gooddata-eval 1.75.1.dev1__tar.gz → 1.75.1.dev3__tar.gz

{gooddata_eval-1.75.1.dev1 → gooddata_eval-1.75.1.dev3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: gooddata-eval
-Version: 1.75.1.dev1
+Version: 1.75.1.dev3
 Summary: Evaluate the GoodData AI agent against your own questions and models.
 Project-URL: Source, https://github.com/gooddata/gooddata-python-sdk
 Author-email: GoodData <support@gooddata.com>
@@ -17,8 +17,9 @@ Classifier: Topic :: Scientific/Engineering
 Classifier: Topic :: Software Development
 Classifier: Typing :: Typed
 Requires-Python: >=3.10
-Requires-Dist: gooddata-sdk~=1.75.1.dev1
+Requires-Dist: gooddata-sdk~=1.75.1.dev3
 Requires-Dist: httpx<1.0,>=0.27
+Requires-Dist: jsonpatch<2.0,>=1.33
 Requires-Dist: orjson<4.0.0,>=3.9.15
 Requires-Dist: pydantic<3.0,>=2.6
 Requires-Dist: rich<15.0,>=13.0

{gooddata_eval-1.75.1.dev1 → gooddata_eval-1.75.1.dev3}/pyproject.toml

@@ -1,7 +1,7 @@
 # (C) 2026 GoodData Corporation
 [project]
 name = "gooddata-eval"
-version = "1.75.1.dev1"
+version = "1.75.1.dev3"
 description = "Evaluate the GoodData AI agent against your own questions and models."
 readme = "README.md"
 license = "MIT"
@@ -11,8 +11,9 @@ authors = [
 keywords = ["gooddata", "ai", "evaluation", "llm", "analytics", "cli"]
 requires-python = ">=3.10"
 dependencies = [
-    "gooddata-sdk~=1.75.1.dev1",
+    "gooddata-sdk~=1.75.1.dev3",
     "httpx>=0.27,<1.0",
+    "jsonpatch>=1.33,<2.0",
     "orjson>=3.9.15,<4.0.0",
     "pydantic>=2.6,<3.0",
     "rich>=13.0,<15.0",

{gooddata_eval-1.75.1.dev1 → gooddata_eval-1.75.1.dev3}/scripts/verify_guardrail_refusal_criteria.py

@@ -39,7 +39,9 @@ import os
 
 from dotenv import load_dotenv
 
-load_dotenv("/Users/petertomko/gdc-mic-ai-evaluation/.env")
+# Whatever .env the caller points at, defaulting to the working directory. It used to be an
+# absolute path, which made the script runnable on exactly one machine.
+load_dotenv(os.environ.get("GD_EVAL_ENV_FILE", ".env"))
 
 from gooddata_eval.core.agentic.guardrail import _GUARDRAIL_EVALUATION_STEPS  # noqa: E402
 from gooddata_eval.core.evaluators._guardrail_criteria import (  # noqa: E402

{gooddata_eval-1.75.1.dev1 → gooddata_eval-1.75.1.dev3}/src/gooddata_eval/cli/agentic_runner.py

@@ -20,6 +20,7 @@ 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
+from gooddata_eval.core.agentic.what_if import evaluate_agentic_what_if
 from gooddata_eval.core.config import ReasoningEffort
 from gooddata_eval.core.models import AgenticEvalOutcome, CreatedVisualization, DatasetItem
 from gooddata_eval.core.runner import EvalReport, ItemReport
@@ -47,6 +48,7 @@ AGENTIC_TEST_KINDS = frozenset(
         "agentic_guardrail",
         "agentic_conversation",
         "agentic_kda_skill",
+        "agentic_what_if",
     }
 )
 
@@ -265,6 +267,17 @@ def _dispatch_agentic(
             agent_id=agent_id,
             **lf_kw,
         )
+    elif kind == "agentic_what_if":
+        return evaluate_agentic_what_if(
+            host=host,
+            token=token,
+            workspace_id=workspace_id,
+            question=item.question,
+            expected_output=eo if isinstance(eo, dict) else {},
+            k=k,
+            agent_id=agent_id,
+            **lf_kw,
+        )
     elif kind == "agentic_conversation":
         fixture_data = eo.get("fixture") or eo if isinstance(eo, dict) else {}
         return evaluate_agentic_conversation(