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>
3.7 KiB
3.7 KiB
QA: Pre-Built Popup — Google ADK
Prerequisites
- Demo is deployed and accessible at
/demos/prebuilt-popupon the dashboard host - Agent backend is healthy (
/api/healthor/api/copilotkitGET);GOOGLE_API_KEYis set on Railway; the ADK agent server hasprebuilt_popupregistered against the neutral_simple_chatagent - Note: the demo source contains no
data-testidattributes of its own. Checks below rely on verbatim visible text, role-based selectors, and CopilotKit's built-in popup testids (copilot-popup,copilot-chat-toggle,copilot-close-button,copilot-suggestion,copilot-assistant-message,copilot-send-button). The underlying agent is the neutral "helpful, concise assistant" (no frontend tools, no agent tools).
Test Steps
1. Basic Functionality
- Navigate to
/demos/prebuilt-popup; verify the main content renders with heading (h1, text: "Popup demo — look for the floating launcher") and paragraph body mentioning<CopilotPopup /> - Verify a floating launcher button is visible in a corner of the viewport (typically bottom-right)
- Verify the
<CopilotPopup />window is OPEN by default (defaultOpen={true}in source) — a chat overlay sits on top of the page content with an input at the bottom - Verify the chat input placeholder is verbatim "Ask the popup anything..."
2. Feature-Specific Checks
Popup Open / Close
- With the popup open, click the popup's close control (X button in the popup header); verify the popup window collapses and only the floating launcher remains
- Click the floating launcher; verify the popup re-opens showing the prior transcript (if any)
- Verify opening/closing does not trigger a full page reload (URL remains
/demos/prebuilt-popup, main content stays mounted) - Verify the popup overlays the page content rather than pushing layout (unlike the docked sidebar form factor)
Suggestions (useConfigureSuggestions)
- With the popup open, verify a suggestion pill titled "Say hi" is rendered in the chat surface (configured with
available: "always") - Click the "Say hi" pill; verify it sends the message "Say hi from the popup!" and an assistant text response appears within 10s
Chat Round-Trip
- Type "Hello" into the popup chat input ("Ask the popup anything..." placeholder) and submit; verify the user bubble appears, followed within 10s by an assistant text response
- Send a second message; verify a second valid response appears and the transcript auto-scrolls to the latest turn
- Close the popup and re-open it; verify the existing transcript persists within the open session
Agent Wiring
- Confirm (via DevTools → Network) that chat submissions POST to
/api/copilotkitwith agent nameprebuilt_popupin the payload; response streams back as SSE with no 4xx/5xx status
3. Error Handling
- Attempt to send an empty message; verify it is a no-op (no user bubble, no network request)
- Resize the viewport to ~375px wide (mobile); verify the popup adapts (full-width or close to it) without clipping the input, header, or close button
- Stop the backend, send a message; verify the UI surfaces a visible error path rather than hanging silently; DevTools → Console shows no uncaught errors during any flow above
Expected Results
- Page + popup render within 3 seconds
- Assistant text response within 10 seconds
- Popup open/close animates smoothly with no layout jank
- Floating launcher remains accessible (not clipped) at all tested viewport sizes
- No UI layout breaks, no uncaught console errors
- The neutral agent (no tools) simply chats — no frontend tool registrations, no tool-call UI expected in this demo