Handle sync guardrail calls to avoid awaitable error

[steven10a]

Fixes reported bug where using a sync client caused a TypeError: object ChatCompletion can't be used in 'await' expression error when LLM based guardrails are executed.

• Root cause was the guardrail LLM is initialized as the same class as the actual client and we run our guardrails asynchronously.
• Fix: Wrap sync methods with blocking callables in a background executor allowing all guardrails to continue to execute asynchronously

Changes:

• Helper method _invoke_openai_callable added to properly handle sync and async traffic from all api endpoints we support
• All LLM based checks now use the new helper
• Added unit tests to catch this in the future

[Copilot]

Pull Request Overview

This PR fixes a bug where using synchronous OpenAI clients caused TypeError: object ChatCompletion can't be used in 'await' expression errors in LLM-based guardrails. The root cause was that guardrail LLMs were initialized as the same class as the actual client, but guardrails always execute asynchronously. The fix wraps synchronous methods in a background executor to allow uniform async execution.

Key changes:

• Added _invoke_openai_callable helper to handle both sync and async OpenAI SDK methods
• Updated all LLM-based checks to use the new helper for calling OpenAI APIs
• Added unit tests to verify sync client support

Reviewed Changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
src/guardrails/checks/text/llm_base.py	Implements _invoke_openai_callable and _request_chat_completion helpers; updates run_llm to support sync/async clients
src/guardrails/checks/text/prompt_injection_detection.py	Updates _call_prompt_injection_detection_llm to use _invoke_openai_callable
src/guardrails/checks/text/hallucination_detection.py	Updates hallucination_detection to use _invoke_openai_callable
tests/unit/checks/test_llm_base.py	Adds test for sync client support in run_llm
tests/unit/checks/test_prompt_injection_detection.py	Adds test for sync response handling in prompt injection detection

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[Copilot]

The bare except Exception is too broad. Consider catching ImportError specifically since this is handling an optional dependency import.

Suggested change

	exceptException: # pragma: no cover - optional dependency
	exceptImportError: # pragma: no cover - optional dependency

[Copilot]

The unused variable assignment _ = kwargs is unnecessary. If the intention is to indicate kwargs are intentionally unused, this can be omitted as Python allows unused parameters.

[steven10a]

This is just in a test, I think it's fine

[Copilot]

The unused variable assignment _ = kwargs is unnecessary. If the intention is to indicate kwargs are intentionally unused, this can be omitted as Python allows unused parameters.

Suggested change

_ = kwargs

[steven10a]

This is just in a test, I think it's fine

[gabor-openai]

Thank you!