feat(gooddata-eval): evaluate the agentic dashboard-creation skill

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

@@ -13,6 +13,7 @@
 from gooddata_eval.core.agentic._trace_linker import BackgroundTraceLinker, SubmitTraceLink, run_trace_link_inline
 from gooddata_eval.core.agentic.alert_skill import evaluate_agentic_alert_skill
 from gooddata_eval.core.agentic.conversation import ConversationFixture, evaluate_agentic_conversation
+from gooddata_eval.core.agentic.dashboard_skill import evaluate_agentic_dashboard_skill
 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
@@ -40,6 +41,7 @@ class _LfKw(TypedDict, total=False):
         "agentic_visualization",  # experimental: expected_output.expected_outputs (multi-candidate)
         "agentic_metric_skill",
         "agentic_alert_skill",
+        "agentic_dashboard_skill",
         "agentic_search",
         "agentic_general_question",
         "agentic_guardrail",
@@ -85,6 +87,10 @@ class _LfKw(TypedDict, total=False):
 # create_key_driver_analysis with no cleanup, and while the evaluator only ever reads that
 # call's ARGUMENTS -- never a created object id -- whether the platform persists anything is
 # unverified. Move it to the allowlist once someone confirms it does not.
+#
+# agentic_dashboard_skill is absent by default rather than by evidence: gen-ai holds the draft and
+# any chart it authors in conversation state and writes neither until a user saves from the UI, so
+# it is a candidate for the allowlist once the dataset has runs behind it.
 WORKSPACE_MUTATING_TEST_KINDS = frozenset(AGENTIC_TEST_KINDS) - PARALLEL_SAFE_TEST_KINDS
 
 
@@ -183,6 +189,18 @@ def _dispatch_agentic(
             agent_id=agent_id,
             **lf_kw,
         )
+    elif kind == "agentic_dashboard_skill":
+        return evaluate_agentic_dashboard_skill(
+            host=host,
+            token=token,
+            workspace_id=workspace_id,
+            question=item.question,
+            expected_output=eo if isinstance(eo, dict) else {},
+            k=k,
+            gate=gate,
+            agent_id=agent_id,
+            **lf_kw,
+        )
     elif kind == "agentic_alert_skill":
         return evaluate_agentic_alert_skill(
             host=host,

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

@@ -16,6 +16,14 @@
     evaluate_agentic_conversation,
     run_agentic_conversation,
 )
+from gooddata_eval.core.agentic.dashboard_skill import (
+    AgenticDashboardSummary,
+    DashboardEvaluation,
+    DashboardRunResult,
+    DashboardSkillAssertionError,
+    evaluate_agentic_dashboard_skill,
+    run_agentic_dashboard_skill,
+)
 from gooddata_eval.core.agentic.general_question import (
     AgenticGeneralQuestionSummary,
     GeneralQuestionAssertionError,
@@ -62,6 +70,7 @@
 
 __all__ = [
     "AgenticAlertSummary",
+    "AgenticDashboardSummary",
     "AgenticGeneralQuestionSummary",
     "AgenticGuardrailSummary",
     "AgenticKdaSummary",
@@ -74,6 +83,9 @@
     "ConversationAssertionError",
     "ConversationFixture",
     "ConversationResult",
+    "DashboardEvaluation",
+    "DashboardRunResult",
+    "DashboardSkillAssertionError",
     "GeneralQuestionAssertionError",
     "GeneralQuestionResult",
     "GuardrailAssertionError",
@@ -91,6 +103,7 @@
     "VisualizationAssertionError",
     "evaluate_agentic_alert_skill",
     "evaluate_agentic_conversation",
+    "evaluate_agentic_dashboard_skill",
     "evaluate_agentic_general_question",
     "evaluate_agentic_guardrail",
     "evaluate_agentic_kda_skill",
@@ -99,6 +112,7 @@
     "evaluate_agentic_visualization",
     "run_agentic_alert_skill",
     "run_agentic_conversation",
+    "run_agentic_dashboard_skill",
     "run_agentic_general_question",
     "run_agentic_guardrail",
     "run_agentic_kda_skill",