Merge pull request #1676 from hkad98/jkd/deps

build(deps): bump dev tooling + wire gooddata-eval into tox

Author: hkad98

packages/gooddata-eval/pyproject.toml

@@ -45,6 +45,7 @@ dev = [
 test = [
     "pytest~=8.3.4",
     "pytest-cov~=6.0.0",
+    "pytest-json-report==1.5.0",
     "pytest-mock>=3.14.0",
 ]
 

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

@@ -6,7 +6,7 @@
 import time
 from typing import Any, TypedDict
 
-from gooddata_eval.core.agentic._langfuse import HttpxLangfuseClient, make_langfuse_client
+from gooddata_eval.core.agentic._langfuse import make_langfuse_client
 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.general_question import evaluate_agentic_general_question
@@ -17,17 +17,14 @@
 from gooddata_eval.core.models import CreatedVisualization, DatasetItem
 from gooddata_eval.core.runner import EvalReport, ItemReport
 
-_LfKw = TypedDict(
-    "_LfKw",
-    {
-        "langfuse": Any,
-        "dataset_item_id": str,
-        "dataset_name": str,
-        "run_timestamp": str,
-        "model_version_override": str | None,
-    },
-    total=False,
-)
+
+class _LfKw(TypedDict, total=False):
+    langfuse: Any
+    dataset_item_id: str
+    dataset_name: str
+    run_timestamp: str
+    model_version_override: str | None
+
 
 AGENTIC_TEST_KINDS = frozenset(
     {

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

@@ -12,6 +12,7 @@
 from rich.console import Console
 from rich.table import Table
 
+from gooddata_eval.cli.agentic_runner import AGENTIC_TEST_KINDS, run_agentic_items
 from gooddata_eval.core.chat.sse_client import ChatClient
 from gooddata_eval.core.config import RunConfig
 from gooddata_eval.core.connection import ConnectionError_, resolve_connection
@@ -20,7 +21,6 @@
 from gooddata_eval.core.models import ChatResult, DatasetItem
 from gooddata_eval.core.reporting.console import render_comparison, render_console
 from gooddata_eval.core.reporting.json_report import write_multi_model_report
-from gooddata_eval.cli.agentic_runner import AGENTIC_TEST_KINDS, run_agentic_items
 from gooddata_eval.core.runner import ItemReport, run_items
 from gooddata_eval.core.summary.http_client import SummaryClient
 from gooddata_eval.core.workspace import ModelResolutionError, WorkspaceModelController

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

@@ -7,12 +7,10 @@
 import os
 import re
 from dataclasses import dataclass
-
 from typing import Any
 
-from gooddata_eval.core.chat.sse_client import ChatClient
 from gooddata_eval.core.agentic._catalog import CatalogMetricAlert
-
+from gooddata_eval.core.chat.sse_client import ChatClient
 from gooddata_eval.core.models import ToolCallEvent
 
 try:
@@ -438,7 +436,9 @@ def evaluate_agentic_alert_skill(
     model_version_override: str | None = None,
 ) -> None:
     """Run alert-skill evaluation, log to Langfuse, and raise AlertSkillAssertionError on failure."""
-    from datetime import datetime as _dt, timezone as _tz  # noqa: PLC0415
+    from datetime import datetime as _dt  # noqa: PLC0415
+    from datetime import timezone as _tz  # noqa: PLC0415
+
     from gooddata_eval.core.agentic._langfuse import try_make_langfuse_client  # noqa: PLC0415
 
     if langfuse is None:

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

@@ -386,7 +386,9 @@ def evaluate_agentic_conversation(
     model_version_override: str | None = None,
 ) -> None:
     """Run conversation evaluation, log to Langfuse, and raise on failure."""
-    from datetime import datetime as _dt, timezone as _tz  # noqa: PLC0415
+    from datetime import datetime as _dt  # noqa: PLC0415
+    from datetime import timezone as _tz  # noqa: PLC0415
+
     from gooddata_eval.core.agentic._langfuse import try_make_langfuse_client  # noqa: PLC0415
 
     if langfuse is None:

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

@@ -154,7 +154,9 @@ def evaluate_agentic_general_question(
     model_version_override: str | None = None,
 ) -> None:
     """Run general-question evaluation, log to Langfuse, and raise on failure."""
-    from datetime import datetime as _dt, timezone as _tz  # noqa: PLC0415
+    from datetime import datetime as _dt  # noqa: PLC0415
+    from datetime import timezone as _tz  # noqa: PLC0415
+
     from gooddata_eval.core.agentic._langfuse import try_make_langfuse_client  # noqa: PLC0415
 
     if langfuse is None:

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

@@ -151,7 +151,9 @@ def evaluate_agentic_guardrail(
     model_version_override: str | None = None,
 ) -> None:
     """Run guardrail evaluation, log to Langfuse, and raise on failure."""
-    from datetime import datetime as _dt, timezone as _tz  # noqa: PLC0415
+    from datetime import datetime as _dt  # noqa: PLC0415
+    from datetime import timezone as _tz  # noqa: PLC0415
+
     from gooddata_eval.core.agentic._langfuse import try_make_langfuse_client  # noqa: PLC0415
 
     if langfuse is None:

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

@@ -3,11 +3,10 @@
 
 from __future__ import annotations
 
-from typing import Any
-
 import os
 import re
 from dataclasses import dataclass
+from typing import Any
 
 from gooddata_eval.core.chat.sse_client import ChatClient
 from gooddata_eval.core.models import ToolCallEvent
@@ -247,7 +246,9 @@ def evaluate_agentic_metric_skill(
     model_version_override: str | None = None,
 ) -> None:
     """Run metric-skill evaluation, log to Langfuse, and raise MetricSkillAssertionError on failure."""
-    from datetime import datetime as _dt, timezone as _tz  # noqa: PLC0415
+    from datetime import datetime as _dt  # noqa: PLC0415
+    from datetime import timezone as _tz  # noqa: PLC0415
+
     from gooddata_eval.core.agentic._langfuse import try_make_langfuse_client  # noqa: PLC0415
 
     if langfuse is None:

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

@@ -145,7 +145,9 @@ def evaluate_agentic_search_tool(
     model_version_override: str | None = None,
 ) -> None:
     """Run search-tool evaluation, log to Langfuse, and raise SearchToolAssertionError on failure."""
-    from datetime import datetime as _dt, timezone as _tz  # noqa: PLC0415
+    from datetime import datetime as _dt  # noqa: PLC0415
+    from datetime import timezone as _tz  # noqa: PLC0415
+
     from gooddata_eval.core.agentic._langfuse import try_make_langfuse_client  # noqa: PLC0415
 
     if langfuse is None:

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

@@ -267,7 +267,9 @@ def evaluate_agentic_visualization(
 ) -> None:
     """Run visualization evaluation, log to Langfuse, and raise VisualizationAssertionError on failure."""
     import json as _json  # noqa: PLC0415
-    from datetime import datetime as _dt, timezone as _tz  # noqa: PLC0415
+    from datetime import datetime as _dt  # noqa: PLC0415
+    from datetime import timezone as _tz  # noqa: PLC0415
+
     from gooddata_eval.core.agentic._langfuse import try_make_langfuse_client  # noqa: PLC0415
 
     if langfuse is None: