Report generation minor fixes (#884)

# What does this PR do?

fixed report generation:
1) do not initialize a new client in report.py - instead get it from
pytest fixture
2) Add "provider" for "safety" and "agents" section
3) add logprobs functionality in "inference" section


## Test Plan

See the regenerated report 



## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.

tests/client-sdk/metadata.py

@@ -20,6 +20,10 @@ INFERENCE_API_CAPA_TEST_MAP = {
             "test_text_chat_completion_with_tool_calling_and_streaming",
             "test_text_chat_completion_with_tool_calling_and_non_streaming",
         ],
+        "log_probs": [
+            "test_completion_log_probs_non_streaming",
+            "test_completion_log_probs_streaming",
+        ],
     },
     "completion": {
         "streaming": ["test_text_completion_streaming"],