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
fix/claude-sdk-python-testid-backfill
copilotkit__copilotkit/showcase/integrations/google-adk/qa/hitl-in-chat.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

2.9 KiB
Raw Permalink Blame History

QA: Human in the Loop (in-chat) — Google ADK

Prerequisites

  • Demo is deployed and accessible
  • Agent backend is healthy (check /api/health)

Test Steps

1. Basic Functionality

  • Navigate to the HITL in-chat demo page (/demos/hitl-in-chat)
  • Verify the chat interface loads in a centered max-w-4xl container
  • Verify the chat input placeholder "Type a message" is visible

2. Suggestions

  • Verify "Book a call with sales" suggestion pill is visible
  • Verify "Schedule a 1:1 with Alice" suggestion pill is visible
  • Click the "Book a call with sales" suggestion
  • Verify the message "Please book an intro call with the sales team to discuss pricing." is sent

3. Time-picker card (book_call HITL flow)

The book_call HITL tool is defined on the frontend via useHumanInTheLoop. The ADK agent (hitl_in_chat_book_call_agent) is instructed to call that tool with topic + attendee args; the frontend renders a TimePickerCard and forwards the user's choice back to the agent as the tool result.

  • Send "Schedule a 1:1 with Alice next week to review Q2 goals."
  • Within 60s, the time-picker card renders (data-testid="time-picker-card")
  • Verify the card shows "With Alice" (attendee from tool args)
  • Verify four time slots are visible (data-testid="time-picker-slot")
  • Click the first time slot
  • Verify the card transitions to the picked state (data-testid="time-picker-picked") showing "Booked for ..."
  • Verify the agent's follow-up confirmation arrives within 30s and mentions Alice / the booked label

4. Sales-team flow (second suggestion)

  • Send "Please book an intro call with the sales team to discuss pricing."
  • Time-picker card renders within 60s
  • Verify the card mentions the sales team
  • Pick a slot; the picked-state card appears
  • Agent's follow-up confirmation arrives mentioning "sales team"

5. Back-to-back flow (regression check)

  • In the same session (no refresh), trigger both flows back-to-back:
    • Flow A: "Schedule a 1:1 with Alice next week to review Q2 goals."
    • Flow B: "Please book an intro call with the sales team to discuss pricing."
  • Verify a SECOND time-picker card appears for Flow B
  • Pick a slot in the new card; verify the sales-specific confirmation arrives without conflating with the Alice flow

6. Cancel path

  • Trigger a booking flow
  • Click "None of these work"
  • Verify the cancelled-state card appears (data-testid="time-picker-cancelled") reading "Cancelled — no time picked."

7. Error Handling

  • Send an empty message (should be handled gracefully)
  • Verify no console errors during normal usage

Expected Results

  • Chat loads within 3 seconds
  • Time-picker card appears within 60 seconds of the booking message
  • Agent confirmation arrives within 30s of slot selection
  • No UI errors or broken layouts
Reference in New Issue View Git Blame Copy Permalink