T

Adriano 33d8e275e7 feat(llm): full multi-tier S/A/B/C/D with routing + pricing

Estende ModelTier a 5 livelli (S/A/B/C/D) con routing automatico:
S/A/B via Anthropic SDK, C/D via OpenRouter (OpenAI SDK). Aggiunge
prezzi per tier S (Opus), A (Sonnet placeholder) e D (Llama). Refactor
LLMClient.complete con dispatch tramite tier_models map e helper
_call_anthropic / _call_openrouter. Settings esposte per tutti e 5
i modelli env-configurabili.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-10 09:18:57 +02:00

docs/superpowers

docs(plans): Phase 1 lean spike implementation plan

2026-05-09 18:45:09 +02:00

scripts

feat(llm): full multi-tier S/A/B/C/D with routing + pricing

2026-05-10 09:18:57 +02:00

src/multi_swarm

feat(llm): full multi-tier S/A/B/C/D with routing + pricing

2026-05-10 09:18:57 +02:00

tests

feat(llm): full multi-tier S/A/B/C/D with routing + pricing

2026-05-10 09:18:57 +02:00

.env.example

feat(llm): full multi-tier S/A/B/C/D with routing + pricing

2026-05-10 09:18:57 +02:00

.gitignore

feat(data): OHLCV loader via ccxt with parquet cache

2026-05-09 19:01:25 +02:00

00_documento_zero.md

Initial commit: framework concettuale + design strategico PoC

2026-05-09 18:19:55 +02:00

coevolutive_swarm_system.md

Initial commit: framework concettuale + design strategico PoC

2026-05-09 18:19:55 +02:00

poc_trading_swarm.md

Initial commit: framework concettuale + design strategico PoC

2026-05-09 18:19:55 +02:00

pyproject.toml

feat(cerbero): HTTP client with bearer + bot-tag + retry

2026-05-09 19:25:00 +02:00

README.md

chore: project skeleton with uv + pyproject + deps

2026-05-09 18:49:27 +02:00

uv.lock

feat(cerbero): HTTP client with bearer + bot-tag + retry

2026-05-09 19:25:00 +02:00

README.md

Multi_Swarm_Coevolutive — Phase 1

Lean spike del PoC. Vedi docs/superpowers/specs/2026-05-09-decisione-strategica-design.md per il razionale e docs/superpowers/plans/2026-05-09-phase1-lean-spike.md per il piano implementativo.

Setup

uv sync
cp .env.example .env  # compilare token e API key
uv run pytest         # verifica che tutto installi

Cerbero locale

Phase 1 backtest legge dataset OHLCV cached, ma alcune feature di indicatore sono delegate a Cerbero. Avviare Cerbero locale prima di eseguire un run:

cd /home/adriano/Documenti/Git_XYZ/CerberoSuite/Cerbero_mcp
docker compose up -d

Comandi principali

uv run pytest                                # tutti i test
uv run pytest tests/unit -v                  # solo unit
uv run pytest tests/integration -v -m integration  # solo integration
uv run python scripts/run_phase1.py          # run completo Phase 1
uv run streamlit run src/multi_swarm/dashboard/streamlit_app.py