skills/copilotkit__copilotkit
1
0
Fork 0
mirror of https://github.com/CopilotKit/CopilotKit.git synced 2026-09-14 16:26:20 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
codex/remove-threads-cli-path
copilotkit__copilotkit/showcase/integrations/google-adk/qa/frontend-tools.md
T
Tyler Slaton ef1ca9808c feat(showcase/google-adk): QA-blitz parity ports — agent prompts, tool surface, e2e specs 
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>
2026-05-12 17:58:06 -07:00

4.4 KiB
Raw Permalink Blame History

QA: Frontend Tools (In-App Actions) — Google ADK

Prerequisites

  • Demo is deployed and accessible at /demos/frontend-tools on the dashboard host
  • Agent backend is healthy (/api/copilotkit GET returns agent_status: "reachable"); GOOGLE_API_KEY is set; the Python agent_server exposes the frontend_tools agent (which shares _simple_chat with the other frontend-only demos)
  • The backend _simple_chat registers NO server-side change_background tool — the agent forwards the frontend tool schema at runtime; the browser owns the handler
  • Frontend registers exactly ONE tool via useFrontendTool: change_background (parameter: background: string — a CSS background value, colors or gradients). Handler sets local React state and returns { status: "success", message: "Background changed to …" }

Test Steps

1. Basic Functionality

  • Navigate to /demos/frontend-tools; verify the page loads within 3s
  • Verify the background container (data-testid="background-container") is visible, full-screen, flex-centered
  • Verify the initial background value is var(--copilot-kit-background-color) (the theme default) — inspect the container's inline style.background
  • Verify the CopilotChat panel renders centered (max width 4xl, rounded-2xl corners) inside the background container
  • Send "Hello"; verify the agent responds with plain text within 10s and does NOT call change_background

2. Feature-Specific Checks

Suggestion Pills

  • Verify the "Change background" suggestion pill is visible above the input
  • Verify the "Sunset theme" suggestion pill is visible
  • Click the "Change background" pill; verify it sends the verbatim prompt "Change the background to a blue-to-purple gradient."

change_background — Successful Invocation

  • After clicking the "Change background" pill (or typing "Change the background to a linear gradient from indigo to pink"), verify within 15s that the agent invokes the change_background tool
  • Verify the data-testid="background-container" element's inline style.background mutates from var(--copilot-kit-background-color) to a CSS gradient string containing linear-gradient (or radial-gradient)
  • Verify the change is visually reflected (color/gradient swap is instant, no flash)

Round-Trip — Agent References Tool Return Value

  • Immediately after the background changes, verify the agent emits a follow-up assistant message that acknowledges the change
  • Verify the follow-up message text references the new background value OR echoes the "Background changed to <value>" success message (confirming the agent consumed the handler's return payload, not just triggered the tool blindly)
  • Ask "What color is the background right now?"; verify the agent replies with a description consistent with the last change_background call's argument (demonstrates the agent received the handler's return string into context)

Second Invocation — State Persistence

  • Ask "Change it to a sunset gradient with orange and pink"; verify the background mutates again to a new gradient
  • Verify the previous gradient is fully replaced (not layered)
  • Ask "Now make it solid dark blue"; verify style.background becomes a solid color value (e.g. #00008b, darkblue, or rgb(...)) — no gradient keyword

3. Error Handling

  • Send "Change the background to banana"; verify the agent either (a) calls change_background with a valid CSS fallback (e.g. yellow, #FFE135) and the container updates, or (b) declines politely without calling the tool — either is acceptable, but the UI must not crash
  • Send an empty message; verify it is a no-op
  • Send a ~500-character prompt unrelated to backgrounds; verify the agent responds normally without invoking change_background
  • Open DevTools → Console; verify no uncaught errors, no Zod parse failures, no useFrontendTool warnings

Expected Results

  • Chat loads within 3 seconds; first change_background invocation completes within 15 seconds of prompt
  • The [data-testid="background-container"] inline style.background updates in real time as the tool is invoked
  • Agent's follow-up reply demonstrably uses the handler's returned message field (round-trip verified)
  • Multiple sequential invocations replace the background cleanly with no visual artifacts
  • No uncaught console errors; no broken layouts
Reference in New Issue View Git Blame Copy Permalink