refactor: improve multimodal file handling architecture

Browse Source

- Make crewai_files an optional dependency with graceful fallbacks
- Move file formatting from executor to LLM layer (_process_message_files)
- Add files field to LLMMessage type for cleaner message passing
- Add cache_control to Anthropic content blocks for prompt caching
- Clean up formatters: static methods for OpenAI/Gemini, proper error handling
- Remove unused ContentFormatter protocol
- Move test fixtures to lib/crewai-files/tests/fixtures
- Add Azure and Bedrock multimodal integration tests
- Fix mypy errors in crew_agent_executor.py

...

This commit is contained in:

Greyson LaLonde

2026-01-22 21:55:10 -05:00

parent dc015b14f9

commit a1cbb2f4e2

31 changed files with 320 additions and 1278 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

105

lib/crewai/tests/cassettes/llms/TestAnthropicMultimodalIntegration.test_describe_image.yaml

File diff suppressed because one or more lines are too long