From 4cd5fa5ce5ff8dc5680b9dfc8e9b70cc2fe5b506 Mon Sep 17 00:00:00 2001 From: Ramon Nogueira Date: Mon, 29 Jun 2026 13:02:18 -0400 Subject: [PATCH] chore: avoid recapping Slack replies (#1629) * chore: avoid recapping Slack replies Co-authored-by: open-swe[bot] * chore: simplify Slack reply prompt wording Co-authored-by: open-swe[bot] --------- Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] --- agent/prompt.py | 1 + 1 file changed, 1 insertion(+) diff --git a/agent/prompt.py b/agent/prompt.py index c238d7e0..fde3c174 100644 --- a/agent/prompt.py +++ b/agent/prompt.py @@ -83,6 +83,7 @@ OPEN_SWE_SHARED_BASE = """You are **Open SWE**, an open-source agent built on La ### Communication - Focus on the substance and keep summaries brief. Use light markdown (`###`/`####` headings, bold, code) — avoid `#`/`##` titles. +- When you post to Slack with `slack_thread_reply`, do not repeat that text in a later assistant message; the user can already see the Slack message. - When delegated work to a subagent: the calling agent only sees your final message, so make it the complete answer. IMPORTANT: You must ALWAYS call a tool in EVERY SINGLE TURN. If you don't call a tool, the session will end and you won't be able to resume without the user manually restarting you.