Task 6 del piano Phase 2.5 (deferito → ora completato):
- CostRecord: nuovo campo call_kind (default "hypothesis")
- CostTracker.record: accetta call_kind opzionale, summary include
by_call_kind breakdown (hypothesis vs mutation)
- Schema cost_records: aggiunta colonna call_kind TEXT NOT NULL DEFAULT
'hypothesis' + migration soft via ALTER TABLE in init_schema (silently
catched per DB pre-Task 6)
- Repository.save_cost_record: nuova arg call_kind opzionale
- mutate_prompt_llm: accetta cost_tracker/repo/run_id opzionali e logga
la call mutator con call_kind="mutation" quando sink presente
- weighted_random_mutate, next_generation: propagano cost sink
- orchestrator.run_phase1: passa cost_tracker+repo+run_id a
next_generation solo se prompt_mutation_weight > 0
Esposto fees_eat_alpha_threshold come parametro AdversarialAgent
(default 0.5 = comportamento Phase 1.5 invariato), propagato via
RunConfig.fees_eat_alpha_threshold e flag CLI
--fees-eat-alpha-threshold. Abilita ablation con soglia 0.7-0.8 senza
modificare codice — adversarial finding dominante in tutti i run
Phase 2/2.5 (50+ HIGH per run).
Tests (+4 → 186 totale):
- test_cost_tracker: default call_kind="hypothesis"; breakdown
by_call_kind con hypothesis+mutation
- test_mutation_prompt_llm: logging mutation cost con sink completo;
backward compat senza sink (no errore)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Run controllo phase2-qwen25-control-001 (seed 42, stessa pipeline Phase 2,
solo tier C switched) ha dimostrato che qwen-2.5-72b è qualitativamente
SUPERIORE a qwen3-235b sul nostro workload:
| metrica | qwen3-235b | qwen-2.5-72b | delta |
| ----------------- | ---------- | ------------ | ----- |
| max fitness | 0.0238 | 0.0311 | +30% |
| median > 0 in gen | mai | 4 gen su 10 | -- |
| entropy media | 0.199 | 0.85 | 4.3x |
| genomi fit > 0 | 5 | 10 | 2x |
| parse success | 97.7% | 100% | + |
| durata | 50 min | 28 min | 0.56x |
| LLM calls | 148 | 90 | 0.61x |
| cost USD | 0.0223 | 0.0122 | 0.55x |
Controintuitivo: 235B con context 262k era atteso superiore al 72B legacy.
In pratica qwen3-235b in tier C produce strategie meno diverse,
meno parsabili e meno ottimizzabili dal GA.
Ripristinati prezzi cost_tracker tier C a 0.40/0.40 (qwen-2.5-72b).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Tier S → google/gemini-3-flash-preview ($0.50/$3.00)
- Tier A/B → deepseek/deepseek-v4-flash ($0.14/$0.28)
- Tier C → qwen/qwen3-235b-a22b-2507 ($0.071/$0.10) — Phase 2 target
- Tier D → openai/gpt-oss-20b ($0.03/$0.14)
Aggiornato cost_tracker con prezzi reali per tier. Defaults config.py
ora rispecchiano .env corrente per evitare divergenze dead-code.
Tier S/A/B/D restano cablati ma non ancora invocati nel loop Phase 2
(solo Hypothesis tier C attivo).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
Adriano