mirror of
https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools.git
synced 2026-06-17 23:09:35 +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
29 lines
934 B
Python
29 lines
934 B
Python
"""In-memory response cache — avoids re-analyzing the same company."""
|
|
import hashlib
|
|
import json
|
|
import time
|
|
from typing import Optional
|
|
|
|
_cache: dict[str, dict] = {}
|
|
|
|
def _key(agent_name: str, input_data: dict) -> str:
|
|
raw = f"{agent_name}:{json.dumps(input_data, sort_keys=True, ensure_ascii=False)}"
|
|
return hashlib.sha256(raw.encode()).hexdigest()[:16]
|
|
|
|
def get_cached(agent_name: str, input_data: dict, ttl_hours: float = 24) -> Optional[dict]:
|
|
k = _key(agent_name, input_data)
|
|
entry = _cache.get(k)
|
|
if not entry:
|
|
return None
|
|
if time.time() - entry["ts"] > ttl_hours * 3600:
|
|
del _cache[k]
|
|
return None
|
|
return entry["data"]
|
|
|
|
def set_cached(agent_name: str, input_data: dict, result: dict):
|
|
k = _key(agent_name, input_data)
|
|
_cache[k] = {"data": result, "ts": time.time()}
|
|
|
|
def cache_stats() -> dict:
|
|
return {"entries": len(_cache), "keys": list(_cache.keys())[:10]}
|