mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
5cd77233b7
Brings ms-agent-python to one-to-one parity with langgraph-python (the D5
north star). Playwright e2e suite goes from 49/108 (~26%) → 164/178 (~92%),
33 of 37 cells fully green.
Manifest parity:
- Drop 4 MAF-only cells with no LGP analog: agentic-chat-reasoning,
hitl-in-chat-booking, shared-state-write, reasoning-default-render.
Reasoning is handled by reasoning-default + reasoning-custom (LGP);
booking pill folds into hitl-in-chat; shared-state-write was a TODO stub.
- Rename byoc-hashbrown → declarative-hashbrown and byoc-json-render →
declarative-json-render. Demo dir, API route dir, and frontend agent id
follow LGP's naming. Python module files retain the legacy `byoc_*`
prefix and FastAPI paths stay `/byoc-hashbrown` / `/byoc-json-render`
(matches LGP's "module name retains legacy graph id" convention).
- Port LGP `_shared/`, `_shared/interrupt-fallback-slots.ts`, and
`demos/layout.tsx` for one-to-one parity.
Cells ported verbatim from LGP (page + spec):
- agentic-chat, auth, beautiful-chat, chat-customization-css, chat-slots,
declarative-gen-ui, declarative-hashbrown, declarative-json-render,
frontend-tools, frontend-tools-async, gen-ui-agent, gen-ui-interrupt,
gen-ui-tool-based, headless-complete, headless-simple, hitl-in-app,
hitl-in-chat, shared-state-read, shared-state-read-write,
shared-state-streaming, subagents, tool-rendering, plus all four
tool-rendering* variants, a2ui-fixed-schema, agent-config, mcp-apps,
multimodal, open-gen-ui, open-gen-ui-advanced, prebuilt-popup,
prebuilt-sidebar, readonly-state-agent-context, reasoning-default,
reasoning-custom, voice.
Backend infrastructure:
- Swap shared `OpenAIChatClient` (Responses API) → `OpenAIChatCompletionClient`
(ChatCompletions). Root cause of the cross-cell post-tool ChatClientException
family: Responses API is stateful and only sends NEW items per leg,
relying on `previous_response_id` for history. aimock has no view of
that server-side state, so second-leg requests arrived without the
user message — fixture matchers keyed on `userMessage` couldn't fire
and the run fell through to real OpenAI. ChatCompletions sends full
history every leg, matching the LGP wire shape.
- Bump @ag-ui/client ^0.0.43 → ^0.0.53 (matches google-adk/LGP). Fixes
the REASONING_* Zod discriminator trap on the catch-all agent.
- Regenerate package-lock.json in isolation outside the pnpm monorepo so
npm-arborist doesn't resolve transitives against pnpm's hoisted
symlinks (avoid 40+ `../../../node_modules/.pnpm/...` paths in the
lockfile that break `npm ci` inside Docker).
- Add `yaml` (^2.8.4) for the new `src/app/demos/layout.tsx` that reads
manifest.yaml for per-cell page titles (LGP parity).
New / re-added MAF agent backends with LGP-equivalent behavior:
- reasoning_agent.py (uses Responses API explicitly — the only chat
client that emits AG-UI REASONING_MESSAGE_* events; rest of the
integration stays on ChatCompletions).
- tool_rendering_agent.py (non-reasoning sibling of the existing
reasoning_chain variant; shares tool surface via direct imports so
they can never drift apart; routes the three catchall cells to a
non-reasoning backend so the default renderer spec stops failing on
leaked reasoning blocks).
- gen_ui_agent.py — `set_steps` tool + `steps` state schema +
`predict_state_config` mirrors LGP's StateStreamingMiddleware shape.
- shared_state_streaming.py — `write_document` tool with
`predict_state_config` that streams the `document` arg into
`state.document` per-token.
- readonly_state_agent_context.py — minimal agent that consumes
frontend-provided `useAgentContext` entries; no tools.
- headless_complete_agent.py — three deterministic tools (`get_weather`,
`get_stock_price`, `get_revenue_chart`) mounted at /headless-complete
on the mcp-apps runtime (was routing to catch-all sales agent, which
returned seeded-random weather instead of the deterministic 68°F the
test asserts on).
Wiring:
- copilotkit/route.ts: register the new agents, drop the stale
shared-state-write entry, route all three tool-rendering variants to
the non-reasoning backend (the reasoning-chain cell keeps its own
dedicated path), register reasoning-default + reasoning-custom on
/reasoning, register gen-ui-agent on /gen-ui-agent,
shared-state-streaming on /shared-state-streaming,
readonly-state-agent-context on its dedicated path.
- copilotkit-mcp-apps/route.ts: register headless-complete agent (was
missing — the strict useAgent runtime sync in the newer
@copilotkit/react-core surfaced the gap).
- copilotkit-declarative-hashbrown/route.ts + copilotkit-declarative-json-render/route.ts:
new dedicated runtimes; agent IDs and runtime URLs follow LGP.
- copilotkit-declarative-gen-ui/route.ts: drop non-LGP `openGenerativeUI:
false` for parity.
A2UI tool rename — `render_a2ui` → `_design_a2ui_surface`:
- Ported LGP's `tools/generate_a2ui.py` (LGP renamed the secondary-LLM
tool to `_design_a2ui_surface` to avoid the A2UI middleware's bypass;
shared d5-all.json fixtures key the response on this name).
- Renamed every `render_a2ui` occurrence in src/agents/{a2ui_dynamic,
agent,beautiful_chat}.py and `tools/__init__.py`.
- Updated 4 declarative-gen-ui aimock fixtures to pass `context` arg in
the first-leg `generate_a2ui` tool call (agent_framework doesn't
auto-inject AgentSession into our @tool function so `session=None` and
the secondary-LLM `user_content` was defaulting to a catch-all string
containing "KPI dashboard" — every pill matched the KPI fixture).
Aimock router patch persisted alongside the integration changes:
hasToolResult matcher restricted to scan only messages after the last
user message (was global). The patch lives in F:/projects/cpk/aimock —
upstream PR pending.
Test infrastructure:
- playwright.config.ts: cap local workers at 4 + retries at 1. CI keeps
workers=1, retries=2. `agent_framework.Agent` is reused across requests
and the shared OpenAI HTTP client serialises concurrent SSE streams;
>4 workers makes 30s timeouts inevitable on a few cells. Confirmed
with hard data: workers=1 = 164 passed (16.8 min), workers=4+retries=1
= 164 passed (7.2 min), workers=undefined = 159 passed. Same green
set, ~2x faster. Long-term upstream fix is per-request Agent
instantiation in agent_framework_ag_ui.
Remaining 14 failures across 4 cells documented per-cell in the Notion
D5 sweep doc (declarative-gen-ui A2UI surface mounting, multimodal
attachment forwarding, tool-rendering-default-catchall multi-pill chain,
tool-rendering-reasoning-chain multi-leg chains). Each has a specific
next-pass action.
230 lines
8.9 KiB
TypeScript
230 lines
8.9 KiB
TypeScript
import { test, expect } from "@playwright/test";
|
|
|
|
// QA reference: qa/open-gen-ui-advanced.md
|
|
// Demo source: src/app/demos/open-gen-ui-advanced/{page.tsx,
|
|
// sandbox-functions.ts, suggestions.ts}
|
|
// Aimock fixture: showcase/aimock/d5-all.json (entries keyed by the
|
|
// verbatim suggestion `message` strings)
|
|
//
|
|
// Advanced Open-Gen-UI: each prompt triggers a deterministic
|
|
// `generateSandboxedUi` tool call whose `jsFunctions` wires in-iframe
|
|
// click handlers to the two host-side sandbox functions registered in
|
|
// `sandbox-functions.ts` via `Websandbox.connection.remote.*`.
|
|
//
|
|
// Two layers of assertions:
|
|
// 1. SMOKE — each prompt produces an iframe with a non-empty `srcdoc`.
|
|
// Confirms the open-gen-ui pipeline mounted SOMETHING.
|
|
// 2. ROUND-TRIP — driving the iframe's buttons fires the host-side
|
|
// handler (observed via the handler's `console.log`) AND updates
|
|
// the iframe's output element with the host response. Confirms
|
|
// the fixture's `jsFunctions` is wired correctly. Catches the
|
|
// regression where a fixture ships HTML+CSS only and every button
|
|
// becomes a silent no-op.
|
|
//
|
|
// Iframe driving works because the fixture HTML is deterministic
|
|
// (stable `#hi`, `#in`, `#go`, `#eq`, `#d`, `#out` selectors) and
|
|
// Playwright `frameLocator` can interact with `sandbox="allow-scripts"`
|
|
// iframes via CDP regardless of the null origin.
|
|
//
|
|
// Composer drive note: we send the prompt by filling the textarea and
|
|
// pressing Enter rather than clicking a suggestion pill. The demo has
|
|
// two chip surfaces (EmptyState vs SuggestionBar) whose mount depends
|
|
// on `messages.length`, which makes pill clicks timing-flaky — see
|
|
// commit 15db0bbf3 (gen-ui-headless-complete: drive via textarea, not
|
|
// chip click). Chip-click and textarea-Enter dispatch the same
|
|
// `runAgent`, so the fixture matcher catches either route and the
|
|
// textarea is always present.
|
|
//
|
|
// Aimock priority note: each pill `message` string is a verbatim short
|
|
// label that matches a high-priority entry in `d5-all.json`. d5-all.json
|
|
// loads BEFORE feature-parity.json, so its first-match-wins ordering
|
|
// beats the broad `userMessage: "hi"` catch-all in feature-parity.json
|
|
// that would otherwise return the showcase-assistant boilerplate
|
|
// greeting. Keep pill message strings in `suggestions.ts` aligned with
|
|
// the fixture keys.
|
|
|
|
// Verbatim `message` values from src/app/demos/open-gen-ui-advanced/suggestions.ts.
|
|
const PROMPTS = {
|
|
calculator: "Calculator (calls evaluateExpression)",
|
|
ping: "Ping the host (calls notifyHost)",
|
|
inlineEval: "Inline expression evaluator",
|
|
};
|
|
|
|
test.describe("Open Generative UI (advanced)", () => {
|
|
test.setTimeout(120_000);
|
|
|
|
test.beforeEach(async ({ page }) => {
|
|
await page.goto("/demos/open-gen-ui-advanced");
|
|
// Wait for React hydration: without this the textarea's keydown
|
|
// handler may not yet be attached when fill+Enter runs, so the
|
|
// Enter press becomes a no-op and the iframe never mounts.
|
|
await page
|
|
.waitForLoadState("networkidle", { timeout: 15_000 })
|
|
.catch(() => {});
|
|
});
|
|
|
|
test("page loads with chat composer and 3 suggestion pills", async ({
|
|
page,
|
|
}) => {
|
|
await expect(page.getByPlaceholder("Type a message")).toBeVisible({
|
|
timeout: 15_000,
|
|
});
|
|
|
|
// Suggestion titles are verbatim from openGenUiSuggestions.
|
|
const expected = [
|
|
"Calculator",
|
|
"Ping the host",
|
|
"Inline expression evaluator",
|
|
];
|
|
const suggestions = page.locator('[data-testid="copilot-suggestion"]');
|
|
for (const title of expected) {
|
|
await expect(suggestions.filter({ hasText: title }).first()).toBeVisible({
|
|
timeout: 15_000,
|
|
});
|
|
}
|
|
});
|
|
|
|
const sendPromptAndAwaitIframe = async (
|
|
page: import("@playwright/test").Page,
|
|
prompt: string,
|
|
) => {
|
|
// Use the stable testid (not getByPlaceholder): the chat composer's
|
|
// textarea wires onKeyDown only after React hydration, and the
|
|
// testid locator + an explicit click force focus + handler attach
|
|
// before fill, preventing a flaky Enter-as-no-op race.
|
|
const textarea = page.locator('[data-testid="copilot-chat-textarea"]');
|
|
await expect(textarea).toBeVisible({ timeout: 15_000 });
|
|
await textarea.click();
|
|
await textarea.fill(prompt);
|
|
await textarea.press("Enter");
|
|
|
|
const iframe = page.locator('iframe[sandbox*="allow-scripts"]').first();
|
|
await expect(iframe).toBeVisible({ timeout: 60_000 });
|
|
|
|
await expect
|
|
.poll(
|
|
async () => {
|
|
const srcdoc = await iframe.getAttribute("srcdoc");
|
|
if (srcdoc && srcdoc.length > 0) return true;
|
|
const src = await iframe.getAttribute("src");
|
|
if (src && src.length > 0) return true;
|
|
return false;
|
|
},
|
|
{ timeout: 30_000 },
|
|
)
|
|
.toBe(true);
|
|
};
|
|
|
|
test("Inline expression evaluator prompt renders a sandboxed iframe with non-empty source", async ({
|
|
page,
|
|
}) => {
|
|
await sendPromptAndAwaitIframe(page, PROMPTS.inlineEval);
|
|
});
|
|
|
|
test("Calculator prompt renders a sandboxed iframe with non-empty source", async ({
|
|
page,
|
|
}) => {
|
|
await sendPromptAndAwaitIframe(page, PROMPTS.calculator);
|
|
});
|
|
|
|
test("Ping the host prompt renders a sandboxed iframe with non-empty source", async ({
|
|
page,
|
|
}) => {
|
|
await sendPromptAndAwaitIframe(page, PROMPTS.ping);
|
|
});
|
|
|
|
// ── Round-trip tests ────────────────────────────────────────────────
|
|
//
|
|
// Drive the in-iframe controls and assert the host-side sandbox-function
|
|
// handler ran. The handlers in `sandbox-functions.ts` log to the host
|
|
// console with a stable `[open-gen-ui/advanced]` prefix; Playwright's
|
|
// `page.on('console')` catches those even though the call originates
|
|
// inside the sandboxed iframe (the handler runs on the host page).
|
|
|
|
const captureHostHandlerLogs = (
|
|
page: import("@playwright/test").Page,
|
|
needle: string,
|
|
): string[] => {
|
|
const logs: string[] = [];
|
|
page.on("console", (msg) => {
|
|
const text = msg.text();
|
|
if (text.includes("[open-gen-ui/advanced]") && text.includes(needle)) {
|
|
logs.push(text);
|
|
}
|
|
});
|
|
return logs;
|
|
};
|
|
|
|
test("Ping the host prompt: in-iframe click fires host notifyHost handler", async ({
|
|
page,
|
|
}) => {
|
|
const hostLogs = captureHostHandlerLogs(page, "notifyHost");
|
|
|
|
await sendPromptAndAwaitIframe(page, PROMPTS.ping);
|
|
|
|
const frame = page.frameLocator('iframe[sandbox*="allow-scripts"]').first();
|
|
await frame.locator("#hi").click();
|
|
|
|
await expect
|
|
.poll(() => hostLogs.length, { timeout: 30_000 })
|
|
.toBeGreaterThan(0);
|
|
expect(hostLogs.some((l) => l.includes("Hello from sandbox"))).toBe(true);
|
|
|
|
// Iframe output element must reflect the host's `receivedAt` reply.
|
|
await expect(frame.locator("#out")).toContainText("host replied at", {
|
|
timeout: 10_000,
|
|
});
|
|
});
|
|
|
|
test("Inline expression evaluator prompt: typing + clicking Evaluate fires host evaluateExpression handler", async ({
|
|
page,
|
|
}) => {
|
|
const hostLogs = captureHostHandlerLogs(page, "evaluateExpression");
|
|
|
|
await sendPromptAndAwaitIframe(page, PROMPTS.inlineEval);
|
|
|
|
const frame = page.frameLocator('iframe[sandbox*="allow-scripts"]').first();
|
|
// `fill()` silently no-ops inside sandbox="allow-scripts" iframes on
|
|
// some Playwright/Chromium combos (null origin blocks the set-value
|
|
// protocol message). `pressSequentially` sends individual key events
|
|
// that always reach the input regardless of sandbox restrictions.
|
|
const input = frame.locator("#in");
|
|
await input.click();
|
|
await input.pressSequentially("2+2");
|
|
await frame.locator("#go").click();
|
|
|
|
await expect
|
|
.poll(() => hostLogs.length, { timeout: 30_000 })
|
|
.toBeGreaterThan(0);
|
|
// Handler logs `evaluateExpression <expr> = <value>` — verify the value.
|
|
expect(hostLogs.some((l) => /=\s*4\b/.test(l))).toBe(true);
|
|
|
|
await expect(frame.locator("#out")).toContainText("= 4", {
|
|
timeout: 10_000,
|
|
});
|
|
});
|
|
|
|
test("Calculator prompt: digit + operator + '=' fires host evaluateExpression handler", async ({
|
|
page,
|
|
}) => {
|
|
const hostLogs = captureHostHandlerLogs(page, "evaluateExpression");
|
|
|
|
await sendPromptAndAwaitIframe(page, PROMPTS.calculator);
|
|
|
|
const frame = page.frameLocator('iframe[sandbox*="allow-scripts"]').first();
|
|
// Build `2+3` then evaluate. Each digit/operator is a separate
|
|
// <button>; `=` has id="eq".
|
|
await frame.getByRole("button", { name: "2", exact: true }).click();
|
|
await frame.getByRole("button", { name: "+", exact: true }).click();
|
|
await frame.getByRole("button", { name: "3", exact: true }).click();
|
|
await frame.locator("#eq").click();
|
|
|
|
await expect
|
|
.poll(() => hostLogs.length, { timeout: 30_000 })
|
|
.toBeGreaterThan(0);
|
|
expect(hostLogs.some((l) => /=\s*5\b/.test(l))).toBe(true);
|
|
|
|
await expect(frame.locator("#d")).toHaveText("5", { timeout: 10_000 });
|
|
});
|
|
});
|