Skip to content

test(sdk-tanstack-ai): cover the onConfig phase guard #162

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
aikins01 merged 1 commit into from
Nov 3, 2026
Merged

test(sdk-tanstack-ai): cover the onConfig phase guard #162

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
22 changes: 22 additions & 0 deletions packages/tanstack-ai/tests/middleware.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -868,6 +868,28 @@ test("a real chat() run opens one iteration span per model call", async () => {
expect(metrics.filter((m) => m.metric === "duration")).toHaveLength(1);
});

// Supported engines call onConfig after onStart only before a model call, so no engine run reaches
// the phase guard; this calls it directly.
test.each(["init", "afterModel", "modelStream", "beforeTools", "afterTools"] as const)(
"onConfig for phase %s after onStart opens no iteration span",
async (phase) => {
const { spanBatches, overrides } = makeCapture();
const mw = middleware(overrides);
const ctx = makeCtx();

await mw.onStart?.(ctx);
await mw.onConfig?.(ctx, chatConfig());
Object.assign(ctx, { phase });
await mw.onConfig?.(ctx, chatConfig());
await mw.onUsage?.(ctx, { promptTokens: 10, completionTokens: 5, totalTokens: 15 } as never);
await mw.onFinish?.(ctx, { finishReason: "stop", duration: 50, content: "done" } as never);

const iterations = spanBatches[0]!.filter((s) => s.kind === SpanKind.CLIENT);
expect(iterations).toHaveLength(1);
expect(iterations[0]!.attributes["gen_ai.usage.input_tokens"]).toBe(10);
},
);

test("structured output finalization records a separate iteration span", async () => {
const { spanBatches, metrics, overrides } = makeCapture();
const mw = middleware(overrides);
Expand Down
Loading