Adriano/Multi_Swarm_Coevolutive
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
103 Commits 2 Branches 1 Tag
14f130aa5a84d016ddd04eb67eb9d608ffea1597
Commit Graph

7 Commits

Author SHA1 Message Date
Adriano 597815a106 docs(plan): Phase 2.5 task 6 spuntato + status finale tutti i task completati 
Mark task 6 (cost attribution) come done dopo commit ba4eb09. Aggiornato
header status con sweet spot empirico weight=0.30 (curva U validata su
run 004 vs control vs weight-0.50).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-12 10:43:02 +02:00
Adriano ec80af9f26 feat(phase-2.5): population_prompt_diversity metric + piano aggiornato 
Task 5 del piano Phase 2.5: nuovo modulo src/multi_swarm/metrics/diversity.py
con population_prompt_diversity(prompts) che ritorna la diversità media
1 - SequenceMatcher.ratio() su tutte le coppie distinte. 0.0 identici,
fino a ~0.9 totalmente diversi (SequenceMatcher considera spazi/lunghezza).

5 test: edge case empty/single, identici, diversi, intermediate, simmetria.

Piano aggiornato a stato "IMPLEMENTATO 2026-05-11": checkbox task 1-5
spuntate, task 6 (cost attribution per call_kind) deferito con motivazione.
Header preambolo aggiornato con trigger verificati e decisione collaterale
rollback tier C.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-11 23:52:09 +02:00
Adriano 41e26cbe5b docs(plan): Phase 2.5 mutate_prompt_llm — operator + dispatcher + integration 
Piano in tasca: NON attivare finché Phase 2 (qwen3 + temporal) non raggiunge
una delle condizioni di trigger documentate:
- plateau max fitness < 0.01 per >= 4 gen consecutive
- diversità prompt Levenshtein <= 0.15
- top genome quasi-fit (>= 0.10) con adversarial HIGH >= 2

Sei tipi di mutazione (tighten_threshold, swap_comparator, add/remove_condition,
change_timeframe, add_temporal_gate) via mutator tier B (deepseek-v4-flash),
weighted_random_mutate dispatcher con default 0.0 (opt-in), diversity guard
Levenshtein, fallback random_mutate su validation fail.

Costo stimato +$0.006/run. A/B con baseline B = phase2-qwen3-001 vs
trattamento T = phase2-qwen3-prompt-mut-001 per attribuzione effetto.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-11 22:16:30 +02:00
Adriano 30dbba4d74 docs: piano implementativo feature temporali 
7 task TDD-driven: estensione grammar, dispatcher compiler per 4
feature temporali (hour/dow/is_weekend/minute_of_hour), aggiornamento
prompt Hypothesis con few-shot, smoke run end-to-end.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-11 16:54:55 +02:00
Adriano c6cb32325e docs: design spec feature temporali Phase 2 
Aggiunge hour/dow/is_weekend/minute_of_hour come FeatureNode nella
grammatica esistente. Universal access (non passa da feature_access),
riuso di FeatureNode (no nuovo tipo AST), few-shot examples nel prompt
Hypothesis. Cinque file toccati, ~120 LOC, backward-compatible.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-11 16:52:28 +02:00
Adriano c46525805b docs(plans): Phase 1 lean spike implementation plan 
Plan TDD a 38 task per la Phase 1 del PoC Multi-Swarm Coevolutivo:
project skeleton, data layer (OHLCV via ccxt + walk-forward),
backtest engine, metrics (Sharpe + Deflated Sharpe Ratio), Cerbero
wrapper, protocollo S-expression (parser/validator/compiler),
genome + mutation/crossover, LLM client (OpenRouter Qwen + Anthropic
Sonnet), cost tracker, agents (hypothesis LLM-driven, falsification
e adversarial hand-crafted), GA (fitness/selection/loop/summary),
persistence SQLite, orchestrator end-to-end, dashboard Streamlit
(Overview/GA Convergence/Genomes), scripts CLI, smoke run, run reale,
gate decision memo + report tecnico.

Plan generato tramite skill writing-plans dopo decisione strategica B3
(spec docs/superpowers/specs/2026-05-09-decisione-strategica-design.md).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-09 18:45:09 +02:00
Adriano eb6b52ff04 Initial commit: framework concettuale + design strategico PoC 
Stato iniziale del progetto Multi_Swarm_Coevolutive:

- 00_documento_zero.md: framework concettuale (Renaissance → swarm
  co-evolutivo LLM, tre layer cognitivi, decisione strategica A/B/C).
- coevolutive_swarm_system.md: design Filone A (sistema completo,
  co-evoluzione 4 popolazioni, 12-18 mesi).
- poc_trading_swarm.md: design Filone B (PoC trading focalizzato,
  3-4 mesi, scope semplificato).
- docs/superpowers/specs/2026-05-09-decisione-strategica-design.md:
  decisione strategica B3 (PoC trading incrementale a 3 fasi con
  gate go/no-go), prodotta tramite skill brainstorming.
- .gitignore: pattern Python, editor, secrets, artefatti runtime
  (runs.db, series/, dataset binari) non versionati.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-05-09 18:19:55 +02:00