mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 09:13:14 +00:00
Some checks are pending
CI / Lint (push) Waiting to run
CI / Format check (push) Waiting to run
CI / Unit tests (push) Waiting to run
CI / Playwright E2E (push) Waiting to run
CI / Docker build smoke (push) Waiting to run
CI / Triage ledger up to date (push) Waiting to run
CI / ui bun.lock in sync (push) Waiting to run
* feat: port plan-review & workflow-approval UX (#135)
Port six upstream commits onto dev:
- c03a6be7 (already ported): keep plan guidance high-level
- 546042a4: add workflow approval UI with diff preview, approval URLs,
web review links, and polling for approval status during active runs
- 216cf181: remove workflow token elevation; approved pushes pass
through directly without proxy token rewriting
- 3dbc0282: preserve plan redirects after login by accepting relative
same-origin redirect_to values and rejecting blocked paths
- bb104d93: submit plan comments with cmd+enter
- 90cb6caa: terse Slack replies, shared content via save_plan outside
plan mode (PLAN_STATUS_SHARED), reject shared-content mutations
Refs: #135
* feat: port durable dispatch hardening and startup latency improvements
Port five upstream PRs onto dev:
- #1621 / #1658: durable dispatch with loopback webhook defense,
create_durable_run helper, _config_with_prepare_run_id, degradation
to None for relative/loopback completion webhook URLs
- #1696: run-level completion webhook deduplication (replace
claim-then-post with post-then-flag per run_id), DeferredErrorModel
for graph-factory resilience, ToolRetryMiddleware for task subagents,
TimeoutWrapupMiddleware for all three graphs
- #1697: lazy-load __init__.py for agent.middleware, agent.tools,
agent.dashboard (PEP 562); defer heavy imports (exa_py in web_search,
agent.webapp in request_pr_review, deepagents in sandbox.py); add
ttl_cache.py with stale-while-revalidate for tool loaders
Refs: #137
* fix: restore login page render and clear CI lint/format
The plan-review port removed the authRedirectUrl import from login.tsx
but left its call site, crashing the login page at runtime (blank page,
no 'Sign in to open-swe'). Pass the relative path straight to loginUrl,
matching the plan route and the backend relative-redirect handling.
Also drop an unused os import in the guard test and reformat
workflow_push_guard.py to satisfy ruff.
* fix: restore RepairOrphaned middleware export and repoint model fake to deferred_model boundary
* fix: restore RepairOrphanedToolCallsMiddleware, fix E2E model-fake patch, drop dead ttl_cache
- Re-add RepairOrphanedToolCallsMiddleware to the lazy middleware __init__
(_MIDDLEWARE_MODULES, __all__, TYPE_CHECKING) so agent.reviewer can import it.
- Reroute E2E model patching to deferred_model.make_model so make_model_or_defer
(used by all three graph factories) returns the scripted fake instead of
building a real model with fake credentials.
- Drop unused agent/utils/ttl_cache.py — no agent module imports it.
- Fix import ordering in agent/reviewer.py and agent/analyzer.py (ruff I001).
- Format tests/test_dispatch.py.
* fix: claim-then-post run-level failure dedup; stop permanent suppression
---------
Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com>
Co-authored-by: Adam Moussa <adam@seahavenind.com>
123 lines
4.4 KiB
Python
123 lines
4.4 KiB
Python
"""Assembly contract for the main agent's context-management + middleware wiring.
|
|
|
|
Locks in that `get_agent` hands a sandbox `backend` to `create_deep_agent` (which
|
|
is what makes deepagents auto-wire `FilesystemMiddleware` tool-result eviction and
|
|
`SummarizationMiddleware` history offloading), and that the redundant custom
|
|
`RepairOrphanedToolCallsMiddleware` is no longer added explicitly — the built-in
|
|
`PatchToolCallsMiddleware` that `create_deep_agent` adds covers it.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
|
|
|
import pytest
|
|
from langgraph.graph.state import RunnableConfig
|
|
|
|
from agent.server import get_agent
|
|
|
|
|
|
class _DummyAgent:
|
|
def with_config(self, config: RunnableConfig) -> _DummyAgent:
|
|
self.config = config
|
|
return self
|
|
|
|
|
|
def _base_config() -> RunnableConfig:
|
|
return {
|
|
"configurable": {
|
|
"__is_for_execution__": True,
|
|
"thread_id": "thread-ctx",
|
|
"github_login": "octocat",
|
|
},
|
|
"metadata": {},
|
|
}
|
|
|
|
|
|
async def _capture_create_deep_agent_kwargs() -> dict[str, object]:
|
|
captured: dict[str, object] = {}
|
|
|
|
def fake_create_deep_agent(**kwargs: object) -> _DummyAgent:
|
|
captured.update(kwargs)
|
|
return _DummyAgent()
|
|
|
|
with (
|
|
patch(
|
|
"agent.server.resolve_github_token",
|
|
new_callable=AsyncMock,
|
|
return_value=("ghp", None),
|
|
),
|
|
patch("agent.server.resolve_triggering_user_identity", return_value=None),
|
|
patch(
|
|
"agent.server.ensure_sandbox_for_thread",
|
|
new_callable=AsyncMock,
|
|
return_value=MagicMock(),
|
|
),
|
|
patch(
|
|
"agent.server.aresolve_sandbox_work_dir",
|
|
new_callable=AsyncMock,
|
|
return_value="/workspace",
|
|
),
|
|
patch(
|
|
"agent.server.get_team_default_model_pair",
|
|
new_callable=AsyncMock,
|
|
return_value=(("openai:gpt-5.5", "medium"), ("openai:gpt-5.5", "low")),
|
|
),
|
|
patch("agent.server.load_profile", new_callable=AsyncMock, return_value=None),
|
|
patch("agent.server.fallback_model_id_for", return_value=None),
|
|
patch("agent.utils.deferred_model.make_model", side_effect=[MagicMock(), MagicMock()]),
|
|
patch("agent.server.construct_system_prompt", return_value="prompt"),
|
|
patch("agent.server.create_deep_agent", side_effect=fake_create_deep_agent),
|
|
):
|
|
await get_agent(_base_config())
|
|
|
|
return captured
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_agent_is_built_with_a_backend_for_eviction_and_summarization() -> None:
|
|
captured = await _capture_create_deep_agent_kwargs()
|
|
# The backend is what enables deepagents' auto-wired FilesystemMiddleware
|
|
# eviction + SummarizationMiddleware offloading.
|
|
assert callable(captured["backend"])
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_agent_does_not_add_custom_repair_middleware() -> None:
|
|
captured = await _capture_create_deep_agent_kwargs()
|
|
middleware = captured["middleware"]
|
|
assert isinstance(middleware, list)
|
|
names = {type(m).__name__ for m in middleware}
|
|
# Built-in PatchToolCallsMiddleware (added by create_deep_agent) replaces it.
|
|
assert "RepairOrphanedToolCallsMiddleware" not in names
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_agent_wires_subdir_agents_middleware_after_tool_error() -> None:
|
|
captured = await _capture_create_deep_agent_kwargs()
|
|
middleware = captured["middleware"]
|
|
assert isinstance(middleware, list)
|
|
names = [type(m).__name__ for m in middleware]
|
|
assert "SubdirAgentsReadMiddleware" in names
|
|
assert names.index("ToolErrorMiddleware") < names.index("SubdirAgentsReadMiddleware")
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_agent_keeps_message_queue_and_step_limit_middleware() -> None:
|
|
captured = await _capture_create_deep_agent_kwargs()
|
|
middleware = captured["middleware"]
|
|
# The dashboard depends on check_message_queue_before_model; the step-limit
|
|
# notifier must still fire when the lowered run budget is hit.
|
|
present = {type(m).__name__ for m in middleware}
|
|
assert "check_message_queue_before_model" in present
|
|
assert "notify_step_limit_reached" in present
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_agent_includes_report_platform_issue_tool() -> None:
|
|
from agent.tools import report_platform_issue
|
|
|
|
captured = await _capture_create_deep_agent_kwargs()
|
|
tools = captured["tools"]
|
|
assert isinstance(tools, list)
|
|
assert report_platform_issue in tools
|