feat(llma): add Gemini async

CHANGELOG.md

@@ -1,3 +1,7 @@
+# 7.1.0 - 2025-11-26
+
+Add support for the async version of Gemini.
+
 # 7.0.2 - 2025-11-18
 
 Add support for Python 3.14.

posthog/ai/gemini/__init__.py

@@ -1,4 +1,5 @@
 from .gemini import Client
+from .gemini_async import AsyncClient
 from .gemini_converter import (
     format_gemini_input,
     format_gemini_response,
@@ -9,12 +10,14 @@
 # Create a genai-like module for perfect drop-in replacement
 class _GenAI:
     Client = Client
+    AsyncClient = AsyncClient
 
 
 genai = _GenAI()
 
 __all__ = [
     "Client",
+    "AsyncClient",
     "genai",
     "format_gemini_input",
     "format_gemini_response",

posthog/ai/gemini/gemini.py

@@ -304,7 +304,7 @@ def _generate_content_streaming(
 
         def generator():
             nonlocal usage_stats
-            nonlocal accumulated_content  # noqa: F824
+            nonlocal accumulated_content
             try:
                 for chunk in response:
                     # Extract usage stats from chunk