mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
Lukas Moschitz
3130a04bd0
validate-parity.ts keys QA filenames to the demo id, so the seven integrations still carrying byoc-* names produced spurious "demo 'declarative-hashbrown' has no qa/declarative-hashbrown.md" warnings. 454 -> 446 warnings, still 21/21 pass. Test steps and expected results are now identical to the langgraph-python north star per demo. Per-integration facts (agent mount, env var, prompt module) moved into an Integration notes section and were verified against source rather than carried over. Python backend modules keep their byoc_ prefix -- manifests reference them under highlight:. Also records a pre-existing break in both crewai packages: the declarative-json-render page requests /api/copilotkit-declarative-json-render, but only copilotkit-byoc-json-render exists, so the demo 404s on its runtime URL.
3.1 KiB
3.1 KiB
QA: Declarative UI — json-render — PydanticAI
Prerequisites
- Demo reachable at
/demos/declarative-json-render agent_server.pyrunning and healthy; it mounts the prompt-specialized agent at/byoc_json_render/src/app/api/copilotkit-declarative-json-render/route.tsproxies to${AGENT_URL}/byoc_json_render/(AGENT_URLdefaults tohttp://localhost:8000)OPENAI_API_KEYset for the agent backend@json-render/core+@json-render/reactpresent inpackage.json(pinned to0.18.0)
Test Steps
1. Page load
- Navigate to
/demos/declarative-json-render. - Chat composer is visible.
- Three suggestion pills appear with titles: "Sales dashboard", "Revenue by category", "Expense trend".
- No console errors.
2. Sales dashboard suggestion
- Click the "Sales dashboard" suggestion.
- Within 60 seconds, a
data-testid="json-render-root"wrapper appears in the assistant bubble. - A
data-testid="metric-card"renders inside the wrapper. - A chart (
data-testid="bar-chart"ordata-testid="pie-chart") renders inside the wrapper. - Nested children of the MetricCard (the BarChart in the Sales Dashboard worked example) render — they are NOT silently dropped.
- No raw JSON text is shown once rendering finishes — the streaming JSON is replaced by components.
3. Revenue by category
- Click the "Revenue by category" suggestion.
- Within 60 seconds, a
data-testid="pie-chart"renders with multiple category slices + legend. - No
useVisibility must be used within a VisibilityProviderconsole error (<JSONUIProvider>must wrap<Renderer>).
4. Expense trend
- Click the "Expense trend" suggestion.
- Within 60 seconds, a
data-testid="bar-chart"renders with month labels.
5. Free-form prompt
- Type "Show me a metric for quarterly revenue" and send.
- Verify at least one
metric-cardrenders; no console errors.
6. Multi-turn
- After a previous render is visible, send a follow-up prompt ("Now break that down by region").
- A new assistant message appears with a new json-render rendering — prior renders stay in the transcript.
7. Malformed output handling
- If the agent ever replies with non-JSON text (force it by asking "tell me a joke"), the chat falls back to rendering that raw text via the default assistant bubble. No crash, no stuck spinner.
Expected Results
- Suggestion renders land within 60 seconds. Budget is slightly higher than the hashbrown demo because a JSON
{ root, elements }spec is more verbose than hashbrown's token stream. - No uncaught errors in the console.
- Streaming falls back to plain text until the JSON parses, then swaps to rendered components.
Integration notes
- The flat-spec prompt lives in
src/agents/byoc_json_render_agent.py; thebyoc_prefix on the backend module, the HTTP mount, and thebyoc_json_renderagent id are deliberate and stay. - No known parity gaps vs. the langgraph-python north star — the catalog shape, suggestion prompts, and renderer tree match the reference.