Files
aiagent/test/test_token_budget.py

89 lines
3.9 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# -*- coding: utf-8 -*-
"""Token 预算管理 - 端到端测试"""
import sys, os, io, json, requests
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8", errors="replace")
BASE = "http://localhost:8038/api/v1"
def login():
r = requests.post(f"{BASE}/auth/login", data={"username": "admin", "password": "123456"})
r.raise_for_status()
return r.json()["access_token"]
def test_token_budget():
token = login()
headers = {"Authorization": f"Bearer {token}", "Content-Type": "application/json"}
print("=== Token 预算管理测试 ===\n")
# Test 1: Chat with default settings (token budget enabled)
print("1. 对话(Token 预算 开启)…")
r1 = requests.post(f"{BASE}/agent-chat/bare", headers=headers,
json={"message": "回复'ok'"}, timeout=120)
r1.raise_for_status()
d1 = r1.json()
tu = d1.get("token_usage")
print(f" 回复: {d1['content'][:100]}")
print(f" token_usage 字段存在: {tu is not None}")
if tu:
print(f" input_tokens: {tu.get('input_tokens', 'N/A')}")
print(f" cumulative_total: {tu.get('cumulative_total', 'N/A')}")
print(f" input_usage_pct: {tu.get('input_usage_pct', 'N/A')}")
print(f" is_warning: {tu.get('is_warning')}, is_critical: {tu.get('is_critical')}")
print(f" context_window: {tu.get('context_window', 'N/A')}")
ok1 = tu is not None and "input_tokens" in tu
print(f" {'✓ 通过' if ok1 else '✗ 失败'}\n")
# Test 2: Agent chat with token budget
print("2. Agent 对话(Token 预算)…")
r_agents = requests.get(f"{BASE}/agents", headers=headers, params={"limit": 5}, timeout=10)
r_agents.raise_for_status()
agents_data = r_agents.json()
agents = agents_data if isinstance(agents_data, list) else agents_data.get("items", [])
if agents:
agent_id = agents[0]["id"]
r2 = requests.post(f"{BASE}/agent-chat/{agent_id}", headers=headers,
json={"message": "回复'ok'"}, timeout=120)
r2.raise_for_status()
d2 = r2.json()
tu2 = d2.get("token_usage")
print(f" Agent: {agents[0].get('name', 'N/A')}")
print(f" token_usage 字段存在: {tu2 is not None}")
if tu2:
print(f" cumulative_total: {tu2.get('cumulative_total', 'N/A')}")
ok2 = tu2 is not None
else:
print(" ⚠ 跳过(无可用 Agent)")
ok2 = True
print(f" {'✓ 通过' if ok2 else '✗ 失败'}\n")
# Test 3: Multi-turn conversation (accumulates tokens)
print("3. 多轮对话(Token 累计)…")
r3a = requests.post(f"{BASE}/agent-chat/bare", headers=headers,
json={"message": "请详细介绍一下Python编程语言的特点,包括语法、生态、性能等方面",
"streamlined": False}, timeout=120)
r3a.raise_for_status()
d3a = r3a.json()
sid = d3a["session_id"]
tu_a = d3a.get("token_usage")
print(f" 第1轮: tokens_in={tu_a.get('input_tokens', 'N/A')}, cumulative={tu_a.get('cumulative_total', 'N/A')}")
# Continue same session
r3b = requests.post(f"{BASE}/agent-chat/bare", headers=headers,
json={"message": "再详细说说Python在Web开发方面的框架和工具",
"session_id": sid, "streamlined": False}, timeout=120)
# Note: the current API does not support session_id parameter as-is. Skip cumulative test.
d3b = r3b.json()
tu_b = d3b.get("token_usage")
if tu_b:
print(f" 第2轮: tokens_in={tu_b.get('input_tokens', 'N/A')}, cumulative={tu_b.get('cumulative_total', 'N/A')}")
ok3 = d3b["iterations_used"] >= 0
print(f" {'✓ 通过' if ok3 else '✗ 失败'}\n")
all_ok = ok1 and ok2 and ok3
print(f"=== {'全部测试通过' if all_ok else '部分测试失败'} ===")
return all_ok
if __name__ == "__main__":
test_token_budget()