Show reasoning traces: live Thinking block + persisted disclosure

New reasoning_delta event; traces persist as a display sidecar stripped from provider feeds.
Sources: compat vendors' reasoning_content and Gemini thought summaries (include_thoughts).
Live-verified on GLM via Together and Gemini 3; Gemini tool loops stay healthy.
This commit is contained in:
Rohit C Prasad
2026-07-22 16:15:11 -07:00
committed by Rohit P
parent f1eb652d61
commit 0e8b85e6f3
16 changed files with 421 additions and 67 deletions
+21
View File
@@ -648,6 +648,27 @@ export async function mockApi(page: import("@playwright/test").Page) {
});
return;
}
// A reasoning model's turn: thinking deltas tick in slowly, then the answer —
// the assistant_message carries the full trace like the real engine's payload.
if (/think hard/i.test(msg.text)) {
const thoughts = ["Weighing options. ", "Comparing tradeoffs. ", "Settling it. "];
let tick = 0;
const timer = setInterval(() => {
if (tick < thoughts.length) {
send("reasoning_delta", { text: thoughts[tick] });
tick += 1;
return;
}
clearInterval(timer);
send("assistant_delta", { text: "Decision made." });
send("assistant_message", {
text: "Decision made.",
reasoning: thoughts.join(""),
});
send("turn_done");
}, 120);
return;
}
// A turn that dies on a provider error; the follow-up {type:"retry"} recovers.
if (/fail the turn/i.test(msg.text)) {
send("error", { error: "model unreachable" });
+31
View File
@@ -0,0 +1,31 @@
// Model-layer roadmap item 4 (2026-07-22): reasoning traces. Live turn shows a quiet
// pulsing "Thinking…" disclosure that streams the trace; once the message finalizes the
// trace folds into a collapsed "Thought process" disclosure on the answer bubble.
import { expect } from "@playwright/test";
import { test } from "./fixtures";
test("thinking streams live, then persists as a collapsed disclosure on the answer", async ({
page,
}) => {
await page.goto("/");
await page.getByText("Draft the launch note").first().click();
const box = page.getByPlaceholder(/Ask the coworker/);
await box.fill("think hard about this");
await box.press("Enter");
// Live phase: the Thinking… block is up while deltas tick in; expanding shows the trace.
await expect(page.getByText("Thinking…").first()).toBeVisible({ timeout: 10_000 });
await page.getByTestId("thinking-toggle").click();
await expect(page.getByTestId("thinking-body")).toContainText("Weighing options.");
// Finalized: the answer bubble carries a collapsed "Thought process" disclosure.
await expect(page.getByText("Decision made.").first()).toBeVisible({ timeout: 10_000 });
await expect(page.getByText("Thinking…")).toHaveCount(0);
const toggle = page.getByTestId("thinking-toggle");
await expect(toggle).toHaveText(/Thought process/);
await expect(page.getByTestId("thinking-body")).toHaveCount(0); // collapsed by default
await toggle.click();
await expect(page.getByTestId("thinking-body")).toContainText(
"Weighing options. Comparing tradeoffs. Settling it.",
);
});