Merge pull request #1706 from gooddata/QA-28800-kda-skill

feat(gooddata-eval): add KDA-skill agentic evaluator

Author: myhoai

packages/gooddata-eval/src/gooddata_eval/cli/agentic_runner.py

@@ -11,6 +11,7 @@
 from gooddata_eval.core.agentic.conversation import ConversationFixture, evaluate_agentic_conversation
 from gooddata_eval.core.agentic.general_question import evaluate_agentic_general_question
 from gooddata_eval.core.agentic.guardrail import evaluate_agentic_guardrail
+from gooddata_eval.core.agentic.kda_skill import evaluate_agentic_kda_skill
 from gooddata_eval.core.agentic.metric_skill import evaluate_agentic_metric_skill
 from gooddata_eval.core.agentic.search_tool import evaluate_agentic_search_tool
 from gooddata_eval.core.agentic.visualization import evaluate_agentic_visualization
@@ -38,6 +39,7 @@ class _LfKw(TypedDict, total=False):
         "agentic_general_question",
         "agentic_guardrail",
         "agentic_conversation",
+        "agentic_kda_skill",
     }
 )
 
@@ -159,6 +161,16 @@ def _dispatch_agentic(
             k=k,
             **lf_kw,
         )
+    elif kind == "agentic_kda_skill":
+        evaluate_agentic_kda_skill(
+            host=host,
+            token=token,
+            workspace_id=workspace_id,
+            question=item.question,
+            expected_output=eo if isinstance(eo, dict) else {},
+            k=k,
+            **lf_kw,
+        )
     elif kind == "agentic_conversation":
         fixture_data = eo.get("fixture") or eo if isinstance(eo, dict) else {}
         evaluate_agentic_conversation(

packages/gooddata-eval/src/gooddata_eval/core/agentic/__init__.py

@@ -30,6 +30,14 @@
     evaluate_agentic_guardrail,
     run_agentic_guardrail,
 )
+from gooddata_eval.core.agentic.kda_skill import (
+    AgenticKdaSummary,
+    KdaEvaluation,
+    KdaRunResult,
+    KdaSkillAssertionError,
+    evaluate_agentic_kda_skill,
+    run_agentic_kda_skill,
+)
 from gooddata_eval.core.agentic.metric_skill import (
     AgenticMetricSummary,
     MetricRunResult,
@@ -56,6 +64,7 @@
     "AgenticAlertSummary",
     "AgenticGeneralQuestionSummary",
     "AgenticGuardrailSummary",
+    "AgenticKdaSummary",
     "AgenticMetricSummary",
     "AgenticSearchSummary",
     "AgenticRunSummary",
@@ -69,6 +78,9 @@
     "GeneralQuestionResult",
     "GuardrailAssertionError",
     "GuardrailResult",
+    "KdaEvaluation",
+    "KdaRunResult",
+    "KdaSkillAssertionError",
     "MetricRunResult",
     "MetricSkillAssertionError",
     "RunResult",
@@ -81,13 +93,15 @@
     "evaluate_agentic_conversation",
     "evaluate_agentic_general_question",
     "evaluate_agentic_guardrail",
+    "evaluate_agentic_kda_skill",
     "evaluate_agentic_metric_skill",
     "evaluate_agentic_search_tool",
     "evaluate_agentic_visualization",
     "run_agentic_alert_skill",
     "run_agentic_conversation",
     "run_agentic_general_question",
     "run_agentic_guardrail",
+    "run_agentic_kda_skill",
     "run_agentic_metric_skill",
     "run_agentic_search_tool",
     "run_agentic_visualization",