mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 23:13:15 +00:00
* feat: CI auto-fix and PR babysitting for agent PRs Watch CI failures and review feedback on PRs Open SWE opened, then dispatch confidence-gated fix runs on the originating agent thread. Adds CI webhook ingestion (check_run/check_suite/workflow_run/status), a per-PR @open-swe autofix on|off toggle, auto-response to review comments, and a polling ci_monitor graph that also flags merge conflicts. Gated by the existing autofix_mode/trigger_mode settings, the enabled-repos opt-in, base-branch and human-commit skip rules, dedupe, and a per-PR attempt cap. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: address review feedback on CI auto-fix - Security: gate the no-mention review-feedback path on author trust — require a trusted author_association (OWNER/MEMBER/COLLABORATOR) plus a GitHub write/maintain/admin permission check before dispatching a write-capable agent run, preventing privilege escalation from read/triage/outside reviewers. - Auth: reuse the originating PR thread's source + login/email when dispatching fix runs so the GitHub-token resolver authenticates them in non-bot-token deployments (bespoke github_ci source failed to resolve). - Docs: document the Commit statuses: Read-only permission required for the Status webhook event. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
252 lines
8.6 KiB
Python
252 lines
8.6 KiB
Python
"""Unit tests for the CI auto-fix orchestration core."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
import pytest
|
|
|
|
from agent import ci_autofix
|
|
|
|
_PR = {
|
|
"number": 5,
|
|
"html_url": "https://github.com/o/r/pull/5",
|
|
"base": {"sha": "base"},
|
|
"head": {"ref": "feat", "sha": "head1"},
|
|
}
|
|
|
|
|
|
@pytest.fixture
|
|
def happy(monkeypatch: pytest.MonkeyPatch) -> dict[str, Any]:
|
|
"""Patch every dependency of handle_ci_failure to a happy-path default."""
|
|
runs_create = AsyncMock()
|
|
lg_client = MagicMock()
|
|
lg_client.runs.create = runs_create
|
|
threads_update = AsyncMock()
|
|
store_client = MagicMock()
|
|
store_client.threads.update = threads_update
|
|
|
|
mocks: dict[str, Any] = {
|
|
"runs_create": runs_create,
|
|
"threads_update": threads_update,
|
|
"status_check": AsyncMock(return_value=True),
|
|
"queue": AsyncMock(return_value=True),
|
|
}
|
|
|
|
monkeypatch.setattr(
|
|
ci_autofix,
|
|
"get_autofix_settings",
|
|
AsyncMock(
|
|
return_value={
|
|
"autofix_mode": "high",
|
|
"autofix_severity_threshold": "medium",
|
|
"trigger_mode": "every_push",
|
|
}
|
|
),
|
|
)
|
|
monkeypatch.setattr(ci_autofix, "is_review_repo_enabled", AsyncMock(return_value=True))
|
|
monkeypatch.setattr(
|
|
ci_autofix, "get_github_app_installation_token", AsyncMock(return_value="tok")
|
|
)
|
|
monkeypatch.setattr(ci_autofix, "is_pr_autofix_disabled", AsyncMock(return_value=False))
|
|
monkeypatch.setattr(
|
|
ci_autofix,
|
|
"find_agent_thread_for_pr",
|
|
AsyncMock(return_value=("t1", {"github_login": "alice", "autofix_attempts": 0})),
|
|
)
|
|
monkeypatch.setattr(
|
|
ci_autofix,
|
|
"list_failing_check_runs",
|
|
AsyncMock(return_value=[{"name": "lint", "conclusion": "failure", "details_url": ""}]),
|
|
)
|
|
monkeypatch.setattr(ci_autofix, "list_failing_statuses", AsyncMock(return_value=[]))
|
|
monkeypatch.setattr(ci_autofix, "names_failing_on_base", AsyncMock(return_value=set()))
|
|
monkeypatch.setattr(
|
|
ci_autofix, "head_commit_author_login", AsyncMock(return_value="open-swe[bot]")
|
|
)
|
|
monkeypatch.setattr(ci_autofix, "is_thread_active", AsyncMock(return_value=False))
|
|
monkeypatch.setattr(ci_autofix, "queue_message_for_thread", mocks["queue"])
|
|
monkeypatch.setattr(ci_autofix, "post_autofix_status_check", mocks["status_check"])
|
|
monkeypatch.setattr(ci_autofix, "langgraph_client", lambda: lg_client)
|
|
monkeypatch.setattr(ci_autofix, "get_client", lambda: store_client)
|
|
return mocks
|
|
|
|
|
|
async def _run(**overrides: Any) -> str:
|
|
kwargs: dict[str, Any] = {
|
|
"repo_config": {"owner": "o", "name": "r"},
|
|
"branch": "feat",
|
|
"head_sha": "head1",
|
|
"pr": _PR,
|
|
}
|
|
kwargs.update(overrides)
|
|
return await ci_autofix.handle_ci_failure(**kwargs)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_dispatch_happy_path(happy: dict[str, Any]) -> None:
|
|
result = await _run()
|
|
assert result == "dispatched"
|
|
happy["runs_create"].assert_awaited_once()
|
|
happy["threads_update"].assert_awaited()
|
|
happy["status_check"].assert_awaited()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_queues_when_thread_busy(happy: dict[str, Any], monkeypatch) -> None:
|
|
monkeypatch.setattr(ci_autofix, "is_thread_active", AsyncMock(return_value=True))
|
|
result = await _run()
|
|
assert result == "queued"
|
|
happy["queue"].assert_awaited_once()
|
|
happy["runs_create"].assert_not_called()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_skip_team_disabled(happy: dict[str, Any], monkeypatch) -> None:
|
|
monkeypatch.setattr(
|
|
ci_autofix,
|
|
"get_autofix_settings",
|
|
AsyncMock(
|
|
return_value={
|
|
"autofix_mode": "off",
|
|
"autofix_severity_threshold": "medium",
|
|
"trigger_mode": "every_push",
|
|
}
|
|
),
|
|
)
|
|
assert await _run() == "autofix_disabled_team"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_skip_repo_not_enabled(happy: dict[str, Any], monkeypatch) -> None:
|
|
monkeypatch.setattr(ci_autofix, "is_review_repo_enabled", AsyncMock(return_value=False))
|
|
assert await _run() == "repo_not_enabled"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_skip_pr_disabled(happy: dict[str, Any], monkeypatch) -> None:
|
|
monkeypatch.setattr(ci_autofix, "is_pr_autofix_disabled", AsyncMock(return_value=True))
|
|
assert await _run() == "pr_disabled"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_skip_no_agent_thread(happy: dict[str, Any], monkeypatch) -> None:
|
|
monkeypatch.setattr(ci_autofix, "find_agent_thread_for_pr", AsyncMock(return_value=None))
|
|
assert await _run() == "no_agent_thread"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_skip_trigger_manual(happy: dict[str, Any], monkeypatch) -> None:
|
|
monkeypatch.setattr(
|
|
ci_autofix,
|
|
"get_autofix_settings",
|
|
AsyncMock(
|
|
return_value={
|
|
"autofix_mode": "high",
|
|
"autofix_severity_threshold": "medium",
|
|
"trigger_mode": "manual",
|
|
}
|
|
),
|
|
)
|
|
assert await _run() == "trigger_manual"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_skip_once_per_pr_after_first(happy: dict[str, Any], monkeypatch) -> None:
|
|
monkeypatch.setattr(
|
|
ci_autofix,
|
|
"get_autofix_settings",
|
|
AsyncMock(
|
|
return_value={
|
|
"autofix_mode": "high",
|
|
"autofix_severity_threshold": "medium",
|
|
"trigger_mode": "once_per_pr",
|
|
}
|
|
),
|
|
)
|
|
monkeypatch.setattr(
|
|
ci_autofix,
|
|
"find_agent_thread_for_pr",
|
|
AsyncMock(return_value=("t1", {"github_login": "alice", "autofix_attempts": 1})),
|
|
)
|
|
assert await _run() == "once_per_pr_done"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_skip_max_attempts(happy: dict[str, Any], monkeypatch) -> None:
|
|
monkeypatch.setattr(
|
|
ci_autofix,
|
|
"find_agent_thread_for_pr",
|
|
AsyncMock(
|
|
return_value=(
|
|
"t1",
|
|
{"github_login": "alice", "autofix_attempts": ci_autofix.MAX_AUTOFIX_ATTEMPTS},
|
|
)
|
|
),
|
|
)
|
|
assert await _run() == "max_attempts"
|
|
happy["status_check"].assert_awaited()
|
|
happy["runs_create"].assert_not_called()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_skip_all_failing_on_base(happy: dict[str, Any], monkeypatch) -> None:
|
|
monkeypatch.setattr(ci_autofix, "names_failing_on_base", AsyncMock(return_value={"lint"}))
|
|
assert await _run() == "all_failing_on_base"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_skip_already_handled(happy: dict[str, Any], monkeypatch) -> None:
|
|
key = ci_autofix._dedupe_key("head1", ["lint"])
|
|
monkeypatch.setattr(
|
|
ci_autofix,
|
|
"find_agent_thread_for_pr",
|
|
AsyncMock(return_value=("t1", {"github_login": "alice", "autofix_handled": [key]})),
|
|
)
|
|
assert await _run() == "already_handled"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_skip_human_commit(happy: dict[str, Any], monkeypatch) -> None:
|
|
monkeypatch.setattr(ci_autofix, "head_commit_author_login", AsyncMock(return_value="mallory"))
|
|
assert await _run() == "human_commit"
|
|
happy["runs_create"].assert_not_called()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_no_failing_checks(happy: dict[str, Any], monkeypatch) -> None:
|
|
monkeypatch.setattr(ci_autofix, "list_failing_check_runs", AsyncMock(return_value=[]))
|
|
assert await _run(failing_checks=None) == "no_failing_checks"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_ci_read_failed(happy: dict[str, Any], monkeypatch) -> None:
|
|
monkeypatch.setattr(ci_autofix, "list_failing_check_runs", AsyncMock(return_value=None))
|
|
monkeypatch.setattr(ci_autofix, "list_failing_statuses", AsyncMock(return_value=None))
|
|
assert await _run(failing_checks=None) == "ci_read_failed"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_find_agent_thread_picks_agent_skips_reviewer(monkeypatch) -> None:
|
|
client = MagicMock()
|
|
client.threads.search = AsyncMock(
|
|
return_value=[
|
|
{"thread_id": "rev", "metadata": {"kind": "reviewer", "agent_kind": "agent"}},
|
|
{"thread_id": "ag", "metadata": {"agent_kind": "agent"}},
|
|
]
|
|
)
|
|
monkeypatch.setattr(ci_autofix, "get_client", lambda: client)
|
|
found = await ci_autofix.find_agent_thread_for_pr("https://github.com/o/r/pull/5")
|
|
assert found is not None
|
|
assert found[0] == "ag"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_find_agent_thread_none_when_only_reviewer(monkeypatch) -> None:
|
|
client = MagicMock()
|
|
client.threads.search = AsyncMock(
|
|
return_value=[{"thread_id": "rev", "metadata": {"kind": "reviewer"}}]
|
|
)
|
|
monkeypatch.setattr(ci_autofix, "get_client", lambda: client)
|
|
assert await ci_autofix.find_agent_thread_for_pr("u") is None
|