mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 18:33:15 +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>
171 lines
5.5 KiB
Python
171 lines
5.5 KiB
Python
from __future__ import annotations
|
|
|
|
import importlib
|
|
from typing import Any
|
|
|
|
import pytest
|
|
|
|
slack_reply_tool = importlib.import_module("agent.tools.slack_thread_reply")
|
|
|
|
|
|
def _config() -> dict[str, Any]:
|
|
return {
|
|
"configurable": {
|
|
"slack_thread": {
|
|
"channel_id": "C1",
|
|
"thread_ts": "1.0",
|
|
}
|
|
}
|
|
}
|
|
|
|
|
|
async def test_slack_thread_reply_returns_structured_error_for_msg_too_long(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
async def fake_post_and_store_mapping(
|
|
channel_id: str,
|
|
thread_ts: str,
|
|
message: str,
|
|
*,
|
|
blocks: list[dict[str, Any]] | None = None,
|
|
) -> tuple[str | None, str | None]:
|
|
return None, "msg_too_long"
|
|
|
|
monkeypatch.setattr(slack_reply_tool, "get_config", _config)
|
|
monkeypatch.setattr(slack_reply_tool, "_post_and_store_mapping", fake_post_and_store_mapping)
|
|
|
|
result = await slack_reply_tool.slack_thread_reply("hello")
|
|
|
|
assert result == {
|
|
"success": False,
|
|
"error": "msg_too_long",
|
|
"slack_error": "msg_too_long",
|
|
"message_chars": 5,
|
|
"hint": "Slack rejected the message as too long; retry with a shorter message.",
|
|
}
|
|
|
|
|
|
@pytest.mark.parametrize("slack_error", ["channel_not_found", "not_in_channel"])
|
|
async def test_slack_thread_reply_hints_not_to_retry_channel_errors(
|
|
slack_error: str,
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
async def fake_post_and_store_mapping(
|
|
channel_id: str,
|
|
thread_ts: str,
|
|
message: str,
|
|
*,
|
|
blocks: list[dict[str, Any]] | None = None,
|
|
) -> tuple[str | None, str | None]:
|
|
return None, slack_error
|
|
|
|
monkeypatch.setattr(slack_reply_tool, "get_config", _config)
|
|
monkeypatch.setattr(slack_reply_tool, "_post_and_store_mapping", fake_post_and_store_mapping)
|
|
|
|
result = await slack_reply_tool.slack_thread_reply("hello")
|
|
|
|
assert result["success"] is False
|
|
assert result["error"] == slack_error
|
|
assert result["slack_error"] == slack_error
|
|
assert result["message_chars"] == 5
|
|
assert "do not retry" in result["hint"]
|
|
assert "trace output" in result["hint"]
|
|
|
|
|
|
async def test_slack_thread_reply_rate_limited_hint_includes_retry_after(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
async def fake_post_and_store_mapping(
|
|
channel_id: str,
|
|
thread_ts: str,
|
|
message: str,
|
|
*,
|
|
blocks: list[dict[str, Any]] | None = None,
|
|
) -> tuple[str | None, str | None]:
|
|
return None, "rate_limited: 30"
|
|
|
|
monkeypatch.setattr(slack_reply_tool, "get_config", _config)
|
|
monkeypatch.setattr(slack_reply_tool, "_post_and_store_mapping", fake_post_and_store_mapping)
|
|
|
|
result = await slack_reply_tool.slack_thread_reply("hello")
|
|
|
|
assert result["success"] is False
|
|
assert result["error"] == "rate_limited: 30"
|
|
assert result["slack_error"] == "rate_limited: 30"
|
|
assert "30s" in result["hint"]
|
|
assert "wait" in result["hint"]
|
|
|
|
|
|
async def test_slack_thread_reply_rate_limited_hint_without_retry_after(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
async def fake_post_and_store_mapping(
|
|
channel_id: str,
|
|
thread_ts: str,
|
|
message: str,
|
|
*,
|
|
blocks: list[dict[str, Any]] | None = None,
|
|
) -> tuple[str | None, str | None]:
|
|
return None, "rate_limited"
|
|
|
|
monkeypatch.setattr(slack_reply_tool, "get_config", _config)
|
|
monkeypatch.setattr(slack_reply_tool, "_post_and_store_mapping", fake_post_and_store_mapping)
|
|
|
|
result = await slack_reply_tool.slack_thread_reply("hello")
|
|
|
|
assert result["success"] is False
|
|
assert result["slack_error"] == "rate_limited"
|
|
assert "wait" in result["hint"]
|
|
|
|
|
|
async def test_slack_thread_reply_uses_post_failed_without_slack_error(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
async def fake_post_and_store_mapping(
|
|
channel_id: str,
|
|
thread_ts: str,
|
|
message: str,
|
|
*,
|
|
blocks: list[dict[str, Any]] | None = None,
|
|
) -> tuple[str | None, str | None]:
|
|
return None, None
|
|
|
|
monkeypatch.setattr(slack_reply_tool, "get_config", _config)
|
|
monkeypatch.setattr(slack_reply_tool, "_post_and_store_mapping", fake_post_and_store_mapping)
|
|
|
|
result = await slack_reply_tool.slack_thread_reply("hello")
|
|
|
|
assert result["success"] is False
|
|
assert result["error"] == "post failed"
|
|
assert result["slack_error"] is None
|
|
assert result["message_chars"] == 5
|
|
|
|
|
|
async def test_slack_thread_reply_builds_option_blocks(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
captured: dict[str, Any] = {}
|
|
|
|
async def fake_post_and_store_mapping(
|
|
channel_id: str,
|
|
thread_ts: str,
|
|
message: str,
|
|
*,
|
|
blocks: list[dict[str, Any]] | None = None,
|
|
) -> tuple[str | None, str | None]:
|
|
captured.update(
|
|
{"channel_id": channel_id, "thread_ts": thread_ts, "message": message, "blocks": blocks}
|
|
)
|
|
return "2.0", None
|
|
|
|
monkeypatch.setattr(slack_reply_tool, "get_config", _config)
|
|
monkeypatch.setattr(slack_reply_tool, "_post_and_store_mapping", fake_post_and_store_mapping)
|
|
|
|
result = await slack_reply_tool.slack_thread_reply("Pick one", options=["A", "B"])
|
|
|
|
assert result == {"success": True}
|
|
assert captured["channel_id"] == "C1"
|
|
assert captured["thread_ts"] == "1.0"
|
|
assert captured["message"] == "Pick one"
|
|
actions = captured["blocks"][1]
|
|
assert actions["type"] == "actions"
|
|
assert [button["text"]["text"] for button in actions["elements"]] == ["A", "B"]
|
|
assert actions["elements"][0]["action_id"] == "open_swe_option_select"
|