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

Adds kda_skill.py, evaluating the chatbot's create_key_driver_analysis /
execute_key_driver_analysis tool calls against the agent_kda_skill Langfuse
dataset (QA-28800).

Current scope is completion, not field correctness: strict_pass requires
kda_triggered + executed + success + turn_completed. Per-field checks
(Measure/Date Attribute/Periods/Filters/Summary) are computed and logged to
Langfuse for visibility, but intentionally excluded from strict_pass --
that verification is scoped to a follow-up ticket.

Includes a bounded (max 2 turns) disambiguation safety net, mirroring
alert_skill's/metric_skill's simulated-user pattern: if the agent asks a
clarifying question (a metric-title collision, or a choice between the
metric-id and ad-hoc fact+SUM forms of the same measure) instead of
triggering KDA, a simulated reply picks an acceptable candidate so the
disambiguation turn doesn't block measuring whether KDA itself completes.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

Author: FrankHuynh

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",