mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 23:13:15 +00:00
98b824bd54
* feat: add size caps for PR diff, fetch_url, Slack threads, pagination, message queue Per-source byte/token caps with explicit truncation markers to prevent unbounded payloads from blowing up LLM context/memory. - reviewer_diff.py: cap PR diff at 200K chars with head+tail truncation - fetch_url.py: cap markdownify output at 100K chars - slack.py: cap thread message fetch at 500 messages - github_comments.py: cap _fetch_paginated at 50 pages - thread_ops.py: cap queued messages at 100 (drop oldest) Closes OPE-51 Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: compute diff line set from full diff, keep most recent Slack messages Address PR review comments: 1. Truncated diffs rejected valid findings: fetch_pr_diff now returns the full diff; truncate_diff is called separately in reviewer.py so the line set used for add_finding/publish_review validation is computed from the complete diff, not the truncated prompt text. 2. Slack cap dropped recent thread context: fetch_slack_thread_messages now keeps the most recent SLACK_THREAD_MAX_MESSAGES messages (was keeping the oldest). The tool surfaces a truncation marker in the formatted output so the LLM knows the thread was truncated. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
63 lines
2.2 KiB
Python
63 lines
2.2 KiB
Python
import asyncio
|
|
from typing import Any
|
|
|
|
from ..utils.slack import (
|
|
SLACK_THREAD_MAX_MESSAGES,
|
|
fetch_slack_thread_messages,
|
|
format_slack_messages_for_prompt,
|
|
get_slack_user_names,
|
|
)
|
|
|
|
|
|
async def _fetch_and_format(channel_id: str, message_ts: str) -> dict[str, Any]:
|
|
"""Fetch thread messages and resolve author names."""
|
|
messages = await fetch_slack_thread_messages(channel_id, message_ts)
|
|
if not messages:
|
|
return {"success": False, "messages": []}
|
|
|
|
user_ids = [
|
|
msg.get("user") for msg in messages if isinstance(msg.get("user"), str) and msg.get("user")
|
|
]
|
|
user_names = await get_slack_user_names(user_ids) if user_ids else {}
|
|
|
|
truncated = len(messages) >= SLACK_THREAD_MAX_MESSAGES
|
|
formatted = format_slack_messages_for_prompt(messages, user_names)
|
|
if truncated:
|
|
formatted = (
|
|
f"[thread truncated — showing most recent {len(messages)} messages]\n{formatted}"
|
|
)
|
|
return {
|
|
"success": True,
|
|
"formatted": formatted,
|
|
"count": len(messages),
|
|
"truncated": truncated,
|
|
}
|
|
|
|
|
|
def slack_read_thread_messages(channel_id: str, message_ts: str) -> dict[str, Any]:
|
|
"""Read messages from a Slack thread.
|
|
|
|
Use this tool to read messages from a Slack channel or thread.
|
|
Provide the channel_id and message_ts (thread timestamp) to fetch all
|
|
messages in that thread.
|
|
|
|
If you encounter a Slack message URL like
|
|
https://workspace.slack.com/archives/C0AME1J0/p1776281321762829
|
|
you can extract the channel_id (C0AME1J0) and convert the timestamp
|
|
by inserting a dot 6 digits from the end (1776281321.762829).
|
|
|
|
Returns formatted thread messages with author names."""
|
|
if not channel_id or not channel_id.strip():
|
|
return {"success": False, "error": "channel_id is required"}
|
|
if not message_ts or not message_ts.strip():
|
|
return {"success": False, "error": "message_ts is required"}
|
|
|
|
result = asyncio.run(_fetch_and_format(channel_id.strip(), message_ts.strip()))
|
|
if not result.get("success"):
|
|
return {
|
|
"success": False,
|
|
"error": "Could not fetch thread messages. The bot may not have access to "
|
|
"that channel, or the message may have been deleted.",
|
|
}
|
|
|
|
return result
|