mirror of
https://github.com/getpaseo/paseo.git
synced 2026-11-07 17:04:42 +00:00
Keep created agents after first-prompt failures and bound fork history (#6379)
* fix(agents): preserve creation when the first prompt fails A rejected initial prompt must leave a created agent with a turn error instead of returning the user to a draft whose creation key is already committed. Preserve receipt replay without repeating the prompt, and bound fork history to 100,000 characters before it becomes an attachment. * test(creation): isolate user agent counters from background naming Workspace naming uses internal provider sessions. Counting and rejecting those sessions made creation assertions depend on installed provider discovery timing. Keep discovery within the test adapters and scope observations to user-created agents. * test(creation): retry temporary directory cleanup on Windows Windows CI completed the rejection assertions but failed teardown with EBUSY. Match the daemon test harness bounded removal retries so transient directory locks do not fail creation tests. * fix(agents): record rejected prompts before their errors Startup rejection recorded only the system error, leaving the client to append its local prompt after it. Record the rejected submission at the terminal failure boundary so stream and fetched history agree on prompt-before-error ordering. * fix(agents): require acceptance for delivery notifications Retain rejected human submissions before their errors without projecting rejected inter-agent prompts as completed deliveries. Reproduces and fixes the notification regression exposed by merge CI. * test(agents): retain rejected submissions across retries The existing browser retry test assumed terminally rejected prompts disappeared. Assert the intended prompt-before-error history and a separate accepted retry while preserving draft, attachment, and ambiguous-steering checks. * test(creation): allow integration latency in raw RPC responses The peer inherited a one-second polling timeout despite exercising Git and provider startup. Reproduce the timeout with delayed startup and wait within an explicit integration budget while retaining all response and identity assertions.
This commit is contained in:
@@ -284,7 +284,6 @@ async function expectRejectedSubmissionRestored(
|
||||
await expectComposerDraft(page, input.prompt);
|
||||
await expectComposerEditable(page);
|
||||
await expectAttachmentPill(page, "composer-image-attachment-pill");
|
||||
await expect(page.getByTestId("user-message").filter({ hasText: input.prompt })).toHaveCount(0);
|
||||
if (input.preservesActiveTurn) {
|
||||
await expect(page.getByTestId("turn-working-indicator")).toBeVisible();
|
||||
return;
|
||||
@@ -295,13 +294,21 @@ async function expectRejectedSubmissionRestored(
|
||||
|
||||
async function retryRestoredSubmission(page: Page, prompt: string): Promise<void> {
|
||||
await page.getByRole("textbox", { name: "Message agent..." }).first().press("Enter");
|
||||
const userMessage = page.getByTestId("user-message").filter({ hasText: prompt });
|
||||
await expect(userMessage).toHaveCount(1);
|
||||
const attempts = page.getByTestId("user-message").filter({ hasText: prompt });
|
||||
await expect(attempts).toHaveCount(2);
|
||||
const userMessage = attempts.last();
|
||||
await expect(userMessage).toHaveAttribute("aria-busy", "false", { timeout: 30_000 });
|
||||
await expect(userMessage.getByRole("button", { name: "Open image attachment" })).toBeVisible();
|
||||
await expect(page.getByTestId("composer-image-attachment-pill")).toHaveCount(0);
|
||||
}
|
||||
|
||||
async function expectRejectedPromptBeforeError(page: Page, prompt: string, errorMessage: string) {
|
||||
const messages = page.getByTestId("user-message").or(page.getByTestId("assistant-message"));
|
||||
await expect(messages).toHaveCount(2);
|
||||
await expect(messages.nth(0)).toContainText(prompt);
|
||||
await expect(messages.nth(1)).toContainText(`[System Error] ${errorMessage}`);
|
||||
}
|
||||
|
||||
async function configureSteerInSettings(page: Page): Promise<void> {
|
||||
const modifier = process.platform === "darwin" ? "Meta" : "Control";
|
||||
await page.keyboard.press(`${modifier}+Comma`);
|
||||
@@ -1173,13 +1180,14 @@ test.describe("Agent message submission", () => {
|
||||
await toasts.expectNeverShown("agent-updating-toast");
|
||||
});
|
||||
|
||||
test("restores a rejected submission and accepts its retry", async ({
|
||||
test("retains a rejected submission before its error and accepts its retry", async ({
|
||||
page,
|
||||
rejectionScenario,
|
||||
}) => {
|
||||
const prompt = "Restore this rejected submission.";
|
||||
await submitMessageThatWillBeRejected(page, prompt);
|
||||
await expectRejectedSubmissionRestored(page, { prompt, ...rejectionScenario });
|
||||
await expectRejectedPromptBeforeError(page, prompt, rejectionScenario.errorMessage);
|
||||
await retryRestoredSubmission(page, prompt);
|
||||
});
|
||||
|
||||
@@ -1209,6 +1217,7 @@ test.describe("Agent message submission", () => {
|
||||
errorMessage: "Requested mock steer transport failure",
|
||||
preservesActiveTurn: true,
|
||||
});
|
||||
await expect(page.getByTestId("user-message").filter({ hasText: prompt })).toHaveCount(0);
|
||||
|
||||
expect(gate.getClientRequestCount("send_agent_message_request")).toBe(sendsBefore + 1);
|
||||
expect(gate.getClientRequestCount("cancel_agent_request")).toBe(cancelsBefore);
|
||||
|
||||
@@ -128,3 +128,46 @@ for (const scenario of [
|
||||
await creation.expectAgentCount(1);
|
||||
});
|
||||
}
|
||||
|
||||
for (const entry of [
|
||||
{
|
||||
name: "agent draft",
|
||||
open: (creation: Awaited<ReturnType<typeof createCreationScenario>>) =>
|
||||
creation.openAgentDraft(),
|
||||
button: "Send message",
|
||||
settled: async (_creation: Awaited<ReturnType<typeof createCreationScenario>>) => {},
|
||||
},
|
||||
{
|
||||
name: "new workspace",
|
||||
open: (creation: Awaited<ReturnType<typeof createCreationScenario>>) =>
|
||||
creation.openWorkspaceForm("local"),
|
||||
button: "Create",
|
||||
settled: (creation: Awaited<ReturnType<typeof createCreationScenario>>) =>
|
||||
creation.expectOneCreatedWorkspace(),
|
||||
},
|
||||
]) {
|
||||
test(`${entry.name} becomes an agent tab when the first prompt is rejected`, async ({
|
||||
creation,
|
||||
promptRejection,
|
||||
page,
|
||||
}, testInfo) => {
|
||||
void promptRejection;
|
||||
const prompt =
|
||||
"Continue the attached conversation.\n" + "Earlier conversation context.\n".repeat(100);
|
||||
await entry.open(creation);
|
||||
await creation.submitPrompt(prompt, entry.button);
|
||||
await entry.settled(creation);
|
||||
await creation.expectCreatedAgentError();
|
||||
await creation.expectPromptBeforeError(prompt);
|
||||
await page.screenshot({ path: testInfo.outputPath("created-agent-prompt-error.png") });
|
||||
await creation.reloadAgent();
|
||||
await creation.expectPromptBeforeError(prompt);
|
||||
await creation.submitPrompt("emit 1 coalesced agent stream updates for a corrected prompt.");
|
||||
await creation.expectPromptVisible(
|
||||
"emit 1 coalesced agent stream updates for a corrected prompt.",
|
||||
);
|
||||
await creation.expectAssistantReply();
|
||||
await creation.expectAgentCount(1);
|
||||
await expect(page.getByText("agent_request_key_conflict", { exact: true })).toHaveCount(0);
|
||||
});
|
||||
}
|
||||
|
||||
@@ -13,6 +13,7 @@ import { delayBrowserAgentCreatedStatus } from "./helpers/new-workspace";
|
||||
|
||||
export const test = base.extend<{
|
||||
startup: { release(): Promise<void>; fail(): Promise<void> };
|
||||
promptRejection: void;
|
||||
creation: Awaited<ReturnType<typeof createCreationScenario>>;
|
||||
promptRetry: ReturnType<typeof createPromptRetryScenario>;
|
||||
agentRetries: Awaited<ReturnType<typeof retryNextAgentCreation>>;
|
||||
@@ -65,6 +66,37 @@ export default function contribute(server) {
|
||||
await client.close();
|
||||
}
|
||||
},
|
||||
promptRejection: async ({ page }, provide) => {
|
||||
void page;
|
||||
const client = await connectNewWorkspaceDaemonClient();
|
||||
const plugin = await copyPluginExample("lifecycle-logger");
|
||||
const previous = await client.getDaemonConfig();
|
||||
try {
|
||||
await writeFile(
|
||||
path.join(plugin.directory, "index.server.ts"),
|
||||
`
|
||||
export default function contribute(server) {
|
||||
return server.before("agent.create", ({ request }) => ({
|
||||
...request,
|
||||
config: {
|
||||
...request.config,
|
||||
model: "e2e-fast-stream",
|
||||
featureValues: { ...request.config.featureValues, mockPromptRejections: 1 },
|
||||
},
|
||||
}));
|
||||
}
|
||||
`,
|
||||
);
|
||||
await client.patchDaemonConfig({ pluginsEnabled: true });
|
||||
await client.installDirectoryPlugin(plugin.directory);
|
||||
await provide();
|
||||
} finally {
|
||||
await client.removePlugin("lifecycle-logger");
|
||||
await client.patchDaemonConfig({ pluginsEnabled: previous.config.pluginsEnabled });
|
||||
await plugin.cleanup();
|
||||
await client.close();
|
||||
}
|
||||
},
|
||||
creation: async ({ page }, provide) => {
|
||||
const creation = await createCreationScenario(page);
|
||||
try {
|
||||
|
||||
@@ -182,6 +182,47 @@ export async function createCreationScenario(page: Page) {
|
||||
await this.expectWorkspaceReadyBeforeAgentCompletion();
|
||||
expect((await project.client.fetchAgents()).entries).toHaveLength(0);
|
||||
},
|
||||
async expectCreatedAgentError() {
|
||||
await requests.settled();
|
||||
await expect(
|
||||
page
|
||||
.getByTestId("assistant-message")
|
||||
.filter({ hasText: "[System Error] Requested mock prompt rejection", visible: true }),
|
||||
).toBeVisible();
|
||||
await expect(
|
||||
page
|
||||
.locator('[data-testid^="workspace-tab-agent_"][aria-selected="true"]')
|
||||
.filter({ visible: true }),
|
||||
).toBeVisible();
|
||||
await expect(
|
||||
page.locator('[data-testid^="workspace-tab-draft_"]').filter({ visible: true }),
|
||||
).toHaveCount(0);
|
||||
await expect(page.getByRole("textbox", { name: "Message agent..." }).first()).toBeEditable();
|
||||
await expect(page.getByTestId("turn-working-indicator")).toHaveCount(0);
|
||||
},
|
||||
async expectPromptBeforeError(prompt: string) {
|
||||
const messages = page
|
||||
.getByTestId("user-message")
|
||||
.or(page.getByTestId("assistant-message"))
|
||||
.filter({ visible: true });
|
||||
await expect(messages).toHaveCount(2);
|
||||
await expect(messages.nth(0)).toContainText(prompt);
|
||||
await expect(messages.nth(1)).toContainText("[System Error]");
|
||||
await expect(messages.nth(1)).toBeInViewport();
|
||||
},
|
||||
async reloadAgent() {
|
||||
await page.reload();
|
||||
await expect(page.getByText("Updating messages", { exact: true })).toHaveCount(0);
|
||||
await this.expectCreatedAgentError();
|
||||
},
|
||||
async expectAssistantReply() {
|
||||
await expect(
|
||||
page
|
||||
.getByTestId("assistant-message")
|
||||
.filter({ visible: true, hasNotText: "[System Error]" })
|
||||
.first(),
|
||||
).toBeVisible();
|
||||
},
|
||||
async expectStartupFailure() {
|
||||
await expect(page.getByText(/Creation startup failed for test/).first()).toBeVisible();
|
||||
},
|
||||
|
||||
Reference in New Issue
Block a user