tzt
ce0f6170d3
- 入库历史遗漏源码/测试：router_system 9 模块（agent/executors/inference/knowledge/ memory/planner/skills/trace）、tests 11 个测试文件、config/knowledge 领域知识 - 入库根目录方案文档（v2/v3/可行性×2）、references 文献（arxiv 14-18/cnki_open/ 参考文献清单）、research 论文素材（routerarena/paper/中文文献 PDF） - 前端构建产物刷新（新 hash）；webapp 误写文档删除 - gitignore 增补：deepseek-harness、research/_refs、.mimosa/.zcode、网关日志/pid、 临时调试脚本、tests/e2e/node_modules、AI代理功能开发/prefix - 基线确认：318 passed
96 lines
3.9 KiB
Python
96 lines
3.9 KiB
Python
"""一次性验证脚本：真实 DeepSeek 架构师 + 脚手架 Worker，走完整协作四步。
|
||
|
||
步骤映射：
|
||
1) architect.brief 分析拆解 -> 交流文本（交接文档）
|
||
2) worker 读交接文档构建实现（第 1 次故意输出不合格 -> 触发问题）
|
||
3) worker 验证失败 -> issue 交接至文档 -> architect.decide 裁决（真实 API）
|
||
4) worker 按裁决修复 -> 全步完成 -> architect.final_review 终审（真实 API）
|
||
"""
|
||
import asyncio
|
||
import json
|
||
import sys
|
||
from pathlib import Path
|
||
|
||
sys.path.insert(0, str(Path(__file__).resolve().parent))
|
||
|
||
from gateway.api import build_agent_chat # noqa: E402 复用 .env 里的 key 构建客户端
|
||
from router_system.architect import build_architect # noqa: E402
|
||
from router_system.pipeline import CollaborativePipeline # noqa: E402
|
||
from router_system.worker import WorkerLoop # noqa: E402
|
||
|
||
QUERY = "用 Python 写一个函数 count_primes(n)，返回小于 n 的质数个数，附单元测试。"
|
||
|
||
GOOD_CODE = '''```python
|
||
def count_primes(n):
|
||
if n < 3:
|
||
return 0
|
||
is_prime = [True] * n
|
||
is_prime[0] = is_prime[1] = False
|
||
for i in range(2, int(n ** 0.5) + 1):
|
||
if is_prime[i]:
|
||
for j in range(i * i, n, i):
|
||
is_prime[j] = False
|
||
return sum(is_prime)
|
||
|
||
|
||
def test_count_primes():
|
||
assert count_primes(0) == 0
|
||
assert count_primes(2) == 0
|
||
assert count_primes(10) == 4
|
||
assert count_primes(20) == 8
|
||
```'''
|
||
|
||
|
||
async def main() -> None:
|
||
cfg = {"base_url": "https://api.deepseek.com", "model": "deepseek-chat"}
|
||
architect = build_architect({**cfg, "api_key": _env_key()})
|
||
print(f"[architect] model={architect.model} key={'已配置' if architect.api_key else '缺失'}")
|
||
|
||
calls = {"n": 0}
|
||
|
||
async def scripted_generate(prompt: str) -> str:
|
||
"""第 1 次故意交不合格产物（触发 issue->decide），第 2 次交合格实现。"""
|
||
calls["n"] += 1
|
||
if calls["n"] == 1:
|
||
print("[worker] 第 1 次生成：故意输出不合格（无代码块）")
|
||
return "这一步我没想清楚，先给个思路：应该用筛法，但代码还没写。"
|
||
print("[worker] 第 2 次生成：交出完整实现（含测试）")
|
||
return GOOD_CODE
|
||
|
||
worker = WorkerLoop(generate=scripted_generate, max_fix_attempts=1,
|
||
model_used="scripted-worker")
|
||
pipe = CollaborativePipeline(architect=architect, worker=worker,
|
||
fast_path=False, rounds_cap=6, api_token_cap=30000)
|
||
result = await pipe.run(QUERY, request_id="collabdemo01")
|
||
|
||
print("\n========== 路线 ==========")
|
||
print(" -> ".join(result.route))
|
||
ws = json.loads(Path(result.workspace_path).read_text(encoding="utf-8"))
|
||
print("\n========== 交流文本关键内容 ==========")
|
||
print("brief.goal:", ws["brief"]["goal"][:80])
|
||
print("plan:", [(p["id"], p["task"][:36]) for p in ws["brief"]["plan"]])
|
||
print("issues:", [(i["id"], i["step"], i["summary"][:40]) for i in ws.get("issues", [])])
|
||
print("decisions:", [(d["ref"], d["reply"][:60]) for d in ws.get("decisions", [])])
|
||
print("progress:", [(p["step"], p["status"]) for p in ws.get("progress", [])])
|
||
print("final verdict:", ws["meta"].get("review_verdict", "(看 route)"))
|
||
print("\n========== 结果 ==========")
|
||
print("status:", result.status, "| rounds:", result.rounds_used,
|
||
"| api_tokens:", result.api_input_tokens, "+", result.api_output_tokens,
|
||
"| latency:", round(result.latency_ms), "ms")
|
||
print("response 前 300 字：\n", result.response[:300])
|
||
|
||
|
||
def _env_key() -> str:
|
||
import os
|
||
from dotenv import load_dotenv
|
||
load_dotenv(Path(__file__).resolve().parent / ".env")
|
||
key = os.environ.get("DEEPSEEK_API_KEY")
|
||
if not key:
|
||
print("缺少 DEEPSEEK_API_KEY，无法做真实协作验证")
|
||
sys.exit(1)
|
||
return key
|
||
|
||
|
||
if __name__ == "__main__":
|
||
asyncio.run(main())
|