fix: surface Slack thread errors (#1627)

* fix: surface Slack thread errors

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>

* fix: don't set failure_reply_posted on Slack preprocessing errors

The preprocessing error handler was setting failure_reply_posted=True,
the same idempotency flag handle_run_completion checks to suppress
duplicate run-failure replies. Since preprocessing failures happen
before any run exists but the flag persists on the thread, a subsequent
run failure on the same thread would be silently ignored.

The preprocessing handler already posts its own Slack reply, so the
run-completion idempotency flag should not be set here.

---------

Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
(cherry picked from commit bb36448b0b)

agent/completion.py

@@ -19,6 +19,7 @@ import os
 from collections.abc import Awaitable, Callable
 from typing import Any
 
+from .utils.dashboard_links import dashboard_thread_url
 from .utils.github_app import get_github_app_installation_token
 from .utils.github_comments import post_github_comment
 from .utils.linear import comment_on_linear_issue
@@ -63,12 +64,15 @@ def verify_run_complete_token(token: str | None) -> bool:
     return token is not None and hmac.compare_digest(token, secret)
 
 
-def _failure_text(status: str) -> str:
+def _failure_text(status: str, dashboard_url: str | None = None) -> str:
     reason = "timed out" if status == "timeout" else "hit an unexpected error"
-    return (
+    text = (
         f"⚠️ I wasn't able to finish that — the run {reason}. "
         "Send another message and I'll pick it back up."
     )
+    if dashboard_url:
+        text += f" You can view the error in <{dashboard_url}|Open SWE Web>."
+    return text
 
 
 async def _post_failure_reply(
@@ -96,7 +100,8 @@ async def _post_failure_reply(
             thread_ts = slack_thread.get("thread_ts")
             if channel_id and thread_ts:
                 await claim()
-                return await post_slack_thread_reply(channel_id, thread_ts, text)
+                slack_text = _failure_text(status, dashboard_thread_url(thread_id))
+                return await post_slack_thread_reply(channel_id, thread_ts, slack_text)
         return False
 
     if source == "linear":

agent/webhooks/slack.py

@@ -4,6 +4,7 @@ Helpers and constants stay in webapp.py; they are accessed through the module
 object (``webapp.X``) so tests that monkeypatch them keep working.
 """
 
+from datetime import UTC, datetime
 from typing import Any
 
 import httpx
@@ -43,6 +44,84 @@ def _format_slack_thread_section(
 
 async def process_slack_mention(event_data: dict[str, Any], repo_config: dict[str, str]) -> None:
     """Process a Slack app mention by creating a run or queuing a mid-run message."""
+    try:
+        await _process_slack_mention_impl(event_data, repo_config)
+    except Exception:  # noqa: BLE001
+        webapp.logger.exception("Unexpected error while processing Slack mention")
+        await _notify_slack_processing_error(event_data, repo_config)
+
+
+async def _notify_slack_processing_error(
+    event_data: dict[str, Any], repo_config: dict[str, str]
+) -> None:
+    channel_id = event_data.get("channel_id", "")
+    thread_ts = event_data.get("thread_ts", "")
+    event_ts = event_data.get("event_ts", "")
+    user_id = event_data.get("user_id", "")
+    text = event_data.get("text", "")
+    bot_user_id = event_data.get("bot_user_id", "")
+    if not channel_id or not thread_ts:
+        return
+
+    thread_id = webapp.generate_thread_id_from_slack_thread(channel_id, thread_ts)
+    try:
+        clean_text = (
+            webapp.strip_bot_mention(text, bot_user_id, bot_username=webapp.SLACK_BOT_USERNAME)
+            or "Slack request"
+        )
+        await webapp.upsert_agent_thread_owner_metadata(
+            thread_id,
+            source="slack",
+            repo_config=repo_config,
+            title=clean_text,
+            source_context={
+                "slack_thread": {
+                    "channel_id": channel_id,
+                    "thread_ts": thread_ts,
+                    "triggering_user_id": user_id,
+                    "triggering_event_ts": event_ts,
+                }
+            },
+        )
+    except Exception:  # noqa: BLE001
+        webapp.logger.warning(
+            "Could not persist Slack error metadata for thread %s", thread_id, exc_info=True
+        )
+
+    try:
+        await webapp.get_client(url=webapp.LANGGRAPH_URL).threads.update(
+            thread_id=thread_id,
+            metadata={
+                "latest_run_status": "error",
+                "updated_at_ms": int(datetime.now(UTC).timestamp() * 1000),
+            },
+        )
+    except Exception:  # noqa: BLE001
+        webapp.logger.warning("Could not mark Slack thread %s as errored", thread_id, exc_info=True)
+
+    try:
+        await webapp.set_slack_assistant_status(channel_id, thread_ts, status="")
+    except Exception:  # noqa: BLE001
+        webapp.logger.debug("Could not clear Slack assistant status", exc_info=True)
+
+    dashboard_url = webapp.dashboard_thread_url(thread_id)
+    message = (
+        "⚠️ I hit an unexpected error while handling this Slack thread. "
+        "Send another message and I'll try again."
+    )
+    if dashboard_url:
+        message += f" You can view the error in <{dashboard_url}|Open SWE Web>."
+    try:
+        await webapp.post_slack_thread_reply(channel_id, thread_ts, message)
+    except Exception:  # noqa: BLE001
+        webapp.logger.warning(
+            "Could not post Slack error notification for thread %s", thread_id, exc_info=True
+        )
+
+
+async def _process_slack_mention_impl(
+    event_data: dict[str, Any], repo_config: dict[str, str]
+) -> None:
     channel_id = event_data.get("channel_id", "")
     thread_ts = event_data.get("thread_ts", "")
     event_ts = event_data.get("event_ts", "")

tests/test_completion_webhook.py

@@ -38,6 +38,9 @@ async def test_error_status_posts_slack_failure_reply(monkeypatch: pytest.Monkey
     monkeypatch.setattr(completion, "langgraph_client", lambda: client)
     reply = AsyncMock(return_value=True)
     monkeypatch.setattr(completion, "post_slack_thread_reply", reply)
+    monkeypatch.setattr(
+        completion, "dashboard_thread_url", lambda thread_id: f"https://ui/{thread_id}"
+    )
 
     result = await completion.handle_run_completion({"thread_id": "t1", "status": "error"})
 
@@ -46,6 +49,7 @@ async def test_error_status_posts_slack_failure_reply(monkeypatch: pytest.Monkey
     args = reply.await_args.args
     assert args[0] == "C1"
     assert args[1] == "123.45"
+    assert "<https://ui/t1|Open SWE Web>" in args[2]
     assert client.threads.updates == [{"failure_reply_posted": True}]
 
 

tests/test_slack_webhook_errors.py

@@ -0,0 +1,71 @@
+from typing import Any
+from unittest.mock import AsyncMock
+
+import pytest
+
+from agent.webhooks import slack as slack_webhook
+
+
+class _FakeThreads:
+    def __init__(self) -> None:
+        self.updates: list[dict[str, Any]] = []
+
+    async def update(self, *, thread_id: str, metadata: dict[str, Any]) -> None:
+        self.updates.append({"thread_id": thread_id, "metadata": metadata})
+
+
+class _FakeClient:
+    def __init__(self) -> None:
+        self.threads = _FakeThreads()
+
+
+@pytest.mark.asyncio
+async def test_slack_processing_error_posts_dashboard_link(
+    monkeypatch: pytest.MonkeyPatch,
+) -> None:
+    async def fail_processing(event_data: dict[str, Any], repo_config: dict[str, str]) -> None:
+        raise RuntimeError("boom")
+
+    client = _FakeClient()
+    upsert = AsyncMock()
+    set_status = AsyncMock()
+    post_reply = AsyncMock(return_value=True)
+
+    monkeypatch.setattr(slack_webhook, "_process_slack_mention_impl", fail_processing)
+    monkeypatch.setattr(
+        slack_webhook.webapp, "generate_thread_id_from_slack_thread", lambda *_: "t1"
+    )
+    monkeypatch.setattr(
+        slack_webhook.webapp, "strip_bot_mention", lambda text, *_args, **_kwargs: text
+    )
+    monkeypatch.setattr(slack_webhook.webapp, "upsert_agent_thread_owner_metadata", upsert)
+    monkeypatch.setattr(slack_webhook.webapp, "get_client", lambda *, url: client)
+    monkeypatch.setattr(slack_webhook.webapp, "set_slack_assistant_status", set_status)
+    monkeypatch.setattr(
+        slack_webhook.webapp, "dashboard_thread_url", lambda thread_id: f"https://ui/{thread_id}"
+    )
+    monkeypatch.setattr(slack_webhook.webapp, "post_slack_thread_reply", post_reply)
+
+    await slack_webhook.process_slack_mention(
+        {
+            "channel_id": "C1",
+            "thread_ts": "123.45",
+            "event_ts": "123.45",
+            "user_id": "U1",
+            "text": "help",
+            "bot_user_id": "BOT",
+        },
+        {"owner": "langchain-ai", "name": "open-swe"},
+    )
+
+    upsert.assert_awaited_once()
+    assert len(client.threads.updates) == 1
+    update = client.threads.updates[0]
+    assert update["thread_id"] == "t1"
+    assert update["metadata"]["latest_run_status"] == "error"
+    assert "failure_reply_posted" not in update["metadata"]
+    assert isinstance(update["metadata"]["updated_at_ms"], int)
+    set_status.assert_awaited_once_with("C1", "123.45", status="")
+    post_reply.assert_awaited_once()
+    assert post_reply.await_args.args[:2] == ("C1", "123.45")
+    assert "<https://ui/t1|Open SWE Web>" in post_reply.await_args.args[2]