fix: failure in responses during construct metrics (#4157)

slekkala1 · web-flow · commit ba744d791ad9 · 2025-11-13T14:21:03.000-08:00
# What does this PR do?
Without this we get below in server logs
```
RuntimeError: OpenAI response failed: InferenceRouter._construct_metrics() got an unexpected keyword argument  
         'model_id'          
```
Seems the method signature got update but this callsite was not updated
## Test Plan
CI and test with Sabre (Agent framework integration)
diff --git a/src/llama_stack/core/routers/inference.py b/src/llama_stack/core/routers/inference.py
@@ -417,7 +417,7 @@ async def stream_tokens_and_compute_metrics_openai_chat(
                             prompt_tokens=chunk.usage.prompt_tokens,
                             completion_tokens=chunk.usage.completion_tokens,
                             total_tokens=chunk.usage.total_tokens,
-                            model_id=fully_qualified_model_id,
+                            fully_qualified_model_id=fully_qualified_model_id,
                             provider_id=provider_id,
                         )
                         for metric in metrics:

Original file line number	Diff line number	Diff line change
`@@ -417,7 +417,7 @@ async def stream_tokens_and_compute_metrics_openai_chat(`
`417`	`417`	`prompt_tokens=chunk.usage.prompt_tokens,`
`418`	`418`	`completion_tokens=chunk.usage.completion_tokens,`
`419`	`419`	`total_tokens=chunk.usage.total_tokens,`
`420`		`- model_id=fully_qualified_model_id,`
	`420`	`+ fully_qualified_model_id=fully_qualified_model_id,`
`421`	`421`	`provider_id=provider_id,`
`422`	`422`	`)`
`423`	`423`	`for metric in metrics:`