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.
254 lines
8.7 KiB
TypeScript
254 lines
8.7 KiB
TypeScript
import { test, expect } from "@playwright/test";
|
||
|
||
// QA reference: qa/tool-rendering-custom-catchall.md
|
||
// Demo source: src/app/demos/tool-rendering-custom-catchall/page.tsx
|
||
// Renderer source: src/app/demos/tool-rendering-custom-catchall/custom-catchall-renderer.tsx
|
||
//
|
||
// This cell registers a SINGLE branded wildcard renderer via
|
||
// `useDefaultRenderTool`. Every tool call must paint via the same
|
||
// `[data-testid="custom-wildcard-card"]` shell — no per-tool
|
||
// specialization. Test 6 is the load-bearing assertion: every card on
|
||
// the page after each pill click shares the same testid signature.
|
||
|
||
const SUGGESTION_TIMEOUT = 15000;
|
||
const TOOL_TIMEOUT = 60000;
|
||
|
||
const PILLS = ["Weather in SF", "Find flights", "Roll a d20", "Chain tools"];
|
||
|
||
test.describe("Tool Rendering — Custom Catch-all (branded wildcard)", () => {
|
||
test.beforeEach(async ({ page }) => {
|
||
await page.goto("/demos/tool-rendering-custom-catchall");
|
||
await expect(page.getByPlaceholder("Type a message")).toBeVisible({
|
||
timeout: SUGGESTION_TIMEOUT,
|
||
});
|
||
});
|
||
|
||
test("page loads with composer and 4 suggestion pills", async ({ page }) => {
|
||
const suggestions = page.locator('[data-testid="copilot-suggestion"]');
|
||
for (const title of PILLS) {
|
||
await expect(suggestions.filter({ hasText: title }).first()).toBeVisible({
|
||
timeout: SUGGESTION_TIMEOUT,
|
||
});
|
||
}
|
||
|
||
// Sanity: per-tool branded testids from sibling cells stay at zero.
|
||
await expect(page.locator('[data-testid="weather-card"]')).toHaveCount(0);
|
||
await expect(page.locator('[data-testid="flights-card"]')).toHaveCount(0);
|
||
await expect(page.locator('[data-testid="stock-card"]')).toHaveCount(0);
|
||
await expect(page.locator('[data-testid="d20-card"]')).toHaveCount(0);
|
||
// Sanity: the OOTB default-renderer testid does NOT appear here.
|
||
await expect(
|
||
page.locator('[data-testid="copilot-tool-render"]'),
|
||
).toHaveCount(0);
|
||
});
|
||
|
||
test("Weather in SF pill paints the branded wildcard card for get_weather", async ({
|
||
page,
|
||
}) => {
|
||
await page
|
||
.locator('[data-testid="copilot-suggestion"]')
|
||
.filter({ hasText: "Weather in SF" })
|
||
.first()
|
||
.click();
|
||
|
||
const card = page
|
||
.locator(
|
||
'[data-testid="custom-wildcard-card"][data-tool-name="get_weather"]',
|
||
)
|
||
.first();
|
||
await expect(card).toBeVisible({ timeout: TOOL_TIMEOUT });
|
||
await expect(
|
||
card.locator('[data-testid="custom-wildcard-tool-name"]'),
|
||
).toHaveText("get_weather");
|
||
await expect(
|
||
card.locator('[data-testid="custom-wildcard-args"]'),
|
||
).toContainText("San Francisco", { timeout: TOOL_TIMEOUT });
|
||
});
|
||
|
||
test("Find flights pill paints the SAME branded wildcard card for search_flights", async ({
|
||
page,
|
||
}) => {
|
||
await page
|
||
.locator('[data-testid="copilot-suggestion"]')
|
||
.filter({ hasText: "Find flights" })
|
||
.first()
|
||
.click();
|
||
|
||
const card = page
|
||
.locator(
|
||
'[data-testid="custom-wildcard-card"][data-tool-name="search_flights"]',
|
||
)
|
||
.first();
|
||
await expect(card).toBeVisible({ timeout: TOOL_TIMEOUT });
|
||
await expect(
|
||
card.locator('[data-testid="custom-wildcard-tool-name"]'),
|
||
).toHaveText("search_flights");
|
||
|
||
// Result block surfaces the deterministic flights from our fixture
|
||
// (NOT the a2ui beautiful-chat boilerplate).
|
||
await expect(
|
||
card.locator('[data-testid="custom-wildcard-result"]'),
|
||
).toContainText(/United|Delta|JetBlue/, { timeout: TOOL_TIMEOUT });
|
||
});
|
||
|
||
test("Roll a d20 pill paints exactly 5 wildcard 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="custom-wildcard-card"][data-tool-name="roll_d20"]',
|
||
);
|
||
await expect
|
||
.poll(async () => cards.count(), { timeout: TOOL_TIMEOUT })
|
||
.toBe(5);
|
||
|
||
// 5th card's result is 20.
|
||
await expect(
|
||
cards.nth(4).locator('[data-testid="custom-wildcard-result"]'),
|
||
).toContainText(/"value":\s*20|"result":\s*20/, { timeout: TOOL_TIMEOUT });
|
||
|
||
// First 4 are non-20.
|
||
for (let i = 0; i < 4; i++) {
|
||
const txt = await cards
|
||
.nth(i)
|
||
.locator('[data-testid="custom-wildcard-result"]')
|
||
.innerText();
|
||
expect(txt).not.toMatch(/"value":\s*20|"result":\s*20/);
|
||
}
|
||
});
|
||
|
||
test("Chain tools pill paints 3 wildcard cards (one per tool)", async ({
|
||
page,
|
||
}) => {
|
||
await page
|
||
.locator('[data-testid="copilot-suggestion"]')
|
||
.filter({ hasText: "Chain tools" })
|
||
.first()
|
||
.click();
|
||
|
||
await expect(
|
||
page
|
||
.locator(
|
||
'[data-testid="custom-wildcard-card"][data-tool-name="get_weather"]',
|
||
)
|
||
.first(),
|
||
).toBeVisible({ timeout: TOOL_TIMEOUT });
|
||
await expect(
|
||
page
|
||
.locator(
|
||
'[data-testid="custom-wildcard-card"][data-tool-name="search_flights"]',
|
||
)
|
||
.first(),
|
||
).toBeVisible({ timeout: TOOL_TIMEOUT });
|
||
await expect(
|
||
page
|
||
.locator(
|
||
'[data-testid="custom-wildcard-card"][data-tool-name="roll_d20"]',
|
||
)
|
||
.first(),
|
||
).toBeVisible({ timeout: TOOL_TIMEOUT });
|
||
});
|
||
|
||
test("every rendered card shares the same wildcard testid signature", async ({
|
||
page,
|
||
}) => {
|
||
// Cross-tool sanity: drive Chain tools (3 distinct tools → 3
|
||
// cards) and assert every card matches the same wildcard shell.
|
||
await page
|
||
.locator('[data-testid="copilot-suggestion"]')
|
||
.filter({ hasText: "Chain tools" })
|
||
.first()
|
||
.click();
|
||
|
||
const cards = page.locator('[data-testid="custom-wildcard-card"]');
|
||
await expect
|
||
.poll(async () => cards.count(), { timeout: TOOL_TIMEOUT })
|
||
.toBeGreaterThanOrEqual(3);
|
||
|
||
const total = await cards.count();
|
||
await expect(
|
||
page.locator('[data-testid="custom-wildcard-tool-name"]'),
|
||
).toHaveCount(total);
|
||
await expect(
|
||
page.locator('[data-testid="custom-wildcard-args"]'),
|
||
).toHaveCount(total);
|
||
|
||
// All cards expose distinct tool names but the SAME shell.
|
||
const toolNames = await cards.evaluateAll((nodes) =>
|
||
nodes.map((n) => n.getAttribute("data-tool-name")),
|
||
);
|
||
const uniqueNames = new Set(toolNames);
|
||
expect(uniqueNames.size).toBeGreaterThanOrEqual(3);
|
||
for (const name of toolNames) {
|
||
expect(["get_weather", "search_flights", "roll_d20"]).toContain(name);
|
||
}
|
||
|
||
// The OOTB default-renderer testid stays at zero — proves the
|
||
// single custom wildcard is what painted, not the framework
|
||
// fallback.
|
||
await expect(
|
||
page.locator('[data-testid="copilot-tool-render"]'),
|
||
).toHaveCount(0);
|
||
});
|
||
|
||
// Regression for the aimock multi-pill bug:
|
||
// The d20 and Chain-tools fixtures used global thread state
|
||
// (`turnIndex`, `hasToolResult`) to drive sequencing. After clicking
|
||
// Find flights, the d20 loop entered at turnIndex=2 (rendering only 3
|
||
// cards instead of 5) and the Chain-tools tool-emitting fixture was
|
||
// skipped entirely (no tool cards, just the final "Done — Tokyo is
|
||
// sunny…" content). Fix: chain all follow-ups via `toolCallId`. This
|
||
// test drives Find flights → Roll a d20 → Chain tools in one thread
|
||
// and asserts the wildcard renderer paints the full card sequence for
|
||
// every pill (1 + 5 + 3 = 9 cards).
|
||
test("sequential pills in one thread render full card sequences for each", async ({
|
||
page,
|
||
}) => {
|
||
// Three sequential pills × multi-tool chains × LLM-mock latency easily
|
||
// exceeds Playwright's 30s default. Bumped to cover the worst case.
|
||
test.setTimeout(240_000);
|
||
|
||
await page
|
||
.locator('[data-testid="copilot-suggestion"]')
|
||
.filter({ hasText: "Find flights" })
|
||
.first()
|
||
.click();
|
||
const cards = page.locator('[data-testid="custom-wildcard-card"]');
|
||
await expect
|
||
.poll(async () => cards.count(), { timeout: TOOL_TIMEOUT })
|
||
.toBe(1);
|
||
|
||
await page
|
||
.locator('[data-testid="copilot-suggestion"]')
|
||
.filter({ hasText: "Roll a d20" })
|
||
.first()
|
||
.click();
|
||
// 1 (flights) + 5 (d20) = 6 cards once d20 chain finishes.
|
||
await expect
|
||
.poll(async () => cards.count(), { timeout: TOOL_TIMEOUT })
|
||
.toBe(6);
|
||
await expect(page.getByText("Rolled the d20 five times")).toBeVisible({
|
||
timeout: TOOL_TIMEOUT,
|
||
});
|
||
|
||
await page
|
||
.locator('[data-testid="copilot-suggestion"]')
|
||
.filter({ hasText: "Chain tools" })
|
||
.first()
|
||
.click();
|
||
// 1 + 5 + 3 = 9 once chain tools mounts get_weather + search_flights +
|
||
// roll_d20 cards.
|
||
await expect
|
||
.poll(async () => cards.count(), { timeout: TOOL_TIMEOUT })
|
||
.toBe(9);
|
||
await expect(page.getByText("Done — Tokyo is sunny")).toBeVisible({
|
||
timeout: TOOL_TIMEOUT,
|
||
});
|
||
});
|
||
});
|