Sweep: In on_comment.py it's possible that the comment is on a closed PR. If this is the case then we should not fire an event. Add logic to src/api.py to address this.

[sweepai]

Sweep: In on_comment.py it's possible that the comment is on a closed PR. If this is the case then we should not fire an event. Add logic to src/api.py to address this.

[sweep-nightly]

Hey @wwzeng1,

I've started working on the issue you've raised. Here's a quick summary of the plan:

1. I'll add a check in the on_comment.py handler to see if the PR associated with the comment is closed. If it is, we won't fire an event.
2. I'll then modify the webhook function in src/api.py to handle this new logic.

This should prevent unnecessary processing for comments on closed PRs.

Give me a minute!

-Sweep bot

Some code snippets I looked at (click to expand). If some file is missing from here, you can mention the path in the ticket description.

sweep/tests/test_gpt_diff_function.py

Lines 785 to 830 in 3fc8817

	return {"success": False, "reason": "Issue is closed"}
	item_to_react_to = current_issue.get_comment(comment_id) if comment_id else current_issue
	eyes_reaction = item_to_react_to.create_reaction("eyes")
	def comment_reply(message: str):
	current_issue.create_comment(message + "\n\n---\n" + bot_suffix)
	comments = current_issue.get_comments()
	replies_text = ""
	if comment_id:
	replies_text = "\nComments:\n" + "\n".join(
	[
	issue_comment_prompt.format(
	username=comment.user.login,
	reply=comment.body,
	) for comment in comments
	]
	)
	def fetch_file_contents_with_retry():
	retries = 3
	error = None
	for i in range(retries):
	try:
	logger.info(f"Fetching relevant files for the {i}th time...")
	return search_snippets(
	repo,
	f"{title}\n{summary}\n{replies_text}",
	num_files=num_of_snippets_to_query,
	branch=None,
	installation_id=installation_id,
	)
	except Exception as e:
	error = e
	continue
	posthog.capture(
	username, "fetching_failed", properties={"error": error, **metadata}
	)
	raise error
	# update_index.call(
	# repo_full_name,
	# installation_id=installation_id,
	# )
	logger.info("Fetching relevant files...")

sweep/src/handlers/on_ticket.py

Lines 95 to 120 in 3fc8817

	return {"success": False, "reason": "Issue is closed"}
	item_to_react_to = current_issue.get_comment(comment_id) if comment_id else current_issue
	eyes_reaction = item_to_react_to.create_reaction("eyes")
	def comment_reply(message: str):
	current_issue.create_comment(message + "\n\n---\n" + bot_suffix)
	comments = current_issue.get_comments()
	replies_text = ""
	if comment_id:
	replies_text = "\nComments:\n" + "\n".join(
	[
	issue_comment_prompt.format(
	username=comment.user.login,
	reply=comment.body,
	) for comment in comments
	]
	)
	def fetch_file_contents_with_retry():
	retries = 3
	error = None
	for i in range(retries):
	try:
	logger.info(f"Fetching relevant files for the {i}th time...")
	return search_snippets(

sweep/tests/test_gpt_diff_function.py

Lines 315 to 360 in 3fc8817

	118: posthog.capture(username, "success", properties={**metadata})
	119: logger.info("on_comment success")
	120: return {"success": True}
	</body>
	<modify>
	* src/handlers/on_comment.py:
	1. Add a new method in on_comment that uses pygithub to send a simple response to the user.
	</modify>
	Pass in start_line and end_line to the `modify` function.
	Make sure `end_line` covers the code you wish to delete and that `new_code` is properly formatted.
	Also make sure start_line is in ascending order and that the code_edits do not overlap.
	'''
	def test_chat_gpt_call():
	human_message = HumanMessagePrompt(
	repo_name ='',
	repo_description='',
	issue_url='',
	username='',
	title='',
	tree='',
	summary='',
	snippets=[],
	)
	cgpt = ChatGPT.from_system_message_content(human_message=human_message, model="gpt-4"
	)
	response = cgpt.call_openai(model="gpt-4-32k-0613", functions=[modify_file_function], function_name={"name": "modify_file"})
	response = openai.ChatCompletion.create(
	model="gpt-4-32k-0613",
	messages=[
	{
	"role": "system",
	"content": system_message_prompt
	},
	{
	"role": "user",
	"content": first_user_prompt
	},
	],
	functions=modify_file_function,
	function_call={"name": "modify_file"}
	)
	assistant_response = response.choices[0]
	arguments = assistant_response["message"]["function_call"]["arguments"]

sweep/tests/test_generate_new_files.py

Lines 124 to 127 in 3fc8817

	118: logger.info("on_comment success")
	119: return {"success":True}
	120:
	</old_file>"""

sweep/src/api.py

Lines 1 to 227 in 3fc8817

	import time
	from loguru import logger
	import modal
	from pydantic import ValidationError
	from src.handlers.create_pr import create_pr # type: ignore
	from src.handlers.on_ticket import on_ticket
	from src.handlers.on_comment import on_comment
	from src.utils.constants import API_NAME, BOT_TOKEN_NAME, LABEL_COLOR, LABEL_DESCRIPTION, LABEL_NAME, SWEEP_LOGIN
	from src.events import (
	CommentCreatedRequest,
	InstallationCreatedRequest,
	IssueCommentRequest,
	IssueRequest,
	PRRequest,
	ReposAddedRequest,
	)
	from src.utils.event_logger import posthog
	from src.utils.github_utils import get_github_client, index_full_repository
	from fastapi import HTTPException, Request
	stub = modal.Stub(API_NAME)
	image = (
	modal.Image.debian_slim()
	.apt_install("git")
	.pip_install(
	"openai",
	"anthropic",
	"PyGithub",
	"loguru",
	"docarray",
	"backoff",
	"tiktoken",
	"highlight-io",
	"GitPython",
	"posthog",
	"tqdm"
	)
	)
	secrets = [
	modal.Secret.from_name(BOT_TOKEN_NAME),
	modal.Secret.from_name("openai-secret"),
	modal.Secret.from_name("anthropic"),
	modal.Secret.from_name("posthog"),
	modal.Secret.from_name("highlight"),
	]
	FUNCTION_SETTINGS = {
	"image": image,
	"secrets": secrets,
	"timeout": 15 * 60,
	}
	handle_ticket = stub.function(**FUNCTION_SETTINGS)(on_ticket)
	handle_comment = stub.function(**FUNCTION_SETTINGS)(on_comment)
	handle_pr = stub.function(**FUNCTION_SETTINGS)(create_pr)
	@stub.function(**FUNCTION_SETTINGS)
	@modal.web_endpoint(method="POST")
	async def webhook(raw_request: Request):
	"""Handle a webhook request from GitHub."""
	try:
	request_dict = await raw_request.json()
	logger.info(f"Received request: {request_dict.keys()}")
	event = raw_request.headers.get("X-GitHub-Event")
	assert event is not None
	match event, request_dict.get("action", None):
	case "issues", "opened":
	request = IssueRequest(**request_dict)
	issue_title_lower = request.issue.title.lower()
	if issue_title_lower.startswith("sweep") or "sweep:" in issue_title_lower:
	g = get_github_client(request.installation.id)
	repo = g.get_repo(request.repository.full_name)
	labels = repo.get_labels()
	label_names = [label.name for label in labels]
	if LABEL_NAME not in label_names:
	repo.create_label(
	name=LABEL_NAME,
	color=LABEL_COLOR,
	description=LABEL_DESCRIPTION,
	)
	# TODO(sweep): figure out why this is breaking
	# else:
	# label = repo.get_label(LABEL_NAME)
	# label.edit(
	# name=LABEL_NAME,
	# color=LABEL_COLOR,
	# description=LABEL_DESCRIPTION
	# )
	current_issue = repo.get_issue(number=request.issue.number)
	current_issue.add_to_labels(LABEL_NAME)
	case "issues", "labeled":
	request = IssueRequest(**request_dict)
	if request.issue is not None and (
	"sweep" in [label.name.lower() for label in request.issue.labels]
	):
	request.issue.body = request.issue.body or ""
	request.repository.description = (
	request.repository.description or ""
	)
	# Update before we handle the ticket to make sure index is up to date
	# other ways suboptimal
	handle_ticket.spawn(
	request.issue.title,
	request.issue.body,
	request.issue.number,
	request.issue.html_url,
	request.issue.user.login,
	request.repository.full_name,
	request.repository.description,
	request.installation.id,
	)
	case "issue_comment", "created":
	request = IssueCommentRequest(**request_dict)
	if request.issue is not None \
	and "sweep" in [label.name.lower() for label in request.issue.labels] \
	and request.comment.user.type == "User":
	request.issue.body = request.issue.body or ""
	request.repository.description = (
	request.repository.description or ""
	)
	# Update before we handle the ticket to make sure index is up to date
	# other ways suboptimal
	handle_ticket.spawn(
	request.issue.title,
	request.issue.body,
	request.issue.number,
	request.issue.html_url,
	request.issue.user.login,
	request.repository.full_name,
	request.repository.description,
	request.installation.id,
	request.comment.id
	)
	elif request.issue.pull_request and request.issue.user.login == SWEEP_LOGIN and request.comment.user.type == "User": # TODO(sweep): set a limit
	logger.info(f"Handling comment on PR: {request.issue.pull_request}")
	handle_comment.spawn(
	repo_full_name=request.repository.full_name,
	repo_description=request.repository.description,
	comment=request.comment.body,
	pr_path=None,
	pr_line_position=None,
	username=request.comment.user.login,
	installation_id=request.installation.id,
	pr_number=request.issue.number,
	)
	case "pull_request_review_comment", "created":
	request = CommentCreatedRequest(**request_dict)
	if "sweep/" in request.pull_request.head.ref.lower():
	handle_comment.spawn(
	repo_full_name=request.repository.full_name,
	repo_description=request.repository.description,
	comment=request.comment.body,
	pr_path=request.comment.path,
	pr_line_position=request.comment.original_line,
	username=request.comment.user.login,
	installation_id=request.installation.id,
	pr_number=request.pull_request.number,
	)
	# Todo: update index on comments
	case "pull_request_review", "submitted":
	# request = ReviewSubmittedRequest(**request_dict)
	pass
	case "installation_repositories", "added":
	repos_added_request = ReposAddedRequest(**request_dict)
	metadata = {
	"installation_id": repos_added_request.installation.id,
	"repositories": [
	repo.full_name
	for repo in repos_added_request.repositories_added
	],
	}
	posthog.capture("installation_repositories", "started", properties={
	**metadata
	})
	for repo in repos_added_request.repositories_added:
	organization, repo_name = repo.full_name.split("/")
	posthog.capture(
	organization,
	"installed_repository",
	properties={
	"repo_name": repo_name,
	"organization": organization,
	"repo_full_name": repo.full_name
	}
	)
	index_full_repository(
	repo.full_name,
	installation_id=repos_added_request.installation.id,
	)
	case "installation", "created":
	repos_added_request = InstallationCreatedRequest(**request_dict)
	for repo in repos_added_request.repositories:
	index_full_repository(
	repo.full_name,
	installation_id=repos_added_request.installation.id,
	)
	case ("pull_request", "closed"):
	pr_request = PRRequest(**request_dict)
	organization, repo_name = pr_request.repository.full_name.split("/")
	commit_author = pr_request.pull_request.user.login
	merged_by = pr_request.pull_request.merged_by.login
	if SWEEP_LOGIN == commit_author:
	posthog.capture(
	merged_by,
	"merged_sweep_pr",
	properties={
	"repo_name": repo_name,
	"organization": organization,
	"repo_full_name": pr_request.repository.full_name,
	"username": merged_by
	})
	case "ping", None:
	return {"message": "pong"}
	case _:
	logger.info(
	f"Unhandled event: {event} {request_dict.get('action', None)}"
	)
	except ValidationError as e:
	logger.warning(f"Failed to parse request: {e}")
	raise HTTPException(status_code=422, detail="Failed to parse request")
	return {"success": True}

---

I'm a bot that handles simple bugs and feature requests but I might make mistakes. Please be kind!