Adriano
ba4eb09a71
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>
89 lines
3.3 KiB
Python
89 lines
3.3 KiB
Python
from multi_swarm.genome.hypothesis import ModelTier
|
|
from multi_swarm.llm.cost_tracker import CostTracker, estimate_cost
|
|
|
|
|
|
def test_estimate_cost_tier_c():
|
|
cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.C)
|
|
assert cost == 0.40 + 0.40
|
|
|
|
|
|
def test_estimate_cost_tier_b():
|
|
cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.B)
|
|
assert cost == 0.14 + 0.28
|
|
|
|
|
|
def test_tracker_accumulates():
|
|
t = CostTracker()
|
|
t.record(input_tokens=10_000, output_tokens=20_000, tier=ModelTier.C, run_id="r", agent_id="a")
|
|
t.record(input_tokens=5_000, output_tokens=15_000, tier=ModelTier.C, run_id="r", agent_id="b")
|
|
summary = t.summary()
|
|
assert summary["calls"] == 2
|
|
assert summary["input_tokens"] == 15_000
|
|
assert summary["output_tokens"] == 35_000
|
|
assert summary["cost_usd"] > 0
|
|
|
|
|
|
def test_tracker_per_tier_breakdown():
|
|
t = CostTracker()
|
|
t.record(input_tokens=10_000, output_tokens=10_000, tier=ModelTier.C, run_id="r", agent_id="a")
|
|
t.record(input_tokens=10_000, output_tokens=10_000, tier=ModelTier.B, run_id="r", agent_id="b")
|
|
summary = t.summary()
|
|
assert "C" in summary["by_tier"]
|
|
assert "B" in summary["by_tier"]
|
|
|
|
|
|
def test_estimate_cost_tier_s():
|
|
cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.S)
|
|
assert cost == 0.50 + 3.00
|
|
|
|
|
|
def test_estimate_cost_tier_a():
|
|
cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.A)
|
|
assert cost == 0.14 + 0.28
|
|
|
|
|
|
def test_estimate_cost_tier_d():
|
|
cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.D)
|
|
assert cost == 0.03 + 0.14
|
|
|
|
|
|
def test_tracker_summary_contains_all_five_tiers():
|
|
t = CostTracker()
|
|
for tier in (ModelTier.S, ModelTier.A, ModelTier.B, ModelTier.C, ModelTier.D):
|
|
t.record(
|
|
input_tokens=1_000,
|
|
output_tokens=1_000,
|
|
tier=tier,
|
|
run_id="r",
|
|
agent_id=f"a-{tier.value}",
|
|
)
|
|
summary = t.summary()
|
|
for tier_letter in ("S", "A", "B", "C", "D"):
|
|
assert tier_letter in summary["by_tier"]
|
|
assert summary["by_tier"][tier_letter]["calls"] == 1
|
|
|
|
|
|
def test_tracker_default_call_kind_is_hypothesis():
|
|
t = CostTracker()
|
|
rec = t.record(input_tokens=10, output_tokens=10, tier=ModelTier.C, run_id="r", agent_id="a")
|
|
assert rec.call_kind == "hypothesis"
|
|
summary = t.summary()
|
|
assert "hypothesis" in summary["by_call_kind"]
|
|
assert summary["by_call_kind"]["hypothesis"]["calls"] == 1
|
|
assert "mutation" not in summary["by_call_kind"]
|
|
|
|
|
|
def test_tracker_by_call_kind_breakdown():
|
|
t = CostTracker()
|
|
t.record(input_tokens=100, output_tokens=200, tier=ModelTier.C, run_id="r", agent_id="a")
|
|
t.record(input_tokens=100, output_tokens=200, tier=ModelTier.C, run_id="r", agent_id="a")
|
|
t.record(
|
|
input_tokens=50, output_tokens=80, tier=ModelTier.B,
|
|
run_id="r", agent_id="parent-x", call_kind="mutation",
|
|
)
|
|
summary = t.summary()
|
|
assert summary["by_call_kind"]["hypothesis"]["calls"] == 2
|
|
assert summary["by_call_kind"]["mutation"]["calls"] == 1
|
|
assert summary["by_call_kind"]["mutation"]["input_tokens"] == 50
|
|
assert summary["by_call_kind"]["mutation"]["output_tokens"] == 80
|