mirror of
https://github.com/ZhuLinsen/daily_stock_analysis
synced 2026-09-20 10:53:33 +08:00
b6f9a61671
* feat: add minimal agent trajectory metrics with golden samples * feat: add runnable agent trajectory eval entry with JSON and text reports * fix: treat unsuccessful AgentResult as a run failure in trajectory eval * fix: reject multi-arch executor and validate golden tools against the real registry
7 lines
224 B
Python
7 lines
224 B
Python
# -*- coding: utf-8 -*-
|
|
"""Agent trajectory evaluation package (Issue #1956).
|
|
|
|
Pure-function metrics layer that scores a real ``tool_calls_log`` against
|
|
golden samples; the runnable entry point lives in ``run_eval.py``.
|
|
"""
|