mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 22:03:14 +00:00
* 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>
205 lines
6.7 KiB
Python
205 lines
6.7 KiB
Python
from __future__ import annotations
|
|
|
|
from datetime import UTC, datetime, timedelta
|
|
from typing import Any
|
|
|
|
import pytest
|
|
|
|
from agent.utils import github_app
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _clear_token_cache() -> Any:
|
|
github_app.clear_app_token_cache()
|
|
yield
|
|
github_app.clear_app_token_cache()
|
|
|
|
|
|
class _FakeResponse:
|
|
def raise_for_status(self) -> None:
|
|
pass
|
|
|
|
def json(self) -> dict[str, str]:
|
|
return {"token": "token", "expires_at": "expires"}
|
|
|
|
|
|
class _FakeAsyncClient:
|
|
last_post: dict[str, Any] | None = None
|
|
|
|
def __init__(self, **kwargs: Any) -> None:
|
|
pass
|
|
|
|
async def __aenter__(self) -> _FakeAsyncClient:
|
|
return self
|
|
|
|
async def __aexit__(self, exc_type: object, exc: object, tb: object) -> None:
|
|
return None
|
|
|
|
async def post(self, url: str, **kwargs: Any) -> _FakeResponse:
|
|
type(self).last_post = {"url": url, **kwargs}
|
|
return _FakeResponse()
|
|
|
|
|
|
def _configure(monkeypatch: pytest.MonkeyPatch, client_cls: type) -> None:
|
|
monkeypatch.setattr(github_app, "GITHUB_APP_ID", "1")
|
|
monkeypatch.setattr(github_app, "GITHUB_APP_PRIVATE_KEY", "key")
|
|
monkeypatch.setattr(github_app, "GITHUB_APP_INSTALLATION_ID", "2")
|
|
monkeypatch.setattr(github_app, "_generate_app_jwt", lambda: "jwt")
|
|
monkeypatch.setattr(github_app.httpx, "AsyncClient", client_cls)
|
|
|
|
|
|
class _CountingResponse:
|
|
def __init__(self, expires_at: str) -> None:
|
|
self._expires_at = expires_at
|
|
|
|
def raise_for_status(self) -> None:
|
|
pass
|
|
|
|
def json(self) -> dict[str, str]:
|
|
return {"token": "tok-123", "expires_at": self._expires_at}
|
|
|
|
|
|
class _CountingClient:
|
|
posts = 0
|
|
expires_at = "2099-01-01T00:00:00Z"
|
|
|
|
def __init__(self, **kwargs: Any) -> None:
|
|
pass
|
|
|
|
async def __aenter__(self) -> _CountingClient:
|
|
return self
|
|
|
|
async def __aexit__(self, exc_type: object, exc: object, tb: object) -> None:
|
|
return None
|
|
|
|
async def post(self, url: str, **kwargs: Any) -> _CountingResponse:
|
|
type(self).posts += 1
|
|
return _CountingResponse(type(self).expires_at)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_token_is_cached_until_near_expiry(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
future = (datetime.now(UTC) + timedelta(hours=1)).isoformat()
|
|
|
|
class Client(_CountingClient):
|
|
posts = 0
|
|
expires_at = future
|
|
|
|
_configure(monkeypatch, Client)
|
|
|
|
t1, _ = await github_app.get_github_app_installation_token_with_expiry()
|
|
t2, _ = await github_app.get_github_app_installation_token_with_expiry()
|
|
|
|
assert t1 == t2 == "tok-123"
|
|
assert Client.posts == 1 # second call served from the in-process cache
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_cache_is_scoped_per_repository_set(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
future = (datetime.now(UTC) + timedelta(hours=1)).isoformat()
|
|
|
|
class Client(_CountingClient):
|
|
posts = 0
|
|
expires_at = future
|
|
|
|
_configure(monkeypatch, Client)
|
|
|
|
await github_app.get_github_app_installation_token_with_expiry(repositories=["a"])
|
|
await github_app.get_github_app_installation_token_with_expiry(repositories=["b"])
|
|
await github_app.get_github_app_installation_token_with_expiry(repositories=["a"])
|
|
|
|
assert Client.posts == 2 # distinct scopes mint separately; the repeat is cached
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_near_expiry_token_is_not_cached(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
soon = (datetime.now(UTC) + timedelta(minutes=2)).isoformat()
|
|
|
|
class Client(_CountingClient):
|
|
posts = 0
|
|
expires_at = soon
|
|
|
|
_configure(monkeypatch, Client)
|
|
|
|
await github_app.get_github_app_installation_token_with_expiry()
|
|
await github_app.get_github_app_installation_token_with_expiry()
|
|
|
|
assert Client.posts == 2 # within the safety margin -> re-minted every call
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_installation_token_can_be_scoped_to_repository_ids(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
monkeypatch.setattr(github_app, "GITHUB_APP_ID", "1")
|
|
monkeypatch.setattr(github_app, "GITHUB_APP_PRIVATE_KEY", "key")
|
|
monkeypatch.setattr(github_app, "GITHUB_APP_INSTALLATION_ID", "2")
|
|
monkeypatch.setattr(github_app, "_generate_app_jwt", lambda: "jwt")
|
|
monkeypatch.setattr(github_app.httpx, "AsyncClient", _FakeAsyncClient)
|
|
|
|
token, expires_at = await github_app.get_github_app_installation_token_with_expiry(
|
|
repository_ids=[123]
|
|
)
|
|
|
|
assert token == "token"
|
|
assert expires_at == "expires"
|
|
assert _FakeAsyncClient.last_post is not None
|
|
assert _FakeAsyncClient.last_post["json"] == {"repository_ids": [123]}
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_installation_token_includes_permissions(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
monkeypatch.setattr(github_app, "GITHUB_APP_ID", "1")
|
|
monkeypatch.setattr(github_app, "GITHUB_APP_PRIVATE_KEY", "key")
|
|
monkeypatch.setattr(github_app, "GITHUB_APP_INSTALLATION_ID", "2")
|
|
monkeypatch.setattr(github_app, "_generate_app_jwt", lambda: "jwt")
|
|
monkeypatch.setattr(github_app.httpx, "AsyncClient", _FakeAsyncClient)
|
|
|
|
await github_app.get_github_app_installation_token_with_expiry(
|
|
repositories=["open-swe"], permissions={"workflows": "write", "contents": "write"}
|
|
)
|
|
|
|
assert _FakeAsyncClient.last_post is not None
|
|
assert _FakeAsyncClient.last_post["json"] == {
|
|
"repositories": ["open-swe"],
|
|
"permissions": {"contents": "write", "workflows": "write"},
|
|
}
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_cache_is_scoped_per_permission_set(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
future = (datetime.now(UTC) + timedelta(hours=1)).isoformat()
|
|
|
|
class Client(_CountingClient):
|
|
posts = 0
|
|
expires_at = future
|
|
|
|
_configure(monkeypatch, Client)
|
|
|
|
await github_app.get_github_app_installation_token_with_expiry(
|
|
permissions={"contents": "write"}
|
|
)
|
|
await github_app.get_github_app_installation_token_with_expiry(
|
|
permissions={"contents": "write", "workflows": "write"}
|
|
)
|
|
await github_app.get_github_app_installation_token_with_expiry(
|
|
permissions={"contents": "write"}
|
|
)
|
|
|
|
assert Client.posts == 2
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_installation_token_omits_scope_for_full_installation(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
monkeypatch.setattr(github_app, "GITHUB_APP_ID", "1")
|
|
monkeypatch.setattr(github_app, "GITHUB_APP_PRIVATE_KEY", "key")
|
|
monkeypatch.setattr(github_app, "GITHUB_APP_INSTALLATION_ID", "2")
|
|
monkeypatch.setattr(github_app, "_generate_app_jwt", lambda: "jwt")
|
|
monkeypatch.setattr(github_app.httpx, "AsyncClient", _FakeAsyncClient)
|
|
|
|
await github_app.get_github_app_installation_token_with_expiry()
|
|
|
|
assert _FakeAsyncClient.last_post is not None
|
|
assert _FakeAsyncClient.last_post["json"] is None
|