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.
154 lines
5.8 KiB
TypeScript
154 lines
5.8 KiB
TypeScript
import { test, expect } from "@playwright/test";
|
|
|
|
/**
|
|
* Auth demo lifecycle. The demo defaults to UNAUTHENTICATED on first
|
|
* paint and renders SignInCard. After sign-in, <CopilotKit> mounts with
|
|
* the bearer header attached and the chat boots. After sign-out the
|
|
* chat STAYS MOUNTED (now with no Authorization header) so the user can
|
|
* actually watch the runtime reject an unauthenticated send — that is
|
|
* the whole point of the demo. The AuthBanner flips between green
|
|
* (authenticated) and amber (signed-out) variants. Only a full page
|
|
* reload resets to the SignInCard first-paint state.
|
|
*/
|
|
test.describe("Authentication", () => {
|
|
test.beforeEach(async ({ page }) => {
|
|
await page.goto("/demos/auth");
|
|
});
|
|
|
|
test("page loads unauthenticated with SignInCard visible", async ({
|
|
page,
|
|
}) => {
|
|
await expect(
|
|
page.locator('[data-testid="auth-sign-in-card"]'),
|
|
).toBeVisible();
|
|
await expect(
|
|
page.locator('[data-testid="auth-sign-in-button"]'),
|
|
).toBeEnabled();
|
|
await expect(page.locator('[data-testid="auth-demo-token"]')).toBeVisible();
|
|
// Chat surface and AuthBanner only render after the first sign-in.
|
|
await expect(page.locator('[data-testid="auth-banner"]')).toHaveCount(0);
|
|
await expect(page.getByPlaceholder("Type a message")).toHaveCount(0);
|
|
});
|
|
|
|
test("signing in mounts the chat surface with AuthBanner", async ({
|
|
page,
|
|
}) => {
|
|
await page.locator('[data-testid="auth-sign-in-button"]').click();
|
|
|
|
const banner = page.locator('[data-testid="auth-banner"]');
|
|
await expect(banner).toBeVisible();
|
|
await expect(banner).toHaveAttribute("data-authenticated", "true");
|
|
await expect(page.locator('[data-testid="auth-status"]')).toContainText(
|
|
"Signed in",
|
|
);
|
|
await expect(
|
|
page.locator('[data-testid="auth-sign-out-button"]'),
|
|
).toBeEnabled();
|
|
await expect(page.getByPlaceholder("Type a message")).toBeVisible();
|
|
// SignInCard is gone once we're authenticated.
|
|
await expect(page.locator('[data-testid="auth-sign-in-card"]')).toHaveCount(
|
|
0,
|
|
);
|
|
});
|
|
|
|
test("authenticated send produces an assistant response", async ({
|
|
page,
|
|
}) => {
|
|
await page.locator('[data-testid="auth-sign-in-button"]').click();
|
|
await expect(page.getByPlaceholder("Type a message")).toBeVisible();
|
|
|
|
const input = page.getByPlaceholder("Type a message");
|
|
await input.fill("Say hello in one short sentence");
|
|
await input.press("Enter");
|
|
|
|
await expect(
|
|
page.locator('[data-testid="copilot-assistant-message"]').first(),
|
|
).toBeVisible({ timeout: 30000 });
|
|
});
|
|
|
|
test("signing out flips the banner amber and keeps the chat surface mounted", async ({
|
|
page,
|
|
}) => {
|
|
await page.locator('[data-testid="auth-sign-in-button"]').click();
|
|
await expect(
|
|
page.locator('[data-testid="auth-sign-out-button"]'),
|
|
).toBeVisible();
|
|
|
|
await page.locator('[data-testid="auth-sign-out-button"]').click();
|
|
|
|
// Banner flips to the amber variant. SignInCard does NOT come back —
|
|
// the demo would never get to showcase the rejection if it did.
|
|
const banner = page.locator('[data-testid="auth-banner"]');
|
|
await expect(banner).toBeVisible();
|
|
await expect(banner).toHaveAttribute("data-authenticated", "false");
|
|
await expect(page.locator('[data-testid="auth-status"]')).toContainText(
|
|
"Signed out",
|
|
);
|
|
await expect(
|
|
page.locator('[data-testid="auth-authenticate-button"]'),
|
|
).toBeVisible();
|
|
await expect(
|
|
page.locator('[data-testid="auth-sign-out-button"]'),
|
|
).toHaveCount(0);
|
|
await expect(page.locator('[data-testid="auth-sign-in-card"]')).toHaveCount(
|
|
0,
|
|
);
|
|
await expect(page.getByPlaceholder("Type a message")).toBeVisible();
|
|
});
|
|
|
|
test("unauthenticated send surfaces a 401 error without crashing the page", async ({
|
|
page,
|
|
}) => {
|
|
await page.locator('[data-testid="auth-sign-in-button"]').click();
|
|
await expect(page.getByPlaceholder("Type a message")).toBeVisible();
|
|
await page.locator('[data-testid="auth-sign-out-button"]').click();
|
|
await expect(
|
|
page.locator('[data-testid="auth-authenticate-button"]'),
|
|
).toBeVisible();
|
|
|
|
// After sign-out, the next send must surface the rejection — not
|
|
// produce an assistant response and not white-screen the page.
|
|
const input = page.getByPlaceholder("Type a message");
|
|
await input.fill("Tell me a one-line joke");
|
|
await input.press("Enter");
|
|
|
|
const errorSurface = page.locator('[data-testid="auth-demo-error"]');
|
|
await expect(errorSurface).toBeVisible({ timeout: 15000 });
|
|
// Page chrome stays visible — no white-screen.
|
|
await expect(page.locator('[data-testid="auth-banner"]')).toBeVisible();
|
|
await expect(
|
|
page.locator('[data-testid="copilot-assistant-message"]'),
|
|
).toHaveCount(0);
|
|
});
|
|
|
|
test("re-signing in from the amber banner clears the error and resumes chat", async ({
|
|
page,
|
|
}) => {
|
|
await page.locator('[data-testid="auth-sign-in-button"]').click();
|
|
await expect(
|
|
page.locator('[data-testid="auth-sign-out-button"]'),
|
|
).toBeVisible();
|
|
await page.locator('[data-testid="auth-sign-out-button"]').click();
|
|
await expect(
|
|
page.locator('[data-testid="auth-authenticate-button"]'),
|
|
).toBeVisible();
|
|
|
|
await page.locator('[data-testid="auth-authenticate-button"]').click();
|
|
const banner = page.locator('[data-testid="auth-banner"]');
|
|
await expect(banner).toHaveAttribute("data-authenticated", "true", {
|
|
timeout: 5000,
|
|
});
|
|
await expect(page.locator('[data-testid="auth-demo-error"]')).toHaveCount(
|
|
0,
|
|
);
|
|
|
|
// Chat is responsive again.
|
|
const input = page.getByPlaceholder("Type a message");
|
|
await input.fill("Give me a fun fact");
|
|
await input.press("Enter");
|
|
await expect(
|
|
page.locator('[data-testid="copilot-assistant-message"]').first(),
|
|
).toBeVisible({ timeout: 30000 });
|
|
});
|
|
});
|