feat(phase-2.5): Task 6 cost_kind attribution + fees_eat_alpha threshold CLI
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>
This commit is contained in:
@@ -161,6 +161,69 @@ def test_mutate_prompt_llm_falls_back_on_llm_exception() -> None:
|
||||
assert child.generation == parent.generation + 1
|
||||
|
||||
|
||||
def test_mutate_prompt_llm_logs_mutation_cost_when_sink_provided() -> None:
|
||||
"""Quando cost_tracker+repo+run_id sono forniti, la call mutator viene loggata
|
||||
con call_kind='mutation' sia in memoria sia nel repo."""
|
||||
mutated = (
|
||||
"Strategia RSI 1h evolved. Entry long quando RSI(14) < 28 e close > "
|
||||
"SMA(50). Exit short quando RSI(14) > 72."
|
||||
)
|
||||
|
||||
class _R:
|
||||
text = f"<prompt>{mutated}</prompt>"
|
||||
input_tokens = 350
|
||||
output_tokens = 140
|
||||
|
||||
class _FakeLLMCosted:
|
||||
def complete(self, genome, system, user, max_tokens=2000):
|
||||
return _R()
|
||||
|
||||
tracker_calls = []
|
||||
repo_calls = []
|
||||
|
||||
class _FakeTracker:
|
||||
def record(self, **kw):
|
||||
tracker_calls.append(kw)
|
||||
from types import SimpleNamespace
|
||||
return SimpleNamespace(cost_usd=0.0042)
|
||||
|
||||
class _FakeRepo:
|
||||
def save_cost_record(self, **kw):
|
||||
repo_calls.append(kw)
|
||||
|
||||
parent = _make_genome()
|
||||
child = mutate_prompt_llm(
|
||||
parent, _FakeLLMCosted(), random.Random(0),
|
||||
cost_tracker=_FakeTracker(), repo=_FakeRepo(), run_id="run-xyz",
|
||||
)
|
||||
assert child.system_prompt == mutated
|
||||
assert len(tracker_calls) == 1
|
||||
assert tracker_calls[0]["call_kind"] == "mutation"
|
||||
assert tracker_calls[0]["tier"] == ModelTier.B
|
||||
assert tracker_calls[0]["run_id"] == "run-xyz"
|
||||
assert tracker_calls[0]["agent_id"] == parent.id
|
||||
assert tracker_calls[0]["input_tokens"] == 350
|
||||
assert tracker_calls[0]["output_tokens"] == 140
|
||||
|
||||
assert len(repo_calls) == 1
|
||||
assert repo_calls[0]["call_kind"] == "mutation"
|
||||
assert repo_calls[0]["tier"] == "B"
|
||||
assert repo_calls[0]["cost_usd"] == 0.0042
|
||||
|
||||
|
||||
def test_mutate_prompt_llm_no_logging_without_sink() -> None:
|
||||
"""Senza cost_tracker+repo+run_id → niente logging cost (backward compat)."""
|
||||
mutated = (
|
||||
"Strategia RSI 1h evoluta. Entry long quando RSI(14) < 25 e close > "
|
||||
"SMA(60). Exit short quando RSI(14) > 75 e ATR rising."
|
||||
)
|
||||
llm = _FakeLLM(response_text=f"<prompt>{mutated}</prompt>")
|
||||
parent = _make_genome()
|
||||
# Non solleva (anche se 0 sink forniti)
|
||||
child = mutate_prompt_llm(parent, llm, random.Random(0))
|
||||
assert child.system_prompt == mutated
|
||||
|
||||
|
||||
def test_mutate_prompt_llm_picks_one_of_six_instructions() -> None:
|
||||
"""Verifica che il system message dell'LLM includa una delle 6 istruzioni."""
|
||||
mutated = (
|
||||
|
||||
Reference in New Issue
Block a user