Devin AI 3bfa1c6559 Fix issue #3454: Add proactive context length checking to prevent empty LLM responses ...

- Add _check_context_length_before_call() method to CrewAgentExecutor
- Proactively check estimated token count before LLM calls in _invoke_loop
- Use character-based estimation (chars / 4) to approximate token count
- Call existing _handle_context_length() when context window would be exceeded
- Add comprehensive tests covering proactive handling and token estimation
- Prevents empty responses from providers like DeepInfra that don't throw exceptions

Co-Authored-By: João <joao@crewai.com>

2025-09-05 16:05:35 +00:00

52 KiB

Raw Blame History

View Raw