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>
3.0 KiB
3.0 KiB
QA: State Streaming — Google ADK
Prerequisites
- Demo is deployed and accessible at
/demos/shared-state-streamingon the dashboard host - Agent backend is healthy (
/api/health);GOOGLE_API_KEYis set (orGOOGLE_GEMINI_BASE_URLpoints at the aimock proxy) - Per-token granularity requires
google-adk >= 1.24.0on Vertex AI. Gemini Studio falls back to chunk-level deltas (still streams; just coarser).
Test Steps
1. Basic Functionality
- Navigate to
/demos/shared-state-streaming; verify the page renders within 3s with the "Document" panel filling the viewport and theCopilotSidebaropen by default on the right - Verify the document panel shows the heading "Document" and the empty-state hint "Ask the agent to write something — its output will stream here token by token."
- Verify the char-count badge reads
0 charsand no "Live" badge is visible on initial load - Verify the chat input placeholder reads "Ask me to write something..."
- Send "Hello" and verify the agent responds within 10s
2. Feature-Specific Checks
Suggestions
- Verify all 3 suggestion pills are visible with verbatim titles:
- "Write a short poem"
- "Draft an email"
- "Explain quantum computing"
Per-Token State Streaming (Predict-State Mapping)
- Click "Write a short poem"
- Within 5s verify the "Live" badge appears next to the "Document" heading (
data-testid="document-live-badge") - Verify the
document-contentnode mounts with text growing over time (each render contains MORE text than the prior one for at least 2 ticks); the char-count display ticks upward in lockstep - Verify the inline blinking cursor element renders alongside the streaming text while the agent is running
- Verify the streamed output forms a coherent short poem about autumn leaves (a few stanzas / lines, not a single token)
- Once the agent finishes, verify the "Live" badge and the cursor disappear and the final document text remains rendered
Streaming Path Selector
- Confirm via the
/api/healthJSON or Railway logs whether the run used Vertex AI per-token deltas or Gemini Studio chunk-level deltas - Either path is acceptable for this demo — the UI must still display token-by-token or chunk-by-chunk growth without freezing on the final value
Second Pill Re-Streams Cleanly
- In the same session, click "Draft an email"
- Verify the document area replaces the prior content (no concatenation) and the new content streams in
- Verify the "Live" badge re-mounts during the new run
3. Error Handling
- Send an empty message; verify it is a no-op
- Verify no uncaught console errors during any streaming cycle above
Expected Results
- Chat loads within 3 seconds; initial document streaming starts within 5 seconds of the triggering prompt
- The document text visibly grows on the page (not a single end-of-run update)
- The "Live" badge and blinking cursor reflect
isRunningaccurately - No console errors, no stuck-state, no orphaned half-streamed output