Add Agent evaluation report site

This commit is contained in:
wuyang
2026-07-27 16:44:10 +08:00
parent df475e8d90
commit cd1eacbd9e
15 changed files with 2487 additions and 0 deletions
+19
View File
@@ -24,6 +24,11 @@ REQUIRED_FILES = (
"research/evaluation/k1412-agent-evaluation-v1.md",
"data/evaluation/k1412-agent-eval-task-contracts-v1.json",
"tools/evaluation/score_agent_runs.py",
"evaluation-site/index.html",
"evaluation-site/assets/styles.css",
"evaluation-site/assets/app.js",
"evaluation-site/Dockerfile",
"evaluation-site/nginx.conf",
"web/app.py",
"web/agent-knowledge-atlas.service",
"web/manage.sh",
@@ -138,6 +143,18 @@ def check_evaluation_contract() -> int:
return len(tasks)
def check_evaluation_site() -> None:
html = (ROOT / "evaluation-site/index.html").read_text(encoding="utf-8")
javascript = (ROOT / "evaluation-site/assets/app.js").read_text(encoding="utf-8")
dockerfile = (ROOT / "evaluation-site/Dockerfile").read_text(encoding="utf-8")
nginx = (ROOT / "evaluation-site/nginx.conf").read_text(encoding="utf-8")
require("不是真实跑分" in html, "evaluation simulation must keep its evidence boundary visible")
require("尚未运行真实模型对比" in html, "evaluation report overstates current evidence")
require("const TASKS" in javascript, "evaluation task browser is missing")
require("install -d -m 0755" in dockerfile, "static asset directory must remain traversable")
require('location = /health' in nginx, "evaluation site health endpoint is missing")
def main() -> int:
check_required_files()
collections = check_collection_index()
@@ -146,6 +163,7 @@ def main() -> int:
check_ollama_contract()
check_experiment_state()
evaluation_tasks = check_evaluation_contract()
check_evaluation_site()
print(
json.dumps(
{
@@ -153,6 +171,7 @@ def main() -> int:
"collections": collections,
"research": research,
"evaluation_tasks": evaluation_tasks,
"evaluation_site": True,
"python_files_checked": python_files,
},
ensure_ascii=False,