ci(evals): Pass the job's test total to run-evals

run-evals checks it against the tests it collects, so a job fails rather than run
another test than create-runs numbered. Needs getsentry/sentry-for-ai-evals#97.

Refs VDY-312

Author: jaydgoss

.github/workflows/ai-evals.yml

@@ -245,6 +245,7 @@ jobs:
         with:
           marker: ${{ matrix.job.marker }}
           test-index: ${{ matrix.job.test-index }}
+          test-total: ${{ matrix.job.test-total }}
           count: ${{ matrix.job.count }}
           harness: ${{ matrix.job.target.harness }}
           model: ${{ matrix.job.target.model }}