fix: prioritize tool calls over text when available_functions is None

[alvinttang]

Summary

Fixes #4788 - Native tool calls are discarded if LLM returns a text response alongside them.

When an LLM (e.g., Anthropic via OpenRouter/Bedrock) returns both a text response and tool calls in the same message, the previous logic in _handle_non_streaming_response returned the text response instead of the tool calls when available_functions was None. This caused the CrewAgentExecutor to treat the text as a final answer, silently discarding the tool calls that should have been executed.

Root cause

The condition at step 5 was:

if (not tool_calls or not available_functions) and text_response:
    return text_response

When tool_calls is truthy (tool calls exist), not available_functions is True (executor passes None), and text_response is truthy, this condition matches and returns the text — never reaching step 6 which would return the tool calls.

Fix

Swap the order of steps 5 and 6 so that tool calls are returned first when available_functions is None, before falling back to text response. The new step 6 now only returns text when there are genuinely no tool calls (not tool_calls).

This is a minimal, focused change (4 lines of logic) that preserves all existing behavior for:

• Responses with only text (no tool calls) — still returns text
• Responses with tool calls and available_functions provided — still executes tools
• Responses with no text and no tool calls — falls through to step 8

Test plan

• Verify LLM responses with both text + tool calls return tool calls when available_functions=None
• Verify text-only responses still work correctly
• Verify tool execution still works when available_functions is provided
• Run existing test suite: pytest lib/crewai/tests/test_llm.py

🤖 Generated with Claude Code

---

Note

Medium Risk
Changes core LLM response selection logic and could affect downstream callers that previously received text in mixed text+tool responses, though the change is small and narrowly scoped to the available_functions=None case.

Overview
Fixes non-streaming LLM response handling so that when a provider returns both tool_calls and text in the same message and available_functions is None, the method returns the tool_calls instead of prematurely treating the text as the final answer.

This reorders the decision logic in _handle_non_streaming_response to give tool calls priority (enabling executors to run native tools) while preserving the existing paths for text-only responses and for executing tools when available_functions is provided.

^{Written by Cursor Bugbot for commit 10cdfd6. This will update automatically on new commits. Configure here.}

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

[cursor]

Async method not updated with same fix

High Severity

The fix to prioritize tool calls over text when available_functions is None was only applied to _handle_non_streaming_response but not to its async counterpart _ahandle_non_streaming_response. The async method at line 1371 still has the original buggy condition if (not tool_calls or not available_functions) and text_response:, which means the exact same bug — discarding tool calls when the LLM returns both text and tool calls — still occurs for all async code paths.

Additional Locations (1)

• lib/crewai/src/crewai/llm.py#L1370-L1384

 

[alvinttang]

Closing — superseded by #4872 which also fixes the async path.