Skip to content

test(e2e): make live image recognition non-blocking #1363

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

Merged
AndrewBarba merged 1 commit into from
Jul 30, 2026
Merged

test(e2e): make live image recognition non-blocking #1363

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 4 additions & 3 deletions e2e/fixtures/agent-tools/evals/static-tools/to-model-output-content-parts.eval.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,8 @@ const TOOL_NAME = "render-stripes";
// The stripe colors are randomized per run, so a blind model cannot pass by
// guessing; the eval stays self-contained by validating the reply against
// the answer key the tool records on action.result. The pixels reach the
// model exclusively through `toModelOutput` content parts.
// model exclusively through `toModelOutput` content parts. Color recognition
// remains tracked rather than gated because live vision quality varies.
export default defineEval({
description: "Static tools smoke: toModelOutput content parts deliver an image to the model.",
async test(t) {
Expand All @@ -21,7 +22,7 @@ export default defineEval({
t.eventsSatisfy("a reply names the rendered colors in order", (events) => {
const answer = assistantAnswers(events)[0];
return answer !== undefined && namesColorsInOrder(events, answer);
});
}).soft();

// The content part is baked into persisted history, so a follow-up turn
// must answer from replay without re-running the tool.
Expand All @@ -34,7 +35,7 @@ export default defineEval({
t.eventsSatisfy("the replayed image still answers the follow-up", (events) => {
const answer = assistantAnswers(events).at(-1);
return answer !== undefined && namesColorsInOrder(events, answer);
});
}).soft();
},
});

Expand Down