Files
copilotkit__copilotkit/showcase/integrations/google-adk/tests/e2e/tool-rendering.spec.ts
Tyler Slaton ef1ca9808c feat(showcase/google-adk): QA-blitz parity ports — agent prompts, tool surface, e2e specs
Result of 10 parallel QA agents auditing all 30 active demos against
langgraph-python (north-star). Each agent ported drift back to LP-verbatim
across three axes:

1. Agent layer
   - tool_rendering_common.py: rebuilt to LP's surface — get_weather,
     search_flights(origin, destination), get_stock_price, roll_d20,
     roll_dice. Removed the ADK-only query_data.
   - tool_rendering_*_agent.py (4 variants): ported LP's travel/concierge
     prompt; reasoning-chain variant got LP's chain-two-tools prompt.
   - beautiful_chat_agent.py: ported LP's per-tool system prompt; added
     manage_sales_todos / get_sales_todos / generate_a2ui; dropped the
     redundant schedule_meeting (frontend HITL handles it).
   - open_gen_ui_agents.py: ported LP's full SYSTEM_PROMPT for both
     variants, including the Websandbox.connection.remote.* contract
     for the advanced sandbox demo (was `window.sandbox.*`, which the
     LP frontend's Websandbox bridge silently no-ops).
   - byoc_agents.py: fused LP's hashbrown + json-render prompts so the
     single ADK byoc_agent emits both wire shapes. Aliases exported for
     a future per-route split.
   - declarative_gen_ui_agent.py: ported LP's a2ui_dynamic SYSTEM_PROMPT.
   - a2ui_fixed_agent.py: picked up LP's #4734 regression guard
     ("exactly ONCE", "do NOT call again").
   - agent_config_agent.py: rewrote to read useAgentContext (was
     state["config"]); reconciled schema to LP's 3-field camelCase
     {tone, expertise, responseLength} with LP's value enums.
   - subagents_agent.py: dropped the "running" placeholder; returns
     plain str so the LP-verbatim frontend's `result?.trim()` works.
   - hitl_in_app_agent.py / hitl_in_chat_book_call_agent.py: prompts +
     tool-result shape ({approved, reason}) aligned to LP.
   - AGUIToolset() added wherever it was missing on the bespoke agents
     (multimodal, mcp_apps, a2ui_fixed) so frontend-registered tools
     reach the model.

2. Dedicated runtime routes
   - copilotkit-multimodal/route.ts (new) — mirrors LP shape with
     ADK's HttpAgent + AGENT_URL pattern.
   - copilotkit-agent-config/route.ts (new) — same pattern.
   - copilotkit-mcp-apps/route.ts — refreshed.

3. Frontend ports (ADK frontend brought to LP-verbatim where it had
   drifted from the parity blitz state)
   - tool-rendering family (4 demos): full re-port — WeatherCard,
     FlightListCard, StockCard, D20Card, ReasoningBlock, CatchallRenderer,
     suggestions, and the page wiring with all useRenderTool /
     useDefaultRenderTool / reasoningMessage registrations.
   - a2ui-fixed-schema, mcp-apps, multimodal: full frontend re-ports
     with their _components/ Tailwind primitives.
   - frontend-tools, frontend-tools-async, agent-config: ported LP's
     component structure (separate Background, NotesCard with query_notes,
     config-context-relay).
   - shared-state-read, shared-state-read-write, readonly-state-agent-context:
     ported LP's demo-layout + _components + suggestions. recipe-card.tsx
     pulled directly from LP (one QA agent had adapted to Unicode glyphs
     thinking ADK lacked lucide-react — it doesn't, after the parity blitz).
   - shared-state-streaming, subagents, hitl-in-app: ported LP's
     DocumentView / supervisor-activity / TicketsPanel structure.
     hitl-in-app/page.tsx pulled directly from LP to keep the hyphenated
     agent slug aligned with the renamed registry key.
   - auth, hitl-in-chat: ported LP's SignInCard-first auth UX and the
     time-picker Tailwind port.
   - prebuilt-popup: pulled LP's main-content + suggestions split.

4. Test fixtures
   - 30 tests/e2e/<slug>.spec.ts ported from LP, several overwriting
     stale stubs (shared-state-streaming, subagents, auth, hitl-in-chat,
     shared-state-read, agent-config).
   - 30 qa/<slug>.md ported from LP with ADK env-var and registry
     references substituted (GOOGLE_API_KEY, AGENT_URL, registry.py).
   - QA3's byoc-hashbrown / byoc-json-render specs renamed to
     declarative-hashbrown / declarative-json-render with internal
     URL references substituted (the orchestrator pass had already
     renamed the demo dirs + manifest entries).

Frontend changes from QA agents were filtered: kept where they ported
LP-verbatim into ADK, replaced with direct LP pulls where the agent
had made ADK-specific adaptations (one Unicode-glyph case, one
stale-registry-slug case).

Not touched per blitz rules: shared_chat.py, registry.py, manifest.yaml,
src/app/api/copilotkit/route.ts.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-12 17:58:06 -07:00

165 lines
5.2 KiB
TypeScript

import { test, expect } from "@playwright/test";
// QA reference: qa/tool-rendering.md
// Demo source: src/app/demos/tool-rendering/page.tsx
//
// Pill-driven 6-test plan. The cell registers a per-tool useRenderTool
// for every "interesting" tool (get_weather, search_flights,
// get_stock_price, roll_d20) plus a wildcard catch-all. Each pill
// drives the corresponding tool path and asserts on the per-tool
// branded card's stable testid plus deterministic fixture values.
//
// Aimock fixtures live in showcase/aimock/d5-all.json and pin every
// pill prompt to a deterministic tool-call sequence.
const SUGGESTION_TIMEOUT = 15000;
const TOOL_TIMEOUT = 60000;
test.describe("Tool Rendering", () => {
test.beforeEach(async ({ page }) => {
await page.goto("/demos/tool-rendering");
await expect(page.getByPlaceholder("Type a message")).toBeVisible({
timeout: SUGGESTION_TIMEOUT,
});
});
test("page loads with composer and 5 suggestion pills", async ({ page }) => {
const suggestions = page.locator('[data-testid="copilot-suggestion"]');
for (const title of [
"Weather in SF",
"Find flights",
"Stock price",
"Roll a d20",
"Chain tools",
]) {
await expect(suggestions.filter({ hasText: title }).first()).toBeVisible({
timeout: SUGGESTION_TIMEOUT,
});
}
});
test("Weather in SF pill renders the SF weather card", async ({ page }) => {
await page
.locator('[data-testid="copilot-suggestion"]')
.filter({ hasText: "Weather in SF" })
.first()
.click();
const card = page.locator('[data-testid="weather-card"]').first();
await expect(card).toBeVisible({ timeout: TOOL_TIMEOUT });
await expect(card.locator('[data-testid="weather-city"]')).toContainText(
"San Francisco",
{ timeout: TOOL_TIMEOUT },
);
await expect(
card.locator('[data-testid="weather-humidity"]'),
).toContainText("55%", { timeout: TOOL_TIMEOUT });
await expect(card.locator('[data-testid="weather-wind"]')).toContainText(
"10",
{ timeout: TOOL_TIMEOUT },
);
});
test("Find flights pill renders the flights card with deterministic flights", async ({
page,
}) => {
await page
.locator('[data-testid="copilot-suggestion"]')
.filter({ hasText: "Find flights" })
.first()
.click();
const card = page.locator('[data-testid="flights-card"]').first();
await expect(card).toBeVisible({ timeout: TOOL_TIMEOUT });
await expect(card.locator('[data-testid="flight-origin"]')).toContainText(
"SFO",
{ timeout: TOOL_TIMEOUT },
);
await expect(
card.locator('[data-testid="flight-destination"]'),
).toContainText("JFK", { timeout: TOOL_TIMEOUT });
// At least 2 flight rows from the deterministic fixture (NOT the
// a2ui beautiful-chat boilerplate — a2ui shows a different shell).
const rows = card.locator('[data-testid="flight-row"]');
await expect
.poll(async () => rows.count(), { timeout: TOOL_TIMEOUT })
.toBeGreaterThanOrEqual(2);
});
test("Stock price pill renders the AAPL stock card", async ({ page }) => {
await page
.locator('[data-testid="copilot-suggestion"]')
.filter({ hasText: "Stock price" })
.first()
.click();
const card = page.locator('[data-testid="stock-card"]').first();
await expect(card).toBeVisible({ timeout: TOOL_TIMEOUT });
await expect(card.locator('[data-testid="stock-ticker"]')).toHaveText(
"AAPL",
{ timeout: TOOL_TIMEOUT },
);
await expect(card.locator('[data-testid="stock-price"]')).toContainText(
"$338.37",
{ timeout: TOOL_TIMEOUT },
);
await expect(card.locator('[data-testid="stock-change"]')).toContainText(
"-2.96%",
{ timeout: TOOL_TIMEOUT },
);
});
test("Roll a d20 pill produces exactly 5 d20 cards, last result is 20", async ({
page,
}) => {
await page
.locator('[data-testid="copilot-suggestion"]')
.filter({ hasText: "Roll a d20" })
.first()
.click();
const cards = page.locator('[data-testid="d20-card"]');
// Wait for all 5 sequential rolls to land.
await expect
.poll(async () => cards.count(), { timeout: TOOL_TIMEOUT })
.toBe(5);
// Final roll is a 20.
await expect(cards.nth(4).locator('[data-testid="d20-value"]')).toHaveText(
"20",
{ timeout: TOOL_TIMEOUT },
);
// First 4 rolls are non-20.
for (let i = 0; i < 4; i++) {
const value = await cards
.nth(i)
.locator('[data-testid="d20-value"]')
.innerText();
expect(value.trim()).not.toBe("20");
}
});
test("Chain tools pill renders weather + flights + d20 cards in one turn", async ({
page,
}) => {
await page
.locator('[data-testid="copilot-suggestion"]')
.filter({ hasText: "Chain tools" })
.first()
.click();
await expect(
page.locator('[data-testid="weather-card"]').first(),
).toBeVisible({ timeout: TOOL_TIMEOUT });
await expect(
page.locator('[data-testid="flights-card"]').first(),
).toBeVisible({ timeout: TOOL_TIMEOUT });
await expect(page.locator('[data-testid="d20-card"]').first()).toBeVisible({
timeout: TOOL_TIMEOUT,
});
});
});