Fix #3715: Remove unwanted LLM stream chunk printing to stdout

[devin-ai-integration]

Fix #3715: Remove unwanted LLM stream chunk printing to stdout

Summary

Removed the print() statement in event_listener.py that was causing all LLM streaming chunks to be printed directly to stdout. This addresses issue #3715 where users reported seeing unwanted LLM output text in their console.

Changes:

• Removed print(content, end="", flush=True) from the on_llm_stream_chunk event handler in src/crewai/events/event_listener.py
• Added test test_llm_stream_chunks_do_not_print_to_stdout to verify chunks are emitted as events but not printed to stdout

The streaming chunks are still collected in the internal text_stream and emitted as LLMStreamChunkEvent events for proper event-driven handling - they're just no longer printed directly to stdout.

Review & Testing Checklist for Human

• Test with actual LLM streaming: Run a crew with stream=True on the LLM and verify that streaming still works correctly but chunks aren't printed to stdout
• Verify event handlers still receive chunks: Confirm that any custom event handlers listening for LLMStreamChunkEvent still receive the chunks properly
• Check console output: Ensure that final agent outputs and task results are still displayed correctly (only the streaming chunks should be suppressed)

Recommended Test Plan

1. Create a simple crew with streaming enabled: llm = LLM(model="gpt-4o", stream=True)
2. Run the crew and observe console output - you should see normal agent/task messages but NOT individual streaming chunks
3. Add a custom event handler for LLMStreamChunkEvent and verify it still receives chunks

Notes

• The fix is minimal and low-risk - it's a single line removal
• The test manually emits events rather than calling a real LLM (to avoid network dependencies in unit tests)
• I couldn't fully run the existing VCR-based streaming tests due to cassette/network issues, so end-to-end verification with actual streaming is recommended
• Link to Devin run: https://app.devin.ai/sessions/905c78a2d39a42ee956423514c83194f
• Requested by: João (joao@crewai.com)

[devin-ai-integration]

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

• Address comments on this PR. Add '(aside)' to your comment to have me ignore it.
• Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

• Disable automatic comment and CI monitoring