feat(eval api): (2.1/n) fix resolver for benchmark routing table + fix precommit (#1691)

# What does this PR do?
- fixes routing table so that `llama stack run` works
- fixes pre-commit
- one of many fixes to address implementation fix

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
```
llama stack run
```

[//]: # (## Documentation)

llama_stack/templates/open-benchmark/open_benchmark.py

@@ -214,27 +214,27 @@ def get_distribution_template() -> DistributionTemplate:
         BenchmarkInput(
             benchmark_id="meta-reference-simpleqa",
             dataset_id="simpleqa",
-            scoring_functions=["llm-as-judge::405b-simpleqa"],
+            grader_ids=["llm-as-judge::405b-simpleqa"],
         ),
         BenchmarkInput(
             benchmark_id="meta-reference-mmlu-cot",
             dataset_id="mmlu_cot",
-            scoring_functions=["basic::regex_parser_multiple_choice_answer"],
+            grader_ids=["basic::regex_parser_multiple_choice_answer"],
         ),
         BenchmarkInput(
             benchmark_id="meta-reference-gpqa-cot",
             dataset_id="gpqa_cot",
-            scoring_functions=["basic::regex_parser_multiple_choice_answer"],
+            grader_ids=["basic::regex_parser_multiple_choice_answer"],
         ),
         BenchmarkInput(
             benchmark_id="meta-reference-math-500",
             dataset_id="math_500",
-            scoring_functions=["basic::regex_parser_math_response"],
+            grader_ids=["basic::regex_parser_math_response"],
         ),
         BenchmarkInput(
             benchmark_id="meta-reference-bfcl",
             dataset_id="bfcl",
-            scoring_functions=["basic::bfcl"],
+            grader_ids=["basic::bfcl"],
         ),
     ]
     return DistributionTemplate(

llama_stack/templates/open-benchmark/run.yaml

@@ -196,27 +196,27 @@ datasets:
 scoring_fns: []
 benchmarks:
 - dataset_id: simpleqa
-  scoring_functions:
+  grader_ids:
   - llm-as-judge::405b-simpleqa
   metadata: {}
   benchmark_id: meta-reference-simpleqa
 - dataset_id: mmlu_cot
-  scoring_functions:
+  grader_ids:
   - basic::regex_parser_multiple_choice_answer
   metadata: {}
   benchmark_id: meta-reference-mmlu-cot
 - dataset_id: gpqa_cot
-  scoring_functions:
+  grader_ids:
   - basic::regex_parser_multiple_choice_answer
   metadata: {}
   benchmark_id: meta-reference-gpqa-cot
 - dataset_id: math_500
-  scoring_functions:
+  grader_ids:
   - basic::regex_parser_math_response
   metadata: {}
   benchmark_id: meta-reference-math-500
 - dataset_id: bfcl
-  scoring_functions:
+  grader_ids:
   - basic::bfcl
   metadata: {}
   benchmark_id: meta-reference-bfcl