feature: add classification evaluators #4161

Job	Run time
discover-testcases	7s
apicalls-testcase / alpha	37s
basic-testcase / alpha	36s
basic-testcase / cloud	32s
calculator-crash-evals / cloud	32s
apicalls-testcase / cloud	42s
calculator-evals / cloud	2m 52s
basic-testcase / staging	34s
apicalls-testcase / staging	43s
eval-level-expected-output / alpha	43s
calculator-crash-evals / staging	39s
eval-input-overrides / cloud	29s
calculator-evals / alpha	3m 12s
langchain-cross / staging	38s
calculator-evals / staging	3m 8s
csv-processor-evals / cloud	34s
calculator-crash-evals / alpha	36s
eval-level-expected-output / cloud	46s
eval-spans-testcase / alpha	1m 26s
target-output-key-evals / alpha	33s
eval-input-overrides / alpha	33s
eval-telemetry-testcase / staging	1m 47s
target-output-key-evals / cloud	30s
langchain-cross / alpha	35s
csv-processor-evals / staging	37s
eval-level-expected-output / staging	42s
tools-evals / cloud	45s
eval-input-overrides / staging	30s
tools-evals / alpha	47s
eval-telemetry-testcase / cloud	1m 44s
langchain-cross / cloud	41s
eval-telemetry-testcase / alpha	1m 46s
tools-evals / staging	43s
target-output-key-evals / staging	34s
eval-spans-testcase / staging	1m 17s
eval-spans-testcase / cloud	1m 5s
csv-processor-evals / alpha	34s
summarize-results	3s
	35m 12s

Provide feedback