fix: retry when model returns empty response after tool execution

[epa-davita]

Bug
Some models (notably Claude, and some Gemini preview models) return an empty content array (parts: []) after processing tool results. ADK's is_final_response() treats this as a valid completed turn because it only checks for the absence of function calls — not the presence of actual content. The agent loop stops and the user sees nothing.

Observed with:

Claude (Opus/Sonnet/Haiku) via AnthropicLlm — after run_shell, computer_use tool results
Gemini preview models — after tool execution with streaming enabled
Example session history showing the bug:

Event 19: agent calls run_shell({"command": "cloudflared --version"})
Event 20: tool responds: {"output": "cloudflared version 2026.3.0", "exit_code": 0}
Event 21: agent responds with parts: [] ← EMPTY, agent loop ends, user sees nothing
Root Cause
In BaseLlmFlow.run_async() (line 757):

if not last_event or last_event.is_final_response() or last_event.partial:
break
And is_final_response() in event.py:

return (
not self.get_function_calls()
and not self.get_function_responses()
and not self.partial
and not self.has_trailing_code_execution_result()
)
An event with parts: [] passes all these checks — no function calls, no function responses, not partial — so is_final_response() returns True and the loop breaks.

Fix
Added a retry mechanism in BaseLlmFlow.run_async():

_has_meaningful_content(event) — helper that checks if an event actually contains content worth showing (non-empty text, function calls, inline data, etc.)
When is_final_response() is True but the event has no meaningful content, the loop continues instead of breaking, re-prompting the model
A maximum retry count (_MAX_EMPTY_RESPONSE_RETRIES = 2) prevents infinite loops if the model keeps returning empty responses
Tests
Added 10 new tests in test_empty_response_retry.py:

_has_meaningful_content tests (7):

test_no_content — None content → not meaningful
test_empty_parts — parts: [] → not meaningful
test_only_empty_text_part — text="" → not meaningful
test_only_whitespace_text_part — text=" \n " → not meaningful
test_non_empty_text — actual text → meaningful
test_function_call — function call → meaningful
test_function_response — function response → meaningful
Integration tests (3):

test_empty_response_retried_then_succeeds — empty response triggers retry, second call succeeds
test_empty_response_stops_after_max_retries — stops after max retries to prevent infinite loop
test_non_empty_response_not_retried — normal responses are not retried
All 10 tests pass. All 356 pre-existing flows/llm_flows/ tests pass.

pytest tests/unittests/flows/llm_flows/test_empty_response_retry.py -v
Closes #3754
Related: #3467, #4090, #3034

Note: This is the same as #4982 but I've fixed the failing unit tests.

🤖 Generated with Claude Code

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[adk-bot]

Response from ADK Triaging Agent

Hello @epa-davita, thank you for submitting this pull request!

This PR is a great fix for the empty model response issue. To help us move forward with reviewing your contribution, please make sure you follow the Contribution Guidelines:

1. Sign the Contributor License Agreement (CLA): It looks like the CLA check has failed. Please visit google/cla to sign or verify your agreement. This is required before we can accept any code contributions.
2. Provide logs/screenshots after the fix: Since this is a bug fix, could you please provide a log or screenshot illustrating the behavior after the fix is applied (e.g., showing the retry log and successful continuation)? This helps reviewers better understand the fix.

Thank you for your contribution to the project!