mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-10-26 21:26:39 +00:00
033fb1aa1f
`get_readme` and `get_file_content` answered every failure with a string -- `[README not found: HTTP 404]`, `[File not found: HTTP 404]` -- while `main()` prints any string result on stdout and exits 0. A rate-limited run, a missing repository and a real README therefore arrived on the same channel with the same exit code, so a caller reading stdout could not tell a failure from a body. Both readers now raise `GitHubAPIError` naming the operation, the target and the underlying HTTP error. The CLI's existing handler already writes an exception to stderr and exits 1, so a failure leaves the success channel empty and the status stays visible; a successful fetch is unchanged. Pins both transports (requests and the urllib fallback), 404 against 403 so a rate limit cannot read as a missing repository, the file reader's path, and the CLI contract: non-zero exit, empty stdout, status on stderr.
273 lines
9.1 KiB
Python
273 lines
9.1 KiB
Python
"""Exercise the GitHub research client's HTTP transports without network IO."""
|
|
|
|
import http.client
|
|
import io
|
|
import runpy
|
|
import sys
|
|
import urllib.request
|
|
from pathlib import Path
|
|
from urllib.parse import parse_qs, urlsplit
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture
|
|
def fallback_client(monkeypatch):
|
|
monkeypatch.setitem(sys.modules, "requests", None)
|
|
script = (
|
|
Path(__file__).resolve().parents[2]
|
|
/ "skills/public/github-deep-research/scripts/github_api.py"
|
|
)
|
|
module = runpy.run_path(str(script))
|
|
captured = {}
|
|
|
|
def fake_urlopen(request, timeout):
|
|
# Validate the request target as the real HTTP transport does, without IO.
|
|
connection = http.client.HTTPSConnection("api.github.com")
|
|
try:
|
|
connection.putrequest("GET", request.selector)
|
|
finally:
|
|
connection.close()
|
|
captured.update(url=request.full_url, timeout=timeout, headers=request.headers)
|
|
response = io.BytesIO(b'{"ok": true}')
|
|
response.status = 200
|
|
return response
|
|
|
|
monkeypatch.setattr(urllib.request, "urlopen", fake_urlopen)
|
|
return module["GitHubAPI"](), captured
|
|
|
|
|
|
@pytest.fixture(params=["requests", "urllib"])
|
|
def file_content_client(request, monkeypatch):
|
|
if request.param == "urllib":
|
|
return request.getfixturevalue("fallback_client")
|
|
|
|
requests = pytest.importorskip("requests")
|
|
script = (
|
|
Path(__file__).resolve().parents[2]
|
|
/ "skills/public/github-deep-research/scripts/github_api.py"
|
|
)
|
|
module = runpy.run_path(str(script))
|
|
captured = {}
|
|
|
|
def fake_send(session, prepared_request, **kwargs):
|
|
captured["url"] = prepared_request.url
|
|
response = requests.Response()
|
|
response.status_code = 200
|
|
response._content = b'{"ok": true}'
|
|
return response
|
|
|
|
monkeypatch.setattr(requests.Session, "send", fake_send)
|
|
return module["GitHubAPI"](), captured
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("path", "encoded_path"),
|
|
[
|
|
("docs/C# guide.md", "docs/C%23%20guide.md"),
|
|
("docs/query?draft.md", "docs/query%3Fdraft.md"),
|
|
("docs/literal%20name.md", "docs/literal%2520name.md"),
|
|
("文档/入门 guide.md", "%E6%96%87%E6%A1%A3/%E5%85%A5%E9%97%A8%20guide.md"),
|
|
("docs/file name.md", "docs/file%20name.md"),
|
|
("src/nested/README.md", "src/nested/README.md"),
|
|
],
|
|
)
|
|
def test_file_content_preserves_repository_path(
|
|
file_content_client, path, encoded_path
|
|
):
|
|
client, captured = file_content_client
|
|
|
|
assert client.get_file_content("owner", "repo", path) == '{"ok": true}'
|
|
|
|
url = urlsplit(captured["url"])
|
|
assert url.path == f"/repos/owner/repo/contents/{encoded_path}"
|
|
assert url.query == ""
|
|
assert url.fragment == ""
|
|
|
|
|
|
@pytest.mark.parametrize("query", ["bug fix", "C++ & retry#fragment", "模型请求"])
|
|
def test_fallback_search_preserves_query(fallback_client, query):
|
|
client, captured = fallback_client
|
|
|
|
assert client.search_issues("owner", "repo", query) == {"ok": True}
|
|
|
|
url = urlsplit(captured["url"])
|
|
assert url.path == "/search/issues"
|
|
assert url.fragment == ""
|
|
assert parse_qs(url.query) == {
|
|
"q": [f"repo:owner/repo {query}"],
|
|
"per_page": ["30"],
|
|
}
|
|
|
|
|
|
def test_fallback_issues_preserves_filters(fallback_client):
|
|
client, captured = fallback_client
|
|
|
|
assert client.get_issues(
|
|
"owner", "repo", state="open", limit=10, labels="bug,help wanted"
|
|
) == {"ok": True}
|
|
|
|
assert parse_qs(urlsplit(captured["url"]).query) == {
|
|
"state": ["open"],
|
|
"per_page": ["10"],
|
|
"labels": ["bug,help wanted"],
|
|
}
|
|
|
|
|
|
def test_fallback_ordinary_parameters(fallback_client):
|
|
client, captured = fallback_client
|
|
|
|
assert client.get_contributors("owner", "repo", limit=10) == {"ok": True}
|
|
|
|
assert parse_qs(urlsplit(captured["url"]).query) == {"per_page": ["10"]}
|
|
assert captured["timeout"] == 30
|
|
assert captured["headers"]["User-agent"] == "Deep-Research-Bot/1.0"
|
|
|
|
|
|
def test_fallback_without_parameters(fallback_client):
|
|
client, captured = fallback_client
|
|
|
|
assert client.get_repo_info("owner", "repo") == {"ok": True}
|
|
|
|
assert captured["url"] == "https://api.github.com/repos/owner/repo"
|
|
|
|
|
|
def test_tree_asks_for_the_repository_head(file_content_client):
|
|
client, captured = file_content_client
|
|
|
|
assert client.get_tree("owner", "repo") == {"ok": True}
|
|
|
|
url = urlsplit(captured["url"])
|
|
assert url.path == "/repos/owner/repo/git/trees/HEAD"
|
|
assert parse_qs(url.query) == {"recursive": ["1"]}
|
|
|
|
|
|
def test_tree_keeps_an_explicit_branch(file_content_client):
|
|
client, captured = file_content_client
|
|
|
|
assert client.get_tree("owner", "repo", branch="dev", recursive=False) == {
|
|
"ok": True
|
|
}
|
|
|
|
url = urlsplit(captured["url"])
|
|
assert url.path == "/repos/owner/repo/git/trees/dev"
|
|
assert url.query == ""
|
|
|
|
|
|
def test_tree_does_not_guess_another_branch(monkeypatch, fallback_client):
|
|
client, _ = fallback_client
|
|
asked: list[str] = []
|
|
|
|
def fail_after_recording(endpoint, params=None, accept=None):
|
|
asked.append(endpoint)
|
|
raise RuntimeError("HTTP 404")
|
|
|
|
monkeypatch.setattr(client, "_get", fail_after_recording)
|
|
|
|
with pytest.raises(RuntimeError):
|
|
client.get_tree("owner", "repo")
|
|
|
|
# A stale `master` still resolves as a branch, so retrying names here silently
|
|
# returns the stale branch's tree instead of failing.
|
|
assert asked == ["/repos/owner/repo/git/trees/HEAD"]
|
|
|
|
|
|
def _client_returning_status(monkeypatch, transport, status, body=b'{"ok": true}'):
|
|
"""One client whose transport answers ``status`` for every request, plus its module.
|
|
|
|
Both transports are exercised because the script picks one at import time: a fix that
|
|
only holds for ``requests`` would leave the fallback (the path taken when the dependency is
|
|
missing) answering an error as content.
|
|
"""
|
|
script = (
|
|
Path(__file__).resolve().parents[2]
|
|
/ "skills/public/github-deep-research/scripts/github_api.py"
|
|
)
|
|
if transport == "urllib":
|
|
monkeypatch.setitem(sys.modules, "requests", None)
|
|
module = runpy.run_path(str(script))
|
|
|
|
def fake_urlopen(request, timeout):
|
|
response = io.BytesIO(body)
|
|
response.status = status
|
|
return response
|
|
|
|
monkeypatch.setattr(urllib.request, "urlopen", fake_urlopen)
|
|
return module["GitHubAPI"](), module
|
|
|
|
requests = pytest.importorskip("requests")
|
|
monkeypatch.delitem(sys.modules, "requests", raising=False)
|
|
module = runpy.run_path(str(script))
|
|
|
|
def fake_send(session, prepared_request, **kwargs):
|
|
response = requests.Response()
|
|
response.status_code = status
|
|
response._content = body
|
|
response.url = prepared_request.url
|
|
return response
|
|
|
|
monkeypatch.setattr(requests.Session, "send", fake_send)
|
|
return module["GitHubAPI"](), module
|
|
|
|
|
|
@pytest.mark.parametrize("transport", ["requests", "urllib"])
|
|
@pytest.mark.parametrize("status", [404, 403])
|
|
def test_a_failed_readme_fetch_is_an_error_not_content(monkeypatch, transport, status):
|
|
client, module = _client_returning_status(monkeypatch, transport, status)
|
|
|
|
with pytest.raises(module["GitHubAPIError"]) as excinfo:
|
|
client.get_readme("owner", "repo")
|
|
|
|
message = str(excinfo.value)
|
|
assert "README" in message and "owner/repo" in message
|
|
assert str(status) in message, "the HTTP status must stay visible"
|
|
|
|
|
|
def test_a_rate_limit_is_distinguishable_from_a_missing_repository(
|
|
monkeypatch,
|
|
):
|
|
limited, module = _client_returning_status(monkeypatch, "requests", 403)
|
|
with pytest.raises(module["GitHubAPIError"]) as excinfo:
|
|
limited.get_readme("owner", "repo")
|
|
limited_message = str(excinfo.value)
|
|
|
|
monkeypatch.undo()
|
|
missing, module = _client_returning_status(monkeypatch, "requests", 404)
|
|
with pytest.raises(module["GitHubAPIError"]) as excinfo:
|
|
missing.get_readme("owner", "repo")
|
|
missing_message = str(excinfo.value)
|
|
|
|
assert "403" in limited_message and "404" not in limited_message
|
|
assert "404" in missing_message and "403" not in missing_message
|
|
|
|
|
|
@pytest.mark.parametrize("transport", ["requests", "urllib"])
|
|
def test_a_failed_file_fetch_names_the_path(monkeypatch, transport):
|
|
client, module = _client_returning_status(monkeypatch, transport, 404)
|
|
|
|
with pytest.raises(module["GitHubAPIError"]) as excinfo:
|
|
client.get_file_content("owner", "repo", "docs/guide.md")
|
|
|
|
message = str(excinfo.value)
|
|
assert "docs/guide.md" in message and "404" in message
|
|
|
|
|
|
@pytest.mark.parametrize("transport", ["requests", "urllib"])
|
|
def test_the_cli_reports_a_fetch_failure_on_stderr_and_exits_nonzero(
|
|
monkeypatch, capsys, transport
|
|
):
|
|
"""The success channel stays empty: a caller reading stdout cannot mistake a failure for a
|
|
README body, and the exit code says the run did not succeed."""
|
|
_, module = _client_returning_status(monkeypatch, transport, 404)
|
|
monkeypatch.setattr(
|
|
sys, "argv", ["github_api.py", "owner", "repo", "readme"]
|
|
)
|
|
|
|
with pytest.raises(SystemExit) as excinfo:
|
|
module["main"]()
|
|
|
|
captured = capsys.readouterr()
|
|
assert excinfo.value.code == 1
|
|
assert captured.out == ""
|
|
assert "404" in captured.err
|