134dce896a
CI / benchmark-publish (pull_request) Has been skipped
CI / build (pull_request) Successful in 17s
CI / lint (pull_request) Successful in 18s
CI / quality (pull_request) Successful in 20s
CI / security (pull_request) Successful in 34s
CI / typecheck (pull_request) Successful in 37s
CI / integration_tests (pull_request) Successful in 3m46s
CI / unit_tests (pull_request) Successful in 8m32s
CI / docker (pull_request) Successful in 39s
CI / benchmark-regression (pull_request) Successful in 19m26s
CI / coverage (pull_request) Successful in 31m23s
CI / lint (push) Successful in 13s
CI / build (push) Successful in 15s
CI / quality (push) Successful in 16s
CI / typecheck (push) Successful in 30s
CI / benchmark-regression (push) Has been skipped
CI / security (push) Successful in 33s
CI / integration_tests (push) Successful in 3m44s
CI / unit_tests (push) Successful in 8m53s
CI / docker (push) Successful in 1m1s
CI / benchmark-publish (push) Successful in 10m35s
CI / coverage (push) Successful in 37m55s
Add token/cost tracking, budget enforcement (per-plan and per-day), provider fallback selection with capability filtering, and cost metadata for plan models. New modules: - providers/cost_table.py: CostEntry + ProviderCostTable with default pricing for OpenAI, Anthropic, Google, Groq, Together, Cohere, Mock - providers/cost_tracker.py: BudgetStatus enum, BudgetCheckResult, CostTracker with warn-at-90%/block-at-100% enforcement - providers/fallback_selector.py: FallbackSelector with capability filtering (tool_calls, streaming, vision, json_mode) and budget - domain/models/core/cost_metadata.py: CostMetadata + BudgetExhaustionEvent Modified: - config/settings.py: budget_per_plan, budget_per_day, fallback_providers - domain/models/core/plan.py: cost_metadata field + CLI dict surfacing - providers/__init__.py: public exports for new classes Testing: - 71 Behave scenarios in features/cost_controls.feature (all pass) - 6 Robot Framework integration tests (all pass) - ASV benchmarks in benchmarks/cost_controls_bench.py - nox lint, typecheck, format, docs, build, dead_code, security_scan pass Closes #324
147 lines
4.5 KiB
Python
147 lines
4.5 KiB
Python
#!/usr/bin/env python3
|
|
"""Helper script for cost controls Robot Framework integration tests."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
# Ensure local source is importable
|
|
_SRC = str(Path(__file__).resolve().parents[1] / "src")
|
|
if _SRC not in sys.path:
|
|
sys.path.insert(0, _SRC)
|
|
|
|
|
|
def test_cost_entry_creation() -> None:
|
|
"""Verify CostEntry creation and estimation."""
|
|
from cleveragents.providers.cost_table import CostEntry
|
|
|
|
entry = CostEntry(input_cost_per_token=0.00001, output_cost_per_token=0.00003)
|
|
cost = entry.estimate_cost(1000, 500)
|
|
assert cost > 0.0, f"Expected positive cost, got {cost}"
|
|
print("cost-entry-ok")
|
|
|
|
|
|
def test_cost_table_lookup() -> None:
|
|
"""Verify ProviderCostTable lookup."""
|
|
from cleveragents.providers.cost_table import ProviderCostTable
|
|
|
|
table = ProviderCostTable()
|
|
entry = table.get_cost_entry("openai", "gpt-4o")
|
|
assert entry.input_cost_per_token > 0
|
|
providers = table.list_providers()
|
|
assert "openai" in providers
|
|
print("cost-table-ok")
|
|
|
|
|
|
def test_cost_tracker_budget() -> None:
|
|
"""Verify CostTracker budget enforcement."""
|
|
from cleveragents.domain.models.core.cost_metadata import CostMetadata
|
|
from cleveragents.providers.cost_tracker import BudgetStatus, CostTracker
|
|
|
|
tracker = CostTracker(budget_per_plan=0.0001)
|
|
metadata = CostMetadata()
|
|
result = tracker.record_usage(
|
|
metadata,
|
|
provider="openai",
|
|
model="gpt-4o",
|
|
input_tokens=10000,
|
|
output_tokens=5000,
|
|
)
|
|
# With a tiny budget, usage should exceed it
|
|
assert result.status in (BudgetStatus.WARNING, BudgetStatus.EXCEEDED), (
|
|
f"Expected warning/exceeded, got {result.status}"
|
|
)
|
|
print("cost-tracker-budget-ok")
|
|
|
|
|
|
def test_fallback_selector() -> None:
|
|
"""Verify FallbackSelector with no configured providers."""
|
|
import os
|
|
|
|
from cleveragents.config.settings import Settings
|
|
from cleveragents.providers.fallback_selector import FallbackSelector
|
|
from cleveragents.providers.registry import ProviderRegistry
|
|
|
|
# Clear all API keys so no providers are configured
|
|
api_key_vars = [
|
|
"OPENAI_API_KEY",
|
|
"ANTHROPIC_API_KEY",
|
|
"GOOGLE_API_KEY",
|
|
"AZURE_OPENAI_API_KEY",
|
|
"AZURE_API_KEY",
|
|
"OPENROUTER_API_KEY",
|
|
"GEMINI_API_KEY",
|
|
"GOOGLE_GEMINI_API_KEY",
|
|
"GROQ_API_KEY",
|
|
"TOGETHER_API_KEY",
|
|
"COHERE_API_KEY",
|
|
"PERPLEXITY_API_KEY",
|
|
]
|
|
saved: dict[str, str] = {}
|
|
for var in api_key_vars:
|
|
val = os.environ.pop(var, None)
|
|
if val is not None:
|
|
saved[var] = val
|
|
try:
|
|
settings = Settings()
|
|
registry = ProviderRegistry(settings)
|
|
selector = FallbackSelector(registry=registry)
|
|
result = selector.select()
|
|
# With no API keys, no provider should be selected
|
|
assert result.provider_type is None
|
|
assert len(result.skipped) > 0
|
|
print("fallback-selector-ok")
|
|
finally:
|
|
# Restore any keys we removed
|
|
os.environ.update(saved)
|
|
|
|
|
|
def test_settings_defaults() -> None:
|
|
"""Verify Settings cost control defaults."""
|
|
from cleveragents.config.settings import Settings
|
|
|
|
settings = Settings()
|
|
assert settings.budget_per_plan is None
|
|
assert settings.budget_per_day is None
|
|
assert settings.fallback_providers == []
|
|
print("settings-defaults-ok")
|
|
|
|
|
|
def test_cost_metadata_display() -> None:
|
|
"""Verify CostMetadata display dict."""
|
|
from cleveragents.domain.models.core.cost_metadata import CostMetadata
|
|
|
|
meta = CostMetadata()
|
|
meta.record_usage(
|
|
input_tokens=100,
|
|
output_tokens=50,
|
|
cost=0.01,
|
|
provider="openai",
|
|
)
|
|
display = meta.as_display_dict()
|
|
assert "total_tokens" in display
|
|
assert "total_cost_usd" in display
|
|
print("cost-metadata-display-ok")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
if len(sys.argv) < 2:
|
|
print("Usage: helper_cost_controls.py <test-name>", file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
test_name = sys.argv[1]
|
|
tests = {
|
|
"cost-entry": test_cost_entry_creation,
|
|
"cost-table": test_cost_table_lookup,
|
|
"cost-tracker": test_cost_tracker_budget,
|
|
"fallback-selector": test_fallback_selector,
|
|
"settings-defaults": test_settings_defaults,
|
|
"cost-metadata": test_cost_metadata_display,
|
|
}
|
|
test_fn = tests.get(test_name)
|
|
if test_fn is None:
|
|
print(f"Unknown test: {test_name}", file=sys.stderr)
|
|
sys.exit(1)
|
|
test_fn()
|