mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 17:23:15 +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>
138 lines
5.1 KiB
Python
138 lines
5.1 KiB
Python
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
from unittest.mock import AsyncMock
|
|
|
|
import pytest
|
|
|
|
from agent import completion
|
|
|
|
|
|
class _FakeThreads:
|
|
def __init__(self, metadata: dict[str, Any]) -> None:
|
|
self._metadata = metadata
|
|
self.updates: list[dict[str, Any]] = []
|
|
|
|
async def get(self, thread_id: str) -> dict[str, Any]:
|
|
return {"thread_id": thread_id, "metadata": self._metadata}
|
|
|
|
async def update(self, *, thread_id: str, metadata: dict[str, Any]) -> None:
|
|
self.updates.append(metadata)
|
|
|
|
|
|
class _FakeClient:
|
|
def __init__(self, metadata: dict[str, Any]) -> None:
|
|
self.threads = _FakeThreads(metadata)
|
|
|
|
|
|
def _slack_metadata() -> dict[str, Any]:
|
|
return {
|
|
"source": "slack",
|
|
"source_context": {"slack_thread": {"channel_id": "C1", "thread_ts": "123.45"}},
|
|
}
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_error_status_posts_slack_failure_reply(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
client = _FakeClient(_slack_metadata())
|
|
monkeypatch.setattr(completion, "langgraph_client", lambda: client)
|
|
reply = AsyncMock(return_value=True)
|
|
monkeypatch.setattr(completion, "post_slack_thread_reply", reply)
|
|
|
|
result = await completion.handle_run_completion({"thread_id": "t1", "status": "error"})
|
|
|
|
assert result["status"] == "ok"
|
|
reply.assert_awaited_once()
|
|
args = reply.await_args.args
|
|
assert args[0] == "C1"
|
|
assert args[1] == "123.45"
|
|
assert client.threads.updates == [{"failure_reply_posted": True}]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_success_status_is_ignored(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
client = _FakeClient(_slack_metadata())
|
|
monkeypatch.setattr(completion, "langgraph_client", lambda: client)
|
|
reply = AsyncMock(return_value=True)
|
|
monkeypatch.setattr(completion, "post_slack_thread_reply", reply)
|
|
|
|
result = await completion.handle_run_completion({"thread_id": "t1", "status": "success"})
|
|
|
|
assert result["status"] == "ignored"
|
|
reply.assert_not_called()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_idempotent_when_already_replied(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
metadata = _slack_metadata()
|
|
metadata["failure_reply_posted"] = True
|
|
client = _FakeClient(metadata)
|
|
monkeypatch.setattr(completion, "langgraph_client", lambda: client)
|
|
reply = AsyncMock(return_value=True)
|
|
monkeypatch.setattr(completion, "post_slack_thread_reply", reply)
|
|
|
|
result = await completion.handle_run_completion({"thread_id": "t1", "status": "timeout"})
|
|
|
|
assert result["status"] == "ignored"
|
|
reply.assert_not_called()
|
|
assert client.threads.updates == []
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_linear_source_comments_on_issue(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
client = _FakeClient({"source": "linear", "source_context": {"linear_issue": {"id": "iss_1"}}})
|
|
monkeypatch.setattr(completion, "langgraph_client", lambda: client)
|
|
comment = AsyncMock(return_value=True)
|
|
monkeypatch.setattr(completion, "comment_on_linear_issue", comment)
|
|
|
|
result = await completion.handle_run_completion({"thread_id": "t1", "status": "timeout"})
|
|
|
|
assert result["status"] == "ok"
|
|
comment.assert_awaited_once()
|
|
assert comment.await_args.args[0] == "iss_1"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_missing_thread_id_is_ignored() -> None:
|
|
result = await completion.handle_run_completion({"status": "error"})
|
|
assert result["status"] == "ignored"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_no_reply_channel_does_not_flag(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
client = _FakeClient({"source": "schedule"})
|
|
monkeypatch.setattr(completion, "langgraph_client", lambda: client)
|
|
|
|
result = await completion.handle_run_completion({"thread_id": "t1", "status": "error"})
|
|
|
|
assert result["status"] == "ignored"
|
|
assert client.threads.updates == []
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_interrupted_status_is_ignored(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
# Follow-ups use multitask_strategy="interrupt", so an interrupted run is a
|
|
# healthy hand-off, not a failure to report.
|
|
client = _FakeClient(_slack_metadata())
|
|
monkeypatch.setattr(completion, "langgraph_client", lambda: client)
|
|
reply = AsyncMock(return_value=True)
|
|
monkeypatch.setattr(completion, "post_slack_thread_reply", reply)
|
|
|
|
result = await completion.handle_run_completion({"thread_id": "t1", "status": "interrupted"})
|
|
|
|
assert result["status"] == "ignored"
|
|
reply.assert_not_called()
|
|
assert client.threads.updates == []
|
|
|
|
|
|
def test_verify_run_complete_token(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
# No secret configured: fail closed (reject everything).
|
|
monkeypatch.setattr(completion, "RUN_COMPLETE_WEBHOOK_SECRET", None)
|
|
assert completion.verify_run_complete_token(None) is False
|
|
assert completion.verify_run_complete_token("whatever") is False
|
|
|
|
# Secret configured: require an exact match.
|
|
monkeypatch.setattr(completion, "RUN_COMPLETE_WEBHOOK_SECRET", "s3cret")
|
|
assert completion.verify_run_complete_token("s3cret") is True
|
|
assert completion.verify_run_complete_token("wrong") is False
|
|
assert completion.verify_run_complete_token(None) is False
|