mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
Tyler Slaton
ef1ca9808c
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>
3.8 KiB
3.8 KiB
QA: Authentication — Google ADK
Prerequisites
- Demo deployed and accessible at /demos/auth
- ADK agent backend healthy (check /api/health)
- GOOGLE_API_KEY set in the deployment
Test Steps
1. Initial unauthenticated state (SignInCard)
- Navigate to /demos/auth (in a fresh browser session — clear
localStorage["copilotkit:auth-demo:token"]if it exists) - Verify the SignInCard is visible (
data-testid="auth-sign-in-card") - Verify the demo token is displayed in plain text
(
data-testid="auth-demo-token") - Verify the "Sign in with demo token" button is enabled
(
data-testid="auth-sign-in-button") - Verify the AuthBanner is NOT yet rendered
(
data-testid="auth-banner"absent) - Verify the chat composer is NOT yet rendered (no "Type a message" placeholder)
- Verify no console errors on page load
2. Signing in mounts the chat surface
- Click "Sign in with demo token"
- Verify the AuthBanner appears with the green/success variant
(
data-authenticated="true") - Verify the auth-status text reads "✓ Signed in as demo user"
- Verify the "Sign out" button is visible and enabled
(
data-testid="auth-sign-out-button") - Verify the SignInCard is gone (
data-testid="auth-sign-in-card"absent) - Verify the chat composer is mounted ("Type a message" placeholder visible)
- Verify no
auth-demo-errorsurface
3. Authenticated send → assistant response
- Type "Hello" and press Enter
- Within 30 seconds, an assistant message is rendered
(
[data-role="assistant"]) - No auth-demo-error surface appears
4. Sign out flips banner amber, keeps chat mounted
- Click "Sign out"
- Within 1 second, the banner flips to the amber variant
(
data-authenticated="false") - Verify the auth-status text reads "⚠ Signed out — the agent will reject your messages until you sign in."
- Verify the "Sign in" button is visible
(
data-testid="auth-authenticate-button") - Verify the chat composer is STILL visible — page must not return to the SignInCard
- Verify no white-screen
5. Unauthenticated send surfaces a 401 without crashing
- After signing out, type "Hello again" and press Enter
- Within 15 seconds, the page-level error surface appears:
data-testid="auth-demo-error"with the runtime's 401 message - Verify the banner is STILL visible
- Verify no assistant response appears
6. Re-signing in clears the error and resumes chat
- Click "Sign in" (amber-state authenticate button)
- Within 1 second, the banner flips back to green
- Verify the
auth-demo-errorsurface is cleared - Type "Hello" and press Enter; an assistant response appears within 30s
7. Hard-reload behavior
- Hard-reload the page (clear cache + reload)
- With a valid
localStoragetoken, the demo lands directly in the authenticated chat state (no SignInCard) - With
localStoragecleared, the demo lands on the SignInCard
8. Error Handling
- With DevTools Network panel blocking
/api/copilotkit-auth, send a message while authenticated - Verify a network-level error surfaces cleanly (no uncaught promise rejection in console)
- Restore network; verify sends work again without a page reload
Expected Results
- Initial paint shows SignInCard (no 401 crash on
/info) - Banner state flips within 1s of Sign out / Sign in clicks
- Post-sign-out sends produce a visible 401 error within 15s via
auth-demo-error - Page never white-screens after sign out — banner and composer stay mounted
- Authenticated sends produce an assistant response within 30s
- Token persists across reloads via localStorage; clearing localStorage returns the demo to its first-paint SignInCard state