mirror of
https://github.com/kuhyx/utils.git
synced 2026-11-10 18:07:24 +01:00
Krzysztof kuhy Rudnicki
a0fb279b1b
New agent_ready/ package (dist and live-url modes, 100% branch coverage) checks robots, sitemap, llms.txt, ai-catalog, 404, no-JS text, markdown mirrors and JSON-LD. repo_contract gains web-repo detection and installs the agent-ready pre-commit hook, CI workflow and check_agent_ready.sh shim; scripts/check_agent_ready.sh is the shared entry point. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NBScELfMUiieK9ManFbS3Y
84 lines
2.8 KiB
Python
84 lines
2.8 KiB
Python
"""Live-mode checks driven by canned responses (no sockets, no network)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from agent_ready import checks_act, checks_find, checks_read
|
|
from agent_ready.backends import Response
|
|
from agent_ready.tests import sitegen
|
|
from agent_ready.tests.fakes import FakeHttp, make_ctx, resp
|
|
|
|
LONG = "Readable text for agents that never run JavaScript. " * 4
|
|
MD_LINK = '</index.md>; rel="alternate"; type="text/markdown"'
|
|
|
|
|
|
def _home(*, ctype: str = "text/html", **headers: str) -> Response:
|
|
return resp(f"<html><body><p>{LONG}</p></body></html>", ctype, **headers)
|
|
|
|
|
|
def test_challenge_page_for_one_agent_is_reported() -> None:
|
|
challenge = resp("<html>Just a moment...</html>")
|
|
ua = checks_find.AGENT_UAS["GPTBot"]
|
|
site = FakeHttp({"/": _home()}, ua_pages={("/", ua): challenge})
|
|
ctx, out = make_ctx(site)
|
|
checks_find.check_agent_access(ctx)
|
|
assert out.getvalue().startswith("FAIL AR-FIND-01 GPTBot got a challenge page")
|
|
|
|
|
|
def test_sitemap_on_another_host_is_a_failure() -> None:
|
|
robots = "User-agent: *\nDisallow:\nSitemap: https://other.test/sitemap.xml\n"
|
|
site = FakeHttp({"/robots.txt": resp(robots, "text/plain")})
|
|
ctx, out = make_ctx(site)
|
|
checks_find.check_robots(ctx)
|
|
ctx.sitemap_pages = []
|
|
assert checks_find._sitemap_paths(ctx) == ["/sitemap.xml"]
|
|
assert (
|
|
"Sitemap is on another host: https://other.test/sitemap.xml" in out.getvalue()
|
|
)
|
|
|
|
|
|
def test_markdown_mirror_advertised_only_by_link_header() -> None:
|
|
site = FakeHttp(
|
|
{
|
|
"/": _home(link=MD_LINK),
|
|
"/index.md": resp(sitegen.mirror("Home"), "text/markdown"),
|
|
}
|
|
)
|
|
ctx, out = make_ctx(site)
|
|
checks_read.check_pages(ctx)
|
|
assert (
|
|
"PASS AR-READ-09 1 pages advertise a working markdown mirror" in out.getvalue()
|
|
)
|
|
|
|
|
|
def test_page_served_with_wrong_content_type() -> None:
|
|
ctx, out = make_ctx(FakeHttp({"/": _home(ctype="text/plain")}))
|
|
checks_read.check_pages(ctx)
|
|
assert (
|
|
"FAIL AR-READ-01 answer not in initial HTML: / (text/plain)" in out.getvalue()
|
|
)
|
|
|
|
|
|
def _mcp(status: int, **headers: str) -> Response:
|
|
return Response(status, "application/json", b"{}", dict(headers))
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("answer", "status"),
|
|
[
|
|
(_mcp(401, **{"www-authenticate": "Bearer"}), "PASS"),
|
|
(_mcp(401), "FAIL"),
|
|
],
|
|
)
|
|
def test_mcp_behind_oauth_needs_www_authenticate(answer: Response, status: str) -> None:
|
|
ctx, out = make_ctx(FakeHttp({}, mcp=answer), act=True)
|
|
checks_act.check_mcp(ctx)
|
|
assert f"{status} AR-ACT-03" in out.getvalue()
|
|
|
|
|
|
def test_act_off_reports_a_single_skip() -> None:
|
|
ctx, out = make_ctx(FakeHttp({}))
|
|
checks_act.run_act(ctx)
|
|
assert out.getvalue().startswith("SKIP AR-ACT-10 act stage off")
|