[devin-ai-integration]

Summary

Closes the code-scan gap where handle_tool_call / add_responded_tool_calls — the multi-turn tool-use wire formatting for all three providers — was only exercised by @pytest.mark.pricy tests that CI (pytest -m 'not pricy') never runs.

Adds 13 non-pricy unit tests in tests/llm/test_response_api.py that build a ToolCalls from mocked raw calls (mirroring what each _parse_tool_calls produces) and assert the exact dicts each builder emits:

• OpenAIResponseAPIMessageBuilder: function_call → {"type": "function_call_output", "call_id", "output": <str>}; computer_call → {"type": "computer_call_output", "call_id", "output": {"type": "input_image", "image_url"}}; raw response output items are preserved ahead of the responses, including the multi-call ordering case.
• AnthropicAPIMessageBuilder: assistant tool_use block followed by a user message whose content is a list of {"type": "tool_result", "tool_use_id", "content": <str>}.
• OpenAIChatCompletionAPIMessageBuilder: raw assistant message followed by {"name", "role": "tool", "tool_call_id", "content"}.

Also covers the guard rails that previously had no CI assertion: image response in a function call, text response in a computer call, all_responses_set False in add_responded_tool_calls, and prepare_message() on a "tool" builder with no responded_tool_calls (raises ValueError).

No production code changed.

Devin-Org: engineering

Link to Devin session: https://app.devin.ai/sessions/8d237cdb781b415ead9ebef85e7b15ae
Open in Devin Desktop: https://app.devin.ai/desktop/session/8d237cdb781b415ead9ebef85e7b15ae?variant=devin

[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, CI, and merge conflict monitoring