Skip to content

feat(gooddata-eval): check that gen-ai sends the Document wire names #1862

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
romrak wants to merge 2 commits into
base: master
Choose a base branch
from
Open

feat(gooddata-eval): check that gen-ai sends the Document wire names #1862

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
83473b8
refactor(gooddata-eval): name the report skill evaluator for documents
Oct 8, 2026
92fe97e
feat(gooddata-eval): check that gen-ai sends the Document wire names
Oct 8, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions packages/gooddata-eval/src/gooddata_eval/cli/agentic_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,11 +15,11 @@
from gooddata_eval.core.agentic.anomaly_detection import evaluate_agentic_anomaly_detection
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.document_skill import evaluate_agentic_document_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
from gooddata_eval.core.agentic.metric_skill import evaluate_agentic_metric_skill
from gooddata_eval.core.agentic.report_skill import evaluate_agentic_report_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
Expand Down Expand Up @@ -47,7 +47,7 @@ class _LfKw(TypedDict, total=False):
"agentic_metric_skill",
"agentic_alert_skill",
"agentic_dashboard_skill",
"agentic_report_skill",
"agentic_document_skill",
"agentic_search",
"agentic_general_question",
"agentic_guardrail",
Expand Down Expand Up @@ -98,8 +98,8 @@ class _LfKw(TypedDict, total=False):
#
# 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. agentic_report_skill is
# absent for the same reason: the report draft stays in conversation state until a user saves it.
# it is a candidate for the allowlist once the dataset has runs behind it. agentic_document_skill is
# absent for the same reason: the document draft stays in conversation state until a user saves it.
WORKSPACE_MUTATING_TEST_KINDS = frozenset(AGENTIC_TEST_KINDS) - PARALLEL_SAFE_TEST_KINDS


Expand Down Expand Up @@ -214,8 +214,8 @@ def _dispatch_agentic(
user_context=item.user_context,
**lf_kw,
)
elif kind == "agentic_report_skill":
return evaluate_agentic_report_skill(
elif kind == "agentic_document_skill":
return evaluate_agentic_document_skill(
host=host,
token=token,
workspace_id=workspace_id,
Expand Down
30 changes: 22 additions & 8 deletions packages/gooddata-eval/src/gooddata_eval/core/agentic/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,14 @@
evaluate_agentic_dashboard_skill,
run_agentic_dashboard_skill,
)
from gooddata_eval.core.agentic.document_skill import (
AgenticDocumentSummary,
DocumentEvaluation,
DocumentRunResult,
DocumentSkillAssertionError,
evaluate_agentic_document_skill,
run_agentic_document_skill,
)
from gooddata_eval.core.agentic.general_question import (
AgenticGeneralQuestionSummary,
GeneralQuestionAssertionError,
Expand Down Expand Up @@ -53,14 +61,6 @@
evaluate_agentic_metric_skill,
run_agentic_metric_skill,
)
from gooddata_eval.core.agentic.report_skill import (
AgenticReportSummary,
ReportEvaluation,
ReportRunResult,
ReportSkillAssertionError,
evaluate_agentic_report_skill,
run_agentic_report_skill,
)
from gooddata_eval.core.agentic.search_tool import (
AgenticSearchSummary,
SearchResult,
Expand All @@ -76,13 +76,22 @@
run_agentic_visualization,
)

# Deprecated names of the document skill, kept for existing callers.
AgenticReportSummary = AgenticDocumentSummary
ReportEvaluation = DocumentEvaluation
ReportRunResult = DocumentRunResult
ReportSkillAssertionError = DocumentSkillAssertionError
evaluate_agentic_report_skill = evaluate_agentic_document_skill
run_agentic_report_skill = run_agentic_document_skill

__all__ = [
"AgenticAlertSummary",
"AgenticDashboardSummary",
"AgenticGeneralQuestionSummary",
"AgenticGuardrailSummary",
"AgenticKdaSummary",
"AgenticMetricSummary",
"AgenticDocumentSummary",
"AgenticReportSummary",
"AgenticSearchSummary",
"AgenticRunSummary",
Expand All @@ -95,6 +104,9 @@
"DashboardEvaluation",
"DashboardRunResult",
"DashboardSkillAssertionError",
"DocumentEvaluation",
"DocumentRunResult",
"DocumentSkillAssertionError",
"GeneralQuestionAssertionError",
"GeneralQuestionResult",
"GuardrailAssertionError",
Expand All @@ -116,6 +128,7 @@
"evaluate_agentic_alert_skill",
"evaluate_agentic_conversation",
"evaluate_agentic_dashboard_skill",
"evaluate_agentic_document_skill",
"evaluate_agentic_general_question",
"evaluate_agentic_guardrail",
"evaluate_agentic_kda_skill",
Expand All @@ -126,6 +139,7 @@
"run_agentic_alert_skill",
"run_agentic_conversation",
"run_agentic_dashboard_skill",
"run_agentic_document_skill",
"run_agentic_general_question",
"run_agentic_guardrail",
"run_agentic_kda_skill",
Expand Down
Loading
Loading