open-swe/tests/test_ci_autofix.py
Johannes du Plessis 209132d355
refactor: durable interrupt dispatch + completion webhook (#1621)
* wip(rebuild): core reliability spine

- remove PR-babysitting (ci_autofix + ci_monitor graph + webhook wiring)
- dispatch core: agent/dispatch.py with multitask_strategy=interrupt +
  durability=sync + completion webhook; reroute all webhook + plan triggers;
  drop the racy in-process lock + is_thread_active busy-check
- completion webhook: agent/completion.py + /webhooks/run-complete loopback
  route for failure/timeout replies (idempotent)

Co-authored-by: open-swe[bot]

* feat(rebuild): async tools, reconcile, shared http timeouts, assembly tuning

Parallel batch on top of the reliability spine:
- async-ify all 24 tools (drop asyncio.run; requests->httpx); re-implement the
  http_request/fetch_url SSRF + DNS-rebinding defense httpx-natively and harden
  the IP check to 'not is_global' (+ IPv4-mapped unwrap)
- reconcile.py: stale pending-run sweep (threads.search -> per-thread runs.list
  -> cancel_many), wired into the scheduler graph via task='reconcile'
- shared DEFAULT_HTTP_TIMEOUT (agent/utils/http.py) on every bare
  httpx.AsyncClient() across utils/dashboard/webapp/middleware
- run budget: MODEL_CALL_RECURSION_LIMIT 5000->250
- fix stale OpenAI->Anthropic fallback id (claude-opus-4-5 -> 4-8)
- drop redundant custom repair middleware (deepagents auto-adds PatchToolCalls)
- confirm tool-result eviction + summarization auto-wired via backend
- slim system prompt ~8% (full harness-profile rewrite deferred)

Co-authored-by: open-swe[bot]

* feat(rebuild): harness-profile prompt + split webhooks out of webapp

- prompt.py: own the system prompt via a registered harness profile
  (OPEN_SWE_SHARED_BASE, kept neutral so the read-only reviewer/analyzer that
  share it stay safe), registered across all 4 providers; per-thread values
  stay in construct_system_prompt. Assembled main-agent prompt ~6.8k -> ~3.1k
  tokens (~55% smaller); de-duped PR/commit/suite/force-push guidance; dropped
  ALL-CAPS markers.
- webapp.py 3325 -> 1890 LOC: moved 14 per-source handlers into
  agent/webhooks/{linear,slack,github}.py; webapp re-exports them for the
  routes + tests; moved handlers reach shared helpers via the webapp namespace
  to preserve the test suite's monkeypatch targets.

Full suite: 1168 passing, lint clean.

Co-authored-by: open-swe[bot]

* Restore MODEL_CALL_RECURSION_LIMIT to 5000 for long-running tasks

Reverts the 250 cap from the run-budget change — long-running tasks legitimately
need many model calls. The notify_step_limit_reached safety net still fires if a
run does hit the cap, so runs end with a signal either way.

Co-authored-by: open-swe[bot]

* fix: address PR review (auth, SSRF, interrupted status, redirect headers)

- completion.py: drop `interrupted` from failure statuses — with
  multitask_strategy=interrupt a follow-up ends the prior run as interrupted,
  which is healthy, not a failure to report. [open-swe]
- /webhooks/run-complete: shared-secret auth — dispatch appends ?token= when
  RUN_COMPLETE_WEBHOOK_SECRET is set; route verifies via hmac.compare_digest.
  [corridor-security]
- SSRF: extract the URL validator to agent/utils/url_safety.py and apply it
  before server-side image fetches in multimodal.fetch_image_block.
  [corridor-security]
- http_request: preserve caller headers/extensions across redirect hops instead
  of dropping them on the first hop. [open-swe]

Co-authored-by: open-swe[bot]

* chore: remove REBUILD_PLAN.md (planning doc, not needed in the repo)

Co-authored-by: open-swe[bot]

* fix: fail closed on run-complete webhook auth when secret unset

Corridor follow-up: verify_run_complete_token returns False (not True) when
RUN_COMPLETE_WEBHOOK_SECRET is unset, so the public route is never
unauthenticated. Logs a startup warning when the secret is absent, and dispatch
skips registering the webhook when there's no secret (no rejected callbacks).

Co-authored-by: open-swe[bot]

---------

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-26 13:48:38 -07:00

249 lines
9.1 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()
store_put = AsyncMock()
lg_client = MagicMock()
lg_client.runs.create = runs_create
lg_client.store.get_item = AsyncMock(return_value=None)
lg_client.store.put_item = store_put
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),
"store_put": store_put,
}
monkeypatch.setattr(ci_autofix, "_user_autofix_enabled", AsyncMock(return_value=True))
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, "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_batches_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 == "batched"
happy["store_put"].assert_awaited()
happy["runs_create"].assert_not_called()
# A batched event must not burn an attempt or mark the SHA handled, so a later
# webhook/sweep can still dispatch if the in-flight run never consumes it.
happy["threads_update"].assert_not_awaited()
@pytest.mark.asyncio
async def test_skip_user_disabled(happy: dict[str, Any], monkeypatch) -> None:
monkeypatch.setattr(ci_autofix, "_user_autofix_enabled", AsyncMock(return_value=False))
assert await _run() == "autofix_disabled_user"
@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_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")
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_review_feedback_skips_user_disabled(happy: dict[str, Any], monkeypatch) -> None:
monkeypatch.setattr(ci_autofix, "_user_autofix_enabled", AsyncMock(return_value=False))
assert (
await ci_autofix.handle_review_feedback(
repo_config={"owner": "o", "name": "r"},
pr_number=5,
pr_url="https://github.com/o/r/pull/5",
reviewer="alice",
body="fix this",
)
== "autofix_disabled_user"
)
happy["runs_create"].assert_not_called()
@pytest.mark.asyncio
async def test_review_feedback_batches_when_thread_busy(happy: dict[str, Any], monkeypatch) -> None:
monkeypatch.setattr(ci_autofix, "has_repo_write_permission", AsyncMock(return_value=True))
monkeypatch.setattr(ci_autofix, "is_thread_active", AsyncMock(return_value=True))
result = await ci_autofix.handle_review_feedback(
repo_config={"owner": "o", "name": "r"},
pr_number=5,
pr_url="https://github.com/o/r/pull/5",
reviewer="alice",
body="fix this",
)
assert result == "batched"
happy["runs_create"].assert_not_called()
@pytest.mark.asyncio
async def test_review_feedback_checks_write_permission_after_user_gate(
happy: dict[str, Any], monkeypatch
) -> None:
permission = AsyncMock(return_value=False)
monkeypatch.setattr(ci_autofix, "has_repo_write_permission", permission)
result = await ci_autofix.handle_review_feedback(
repo_config={"owner": "o", "name": "r"},
pr_number=5,
pr_url="https://github.com/o/r/pull/5",
reviewer="alice",
body="fix this",
)
assert result == "reviewer_no_write_permission"
permission.assert_awaited_once()
happy["runs_create"].assert_not_called()
@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