mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 17:23:15 +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>
78 lines
2.7 KiB
Python
78 lines
2.7 KiB
Python
"""Shared LangGraph thread helpers for webhooks and the dashboard."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
import os
|
|
from typing import Any
|
|
|
|
from langgraph_sdk import get_client
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
MAX_QUEUED_MESSAGES = 100
|
|
|
|
|
|
def langgraph_url() -> str:
|
|
return os.environ.get("LANGGRAPH_URL") or os.environ.get(
|
|
"LANGGRAPH_URL_PROD", "http://localhost:2024"
|
|
)
|
|
|
|
|
|
def langgraph_client():
|
|
return get_client(url=langgraph_url())
|
|
|
|
|
|
async def get_thread_active_status(thread_id: str) -> bool | None:
|
|
"""Return whether the thread is active, or None when status cannot be determined."""
|
|
try:
|
|
thread = await langgraph_client().threads.get(thread_id)
|
|
status = thread.get("status", "idle") if isinstance(thread, dict) else "idle"
|
|
logger.info("Thread %s status check: status=%s", thread_id, status)
|
|
return status == "busy"
|
|
except Exception as exc: # noqa: BLE001
|
|
logger.warning("Failed to get thread status for %s: %s", thread_id, exc)
|
|
return None
|
|
|
|
|
|
async def is_thread_active(thread_id: str) -> bool:
|
|
"""Return whether the thread currently has a running run."""
|
|
return await get_thread_active_status(thread_id) is True
|
|
|
|
|
|
async def queue_message_for_thread(
|
|
thread_id: str, message_content: str | list[dict[str, Any]] | dict[str, Any]
|
|
) -> bool:
|
|
"""Queue a follow-up message for a busy thread (FIFO store namespace)."""
|
|
client = langgraph_client()
|
|
try:
|
|
namespace = ("queue", thread_id)
|
|
key = "pending_messages"
|
|
new_message = {"content": message_content}
|
|
|
|
existing_messages: list[dict[str, Any]] = []
|
|
try:
|
|
existing_item = await client.store.get_item(namespace, key)
|
|
if existing_item and existing_item.get("value"):
|
|
existing_messages = existing_item["value"].get("messages", [])
|
|
except Exception: # noqa: BLE001
|
|
logger.debug("No existing queued messages for thread %s", thread_id)
|
|
|
|
existing_messages.append(new_message)
|
|
if len(existing_messages) > MAX_QUEUED_MESSAGES:
|
|
existing_messages = existing_messages[-MAX_QUEUED_MESSAGES:]
|
|
logger.warning(
|
|
"Thread %s queue capped at %d messages (dropped oldest)",
|
|
thread_id,
|
|
MAX_QUEUED_MESSAGES,
|
|
)
|
|
await client.store.put_item(namespace, key, {"messages": existing_messages})
|
|
logger.info(
|
|
"Queued message for thread %s (total queued: %d)",
|
|
thread_id,
|
|
len(existing_messages),
|
|
)
|
|
return True
|
|
except Exception:
|
|
logger.exception("Failed to queue message for thread %s", thread_id)
|
|
return False
|