_core/docs/decisions/ (gate Phase 1, scelta nemotron).
• Design docs concettuali: src/multi_swarm_core/docs/design/.

Stack: Python 3.13, uv workspace, hatchling, pytest+pytest-mock+responses, openai SDK (verso OpenRouter), requests+tenacity, pandas+numpy+scipy, sqlmodel+sqlite, nicegui+plotly, yfinance.

Setup

uv sync                           # installa entrambi i workspace member come editable
cp .env.example .env              # compila CERBERO_*_TOKEN e OPENROUTER_API_KEY
uv run pytest                     # 186 test attesi (182 core + 4 smoke strategy_crypto)

Variabili .env richieste

# Cerbero MCP (locale o VPS https://cerbero-mcp.tielogic.xyz)
CERBERO_BASE_URL=http://localhost:9001
CERBERO_TESTNET_TOKEN=<testnet bearer>
CERBERO_MAINNET_TOKEN=<mainnet bearer>   # serve per dati storici reali
CERBERO_BOT_TAG=swarm-poc-phase1

# LLM provider (unico endpoint via OpenRouter)
OPENROUTER_API_KEY=<sk-or-v1-...>

# DB paths (split per dominio: core GA vs paper della strategia)
GA_DB_PATH=./state/runs.db
STRATEGY_CRYPTO_DB_PATH=./state/strategy_crypto.db

# Deploy Docker
DOMAIN_NAME=tielogic.xyz
SWARM_DASHBOARD_PORT=8080
DASHBOARD_ROOT_PATH=/strategy_crypto_gui   # subpath traefik per la dashboard

Backcompat: DB_PATH legacy continua a funzionare come alias di GA_DB_PATH.

Comandi principali

# Quality gates
uv run pytest                                       # tutti i test
uv run pytest src/multi_swarm_core/tests/unit -v    # solo unit core
uv run pytest src/strategy_crypto/tests/ -v         # smoke strategy_crypto
uv run ruff check src/ scripts/
uv run mypy src/ scripts/

# Smoke run (MockLLM + OHLCV sintetico, no API calls)
uv run python scripts/smoke_run.py

# Run reale Phase 1/2 (Cerbero + OpenRouter, ~$0.07 per run K=20 10gen)
uv run python scripts/run_phase1.py \
  --name run-XXX \
  --exchange deribit --symbol BTC-PERPETUAL --timeframe 1h \
  --start 2024-01-01T00:00:00+00:00 \
  --end 2026-01-01T00:00:00+00:00 \
  --population-size 20 --n-generations 10 \
  --prompt-mutation-weight 0.30 --fitness-v2

# Backtest standalone di una strategia JSON
uv run python scripts/backtest_strategy.py \
  --strategy src/strategy_crypto/strategy_crypto/strategies/btc_fb63e851.json \
  --start 2018-09-01 --end 2026-01-01

# Paper-trading forward-test (Phase 3)
uv run python scripts/run_paper_trading.py \
  --name phase3-papertrade-XXX \
  --initial-capital 1000 --poll-seconds 300
# Default --strategies-dir: importlib.resources del package strategy_crypto

# Dashboard NiceGUI locale
uv run python -m strategy_crypto.frontend.nicegui_app
# → http://localhost:8080 (env SWARM_DASHBOARD_PORT)

Dashboard

NiceGUI dashboard (dark palette) — dual-DB reader (GA + paper):

• Overview (/): lista runs GA, costo cumulato, metriche aggregate evaluations.
• GA Convergence (/convergence): fitness median/max/p90 per generazione + entropy.
• Genomes (/genomes): top-K ordinati per fitness, ispezione system_prompt + JSON strategy.
• Paper (/paper): forward-test live con equity curve, posizioni aperte, trade list, tick log.

In produzione su https://swarm.tielogic.xyz/strategy_crypto_gui/ (subpath gestito via DASHBOARD_ROOT_PATH + Traefik PathPrefix). La root del dominio resta libera per future GUI di altre strategie.

Deploy

docker-compose.yml definisce due servizi su immagine multi-swarm-coevolutive:dev:

• strategy-crypto-paper — runner scripts/run_paper_trading.py long-running.
• strategy-crypto-gui — NiceGUI dashboard dietro Traefik su https://swarm.${DOMAIN_NAME}/strategy_crypto_gui/.

Persistenza via bind mount: ./data/, ./series/, ./state/. Le strategie JSON sono bind-mounted in read-only dal package: ./src/strategy_crypto/strategy_crypto/strategies/.

docker compose up -d --build
docker compose logs -f strategy-crypto-paper
docker compose ps

Note operative:

• Le bind-mount dir devono essere chown 1000:1000 (uid utente app nel container).
• Override del command paper via env (PAPER_RUN_NAME, PAPER_INITIAL_CAPITAL, ecc.).
• SWARM_DASHBOARD_PORT controlla la porta interna del container (Traefik fa il TLS).

Sviluppo

Conventional commits con prefix feat: fix: chore: docs: refactor: test:. Body italiano. Footer Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> su ogni commit collaborativo.

Branch attuale: main. Workspace single-repo, monorepo unificato dal 15 maggio 2026 (split temporaneo monorepo→figlio invertito, vedi tag v0.1.0-pre-split come bookmark).