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/voice.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: Voice Input — Google ADK

Prerequisites

  • Demo is deployed and accessible at /demos/voice
  • Railway service showcase-google-adk is healthy (/api/health returns 200)
  • OPENAI_API_KEY is set on the Railway service for the dedicated voice runtime at /api/copilotkit-voice (required for the /transcribe endpoint)
  • GOOGLE_API_KEY is set on the ADK agent backend for the voice-demo agent (resolves to the neutral _simple_chat agent)
  • A modern browser that supports MediaRecorder (Chromium, Firefox, Safari 14+)
  • Microphone hardware available (required only for the mic path in section 3)
  • A bundled public/demo-audio/sample.wav is present (used for screenshot/preview generation; the in-app sample button no longer fetches it)

Test Steps

1. Basic Functionality

  • Navigate to /demos/voice
  • Verify the page header "Voice input" is visible
  • Verify the sample-audio row (data-testid="voice-sample-audio") is visible
  • Verify the caption reads Sample: "What is the weather in Tokyo?"
  • Verify the "Play sample" button (data-testid="voice-sample-audio-button") is enabled
  • Verify <CopilotChat /> renders a message composer (data-testid="copilot-chat-input")
  • Verify the composer shows a microphone button (data-testid="copilot-start-transcribe-button") — this is the authoritative signal that transcriptionService is mounted on /api/copilotkit-voice

2. Sample-audio path (no mic permission required)

  • Click the "Play sample" button
  • Immediately, the chat textarea (data-testid="copilot-chat-textarea") contains the canned phrase "What is the weather in Tokyo?" (no async round-trip; no "Transcribing…" state)
  • The button stays enabled
  • Click send (data-testid="copilot-send-button")
  • Within 10 seconds, the agent responds with a text answer or a weather-related tool render (WeatherCard, custom-catchall card, or default tool card — depending on which tool-rendering mode is active on this page)

3. Mic path (manual)

  • Click the microphone button (data-testid="copilot-start-transcribe-button") in the composer
  • Grant microphone permission at the browser prompt
  • Speak "Hello" clearly, then click the mic button again (now data-testid="copilot-finish-transcribe-button") to stop recording
  • Within 5 seconds, the textarea contains text matching "hello" (case-insensitive)
  • Click send
  • Agent responds within 10 seconds

4. Error Handling

  • Deny microphone permission, click the mic button
  • Verify the UI handles permission denial gracefully (no crash, mic button remains visible)

Expected Results

  • Sample button click populates the textarea synchronously (no perceptible delay)
  • Agent response renders within 10 seconds of send
  • No console errors during the successful paths
  • Whisper transcription via the mic path returns text resembling what was spoken (deployment must have OPENAI_API_KEY configured)
Reference in New Issue View Git Blame Copy Permalink