test: add tests for model extraction fallback and bump to 7.4.1

- Add 8 tests covering model extraction from response for stored prompts
- Fix utils.py to add 'unknown' fallback for consistency
- Bump version to 7.4.1
- Update CHANGELOG.md

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <[email protected]>

Author: andrewm4894

CHANGELOG.md

@@ -1,3 +1,9 @@
+# 7.4.1 - 2025-12-19
+
+fix: extract model from response for OpenAI stored prompts
+
+When using OpenAI stored prompts, the model is defined in the OpenAI dashboard rather than passed in the API request. This fix adds a fallback to extract the model from the response object when not provided in kwargs, ensuring generations show up with the correct model and enabling cost calculations.
+
 # 7.4.0 - 2025-12-16
 
 feat: Add automatic retries for feature flag requests

posthog/ai/utils.py

@@ -285,7 +285,7 @@ def call_llm_and_track_usage(
 
         event_properties = {
             "$ai_provider": provider,
-            "$ai_model": kwargs.get("model") or getattr(response, "model", None),
+            "$ai_model": kwargs.get("model") or getattr(response, "model", None) or "unknown",
             "$ai_model_parameters": get_model_params(kwargs),
             "$ai_input": with_privacy_mode(
                 ph_client, posthog_privacy_mode, sanitized_messages
@@ -396,7 +396,7 @@ async def call_llm_and_track_usage_async(
 
         event_properties = {
             "$ai_provider": provider,
-            "$ai_model": kwargs.get("model") or getattr(response, "model", None),
+            "$ai_model": kwargs.get("model") or getattr(response, "model", None) or "unknown",
             "$ai_model_parameters": get_model_params(kwargs),
             "$ai_input": with_privacy_mode(
                 ph_client, posthog_privacy_mode, sanitized_messages