mirror of
https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools.git
synced 2026-06-19 15:59:37 +00:00
503bf2e5d7
AI Layer: - llm_router.py: routes cheap/mid/high models, enforces daily budget, caches - token_counter.py: estimates tokens, truncates to budget - response_cache.py: in-memory cache with TTL per agent - prompt_registry.py: versioned prompts with stable prefix for caching - ai_budget.yaml: model costs, agent budgets, daily limits (10 SAR/day) Guardrails: - output_validator.py: blocks fake claims + prohibited actions - cost_guard.py: prevents runaway spending Observability: - trace.py: trace_id, cost, latency, steps per pipeline run Tests: ALL PASS - 30/30 evals (100%) — 9 sectors, 30 companies - 10/10 prohibited actions blocked - 4/4 allowed actions verified - 3/3 forbidden claims blocked - 3/3 message quality checks passed https://claude.ai/code/session_01W1rJthWDkasijTdXCfxVHs
35 lines
1.3 KiB
Python
35 lines
1.3 KiB
Python
"""Cost guard — prevents runaway AI spending."""
|
|
import yaml
|
|
from pathlib import Path
|
|
|
|
_config_path = Path(__file__).parent.parent / "config" / "ai_budget.yaml"
|
|
_config = {}
|
|
if _config_path.exists():
|
|
with open(_config_path) as f:
|
|
_config = yaml.safe_load(f) or {}
|
|
|
|
class CostGuard:
|
|
def __init__(self):
|
|
budget = _config.get("daily_budget", {})
|
|
self.max_cost = budget.get("max_cost_sar", 10.0)
|
|
self.max_requests = budget.get("max_requests", 500)
|
|
self.alert_pct = budget.get("alert_at_percent", 80)
|
|
self.total_cost = 0.0
|
|
self.total_requests = 0
|
|
|
|
def check(self) -> dict:
|
|
cost_pct = (self.total_cost / self.max_cost * 100) if self.max_cost > 0 else 0
|
|
req_pct = (self.total_requests / self.max_requests * 100) if self.max_requests > 0 else 0
|
|
return {
|
|
"allowed": cost_pct < 100 and req_pct < 100,
|
|
"cost_sar": round(self.total_cost, 4),
|
|
"cost_pct": round(cost_pct, 1),
|
|
"requests": self.total_requests,
|
|
"requests_pct": round(req_pct, 1),
|
|
"alert": cost_pct >= self.alert_pct or req_pct >= self.alert_pct,
|
|
}
|
|
|
|
def record(self, cost_sar: float):
|
|
self.total_cost += cost_sar
|
|
self.total_requests += 1
|