Skip to content

feat(gooddata-eval): evaluate the dashboard summary users actually get #1797

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

feat(gooddata-eval): evaluate the dashboard summary users actually get #1797

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
4e3ba70
feat(gooddata-eval): evaluate the dashboard summary users actually get
Tomkess Sep 9, 2026
a86cd42
fix(gooddata-eval): address review on the agentic dashboard-summary kind
Tomkess Sep 9, 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
23 changes: 23 additions & 0 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 @@ -12,6 +12,7 @@
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_summary import evaluate_agentic_dashboard_summary
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
Expand Down Expand Up @@ -44,6 +45,7 @@ class _LfKw(TypedDict, total=False):
"agentic_guardrail",
"agentic_conversation",
"agentic_kda_skill",
"agentic_dashboard_summary",
}
)

Expand Down Expand Up @@ -228,6 +230,27 @@ def _dispatch_agentic(
agent_id=agent_id,
**lf_kw,
)
elif kind == "agentic_dashboard_summary":
summary_input = item.summary_input
if summary_input is None:
raise ValueError(f"agentic_dashboard_summary item '{item.id}' is missing required 'summary_input'.")
return evaluate_agentic_dashboard_summary(
host=host,
token=token,
workspace_id=workspace_id,
dashboard_id=summary_input.dashboard_id,
expected_output=eo,
# The fixture's own wording is the prompt under test -- a localized fixture is
# only meaningful if its own phrasing is what reaches the agent.
question=item.question,
# Each widget costs an execution, so a fixture asserting on a handful of charts
# can name them instead of paying for the whole dashboard. Same field and meaning
# the headless /summary endpoint gives it; None summarizes everything.
only_visualizations=summary_input.visualizations,
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(
Expand Down
Loading
Loading