feat(metrics): add AdversarialRobustnessMetric

Add a black-box metric that measures how robust an LLM is to adversarial,
meaning-preserving perturbations of its input, addressing #2150.

Inspired by the RoMA framework (arXiv:2504.17723), for each test case the
metric:
  1. uses the evaluation model to generate meaning-preserving adversarial
     perturbations of the input (semantic synonym/rephrasing swaps and
     orthographic typo-style character noise);
  2. probes the system under test via a `model_callback` on every
     perturbation;
  3. uses the evaluation model to judge whether each perturbed response stays
     semantically consistent with the reference `actual_output`.

The score is the fraction of perturbations the system stayed consistent on
(1.0 = perfectly robust); higher is better, so a case passes when
`score >= threshold`. Follows the existing BaseMetric conventions: sync/async
`measure`/`a_measure`, schema-based generation, the compiled prompt-template
bundle, strict/verbose modes, and cost/token accrual.

Unlike the earlier draft (#2181) this pulls in no heavyweight runtime
dependencies (no gensim/nltk/numpy and no large Word2Vec download) and judges
robustness by LLM-graded semantic consistency rather than brittle exact string
matching.

Adds the metric to the public `deepeval.metrics` exports, the compiled
metric-template bundles (Python + TypeScript), and a fully mocked test suite
(no real API calls).

Signed-off-by: xr843 <xianren843@protonmail.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Author: xr843

deepeval/metrics/__init__.py

@@ -14,6 +14,9 @@
 from .non_advice.non_advice import NonAdviceMetric
 from .misuse.misuse import MisuseMetric
 from .role_violation.role_violation import RoleViolationMetric
+from .adversarial_robustness.adversarial_robustness import (
+    AdversarialRobustnessMetric,
+)
 from .hallucination.hallucination import HallucinationMetric
 from .answer_relevancy.answer_relevancy import AnswerRelevancyMetric
 from .summarization.summarization import SummarizationMetric
@@ -102,6 +105,7 @@
     "MisuseMetric",
     "RoleViolationMetric",
     "RoleAdherenceMetric",
+    "AdversarialRobustnessMetric",
     # Task-specific metrics
     "ToolCorrectnessMetric",
     "JsonCorrectnessMetric",

deepeval/metrics/adversarial_robustness/__init__.py

@@ -0,0 +1,3 @@
+from .adversarial_robustness import AdversarialRobustnessMetric
+
+__all__ = ["AdversarialRobustnessMetric"]