Skip to content

Trim --- Metadata --- from message #256

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jun 6, 2025
Merged

Trim --- Metadata --- from message #256

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cb6e889
Trim --- Metadata --- from message
davek-ai Jun 6, 2025
8bf37ba
Merge branch 'staging' into metadata
human058382928 Jun 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 12 additions & 4 deletions services/runner/tasks/tweet_task.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -230,6 +230,12 @@ async def _validate_message(
dao_id=message.dao_id if hasattr(message, "dao_id") else None,
)

def _strip_metadata_section(self, text: str) -> str:
"""Remove metadata section starting with '--- Metadata ---' to the end of the text."""
metadata_pattern = r"--- Metadata ---.*$"
# Remove from '--- Metadata ---' to the end, including the marker
return re.sub(metadata_pattern, "", text, flags=re.DOTALL).rstrip()

async def _process_tweet_message(
self, message: QueueMessage
) -> TweetProcessingResult:
Expand All @@ -250,16 +256,18 @@ async def _process_tweet_message(

# Extract tweet text directly from the message format
original_text = message.message["message"]
# Strip metadata section if present
clean_text = self._strip_metadata_section(original_text)
logger.info(f"Sending tweet for DAO {message.dao_id}")
logger.debug(f"Tweet content: {original_text}")
logger.debug(f"Tweet content: {clean_text}")

# Look for image URLs in the text
image_urls = extract_image_urls(original_text)
image_urls = extract_image_urls(clean_text)
image_url = image_urls[0] if image_urls else None
tweet_text = original_text
tweet_text = clean_text

if image_url:
tweet_text = re.sub(re.escape(image_url), "", original_text).strip()
tweet_text = re.sub(re.escape(image_url), "", clean_text).strip()
tweet_text = re.sub(r"\s+", " ", tweet_text)

# Split tweet text if necessary
Expand Down