fix: guard against empty/filtered LLM responses in get_first_message_content

[qizwiz]

What

Add null checks in api/openai_client.py and api/azureai_client.py before accessing choices[0].message.content in get_first_message_content.

Why

Two crash vectors exist:

1. IndexError — when choices is empty (network interruption, provider edge cases returning HTTP 200 with empty body)
2. AttributeError — when choices[0].message is None. Observed on Gemini via OpenAI-compatible endpoint on PROHIBITED_CONTENT (HTTP 200 with message: null)

Fix

if not completion.choices or completion.choices[0].message is None:
    raise ValueError("LLM returned empty or filtered response")
return completion.choices[0].message.content

No behaviour change for well-formed responses.

[gemini-code-assist]

Code Review

This pull request introduces validation checks in the get_first_message_content function for both Azure and OpenAI clients to handle empty or null responses from the LLM. The reviewer recommended extending these checks to include a validation for message.content being None. This ensures the function consistently returns a string as per its type hint, preventing potential errors when responses are filtered or contain non-textual data.

[gemini-code-assist]

The check should also include a validation for completion.choices[0].message.content. In some scenarios (such as content filtering or when the model returns a tool call instead of text), the message object might exist but its content field can be None. Since this function is type-hinted to return a str, returning None would violate the contract and likely cause errors in downstream components that expect a string. Adding this check ensures that we only proceed when actual text content is available.

Suggested change

	if not completion.choices or completion.choices[0].message is None:
	raise ValueError("LLM returned empty or filtered response")
	if not completion.choices or completion.choices[0].message is None or completion.choices[0].message.content is None:
	raise ValueError("LLM returned empty or filtered response")

[gemini-code-assist]

Similar to the Azure client, the check here should also validate that completion.choices[0].message.content is not None. This prevents the function from returning None when a str is expected, which can happen if the response is filtered or contains non-textual data. This is especially important given the PR's goal of guarding against "filtered" responses.

Suggested change

	if not completion.choices or completion.choices[0].message is None:
	raise ValueError("LLM returned empty or filtered response")
	if not completion.choices or completion.choices[0].message is None or completion.choices[0].message.content is None:
	raise ValueError("LLM returned empty or filtered response")