mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
Alem Tuzlak
23a3b24a01
Adds real working Shared State (Read+Write) and Sub-Agents demos to 15 showcase integrations, mirroring the canonical langgraph-python and google-adk reference implementations. Fills rows previously empty on the showcase coverage dashboard. Packages: ag2, agno, claude-sdk-python, claude-sdk-typescript, crewai-crews, langgraph-fastapi, langgraph-typescript, langroid, llamaindex, mastra, ms-agent-dotnet, ms-agent-python, pydantic-ai, spring-ai, strands. (built-in-agent landed independently on main as PR #4321 — its variant is canonical; this PR no longer touches it.) Per-package deliverables: framework-native backend agents (preferences-injection middleware/callback + set_notes tool; supervisor + 3 sub-agents wired as tools with running -> completed /failed delegation log); frontend page.tsx + preferences-card.tsx / notes-card.tsx for SSRW and delegation-log.tsx for subagents — wired to useAgent({ updates: [OnStateChanged] }); manifest entries; runtime route registration + per-package agent server config; real QA scripts. Includes targeted hardening fixes from a 7-agent code-review loop: - Sub-agent failure paths now correctly emit status: "failed" (previously hardcoded "completed" or unreachable in mastra/strands/langgraph-fastapi/langgraph-typescript/ag2) - Parallel-tool-call delegation race fixed in langgraph-fastapi (Annotated[list, add]) and langgraph-typescript (concat reducer) - Silent data loss eliminated in claude-sdk-python/claude-sdk-typescript/crewai-crews — empty JSON.parse catches now log + emit error events - ms-agent-dotnet set_notes writes to per-thread slot via AsyncLocal - mastra working-memory writes are deterministic via src/mastra/tools/working-memory.ts helper - spring-ai tool-call envelope ids match supervisor's tc.id() and AG-UI event ordering reordered; CopyOnWriteArrayList for parallel-call safety - Stack trace + raw error message leaks scrubbed across 8+ Next.js routes — log server-side with errorId + return generic envelope - Sub-agent calls no longer block event loops in ag2 (asyncio.to_thread), langroid (llm_response_async), pydantic-ai (async run + async tools) - langroid lru_cache cross-request contamination dropped - Numerous smaller items: claude-sdk-python invalid model id, Callable annotation, /health endpoint exposed; crewai-crews supervisor no longer resets delegations every turn; pydantic-ai snapshot uses model_dump() CI fixes folded in: - crewai-crews test_forwarded_props: extend the stubbed ag_ui_crewai.endpoint module to expose add_crewai_flow_fastapi_endpoint and add stub agents.shared_state_read_write / agents.subagents modules - generate-catalog test: bump crewai-crews wired-cell expectation 28 -> 30; replace hardcoded total-wired count with an invariant (wired + stub + unshipped = 737) plus a lower-bound floor - oxfmt run on the qa/shared-state-read-write.md files in mastra + spring-ai Rebased onto latest main (post showcase/packages -> showcase/integrations rename + post built-in-agent landing). Original blitz history preserved at the blitz-pre-rebase-snapshot tag. Known follow-ups (deferred to follow-up PR): - agno sync sub_agent.run() blocks event loop (perf only) - ms-agent-python asyncio thread-fallback fragility - llamaindex initial-state coercion when UI clears state - Manifest highlight audit (langgraph-typescript headless-complete, langgraph-fastapi byoc-* missing route.ts highlights) - agno hitl-in-chat declared in demos but not features; duplicate /demos/hitl-in-chat route - langgraph-typescript server.mjs graphSpec only registers 3 graphs vs 23 in langgraph.json (pre-existing) - mastra hitl legacy demo missing from features list - claude-sdk-python agents/agent.py line 474 also has the legacy claude-opus-4-5 default - PARITY_NOTES vs manifest mismatches for hitl-in-app across spring-ai/agno/ag2 (pre-existing) - spring-ai a2ui-fixed-schema missing from generative_ui list
3.2 KiB
3.2 KiB
QA: Shared State (Read + Write) — Mastra
Prerequisites
- Demo is deployed and accessible
- Agent backend is healthy (check /api/health)
Test Steps
1. Basic Functionality
- Navigate to the shared-state-read-write demo page
- Verify the preferences card loads (
data-testid="preferences-card") - Verify the notes card loads (
data-testid="notes-card") - Verify the empty notes message renders (
data-testid="notes-empty"): "No notes yet. Ask the agent to remember something." - Verify the chat panel is visible with placeholder "Chat with the agent..."
- Send a basic message (e.g. "Say hi.") and verify the agent responds.
2. UI -> Agent (Write) — preferences
- Type a name into the Name input (
data-testid="pref-name"). - Verify the JSON state preview (
data-testid="pref-state-json") reflects the new name. - Change the Tone select (
data-testid="pref-tone") to "playful". - Change the Language select (
data-testid="pref-language") to "Spanish". - Toggle two interests (e.g. "Cooking", "Travel"). Verify both buttons render in the selected style.
- Verify the JSON state preview now reads:
{ "name": "...", "tone": "playful", "language": "Spanish", "interests": ["Cooking", "Travel"] } - Send a message: "Greet me, then suggest a quick recipe." Verify the agent: - addresses the user by the name from preferences - replies in Spanish - uses a playful tone - leans on the Cooking interest
3. Agent -> UI (Read) — notes
- Click the "Remember something" suggestion. The chat sends the message: "Remember that I prefer morning meetings and that I don't eat dairy."
- Verify the agent calls the
set_notestool. - Verify the notes card switches from the empty state to a
bulleted list (
data-testid="notes-list"with one or moredata-testid="note-item"entries). - Verify each note is < ~120 chars and each preference the user mentioned is reflected.
- Send another message: "Also remember that I like long walks." Verify the notes list grows (existing notes preserved + the new one).
4. UI -> Agent (Write back) — clear notes
- Click the "Clear" button (
data-testid="notes-clear-button"). - Verify the notes list disappears and the empty state reappears.
- Send a follow-up: "What did I tell you to remember?". Verify the agent acknowledges the empty notes state (it may re-populate notes if it remembers from chat history — this is acceptable).
5. Suggestions
- Verify "Greet me", "Remember something", and "Plan a weekend" suggestion buttons are visible.
6. Error Handling
- Send an empty message — should be ignored or handled gracefully.
- Verify no console errors during normal usage.
Expected Results
- Preferences and notes cards load within 3 seconds.
- Agent replies within 10 seconds for simple turns.
- Preferences edits propagate into agent state (JSON preview updates instantly, agent reply on next turn reflects them).
set_notestool calls visibly populate the notes card without a page refresh.- The Clear button removes notes from agent state, surfaced via the empty state.
- No UI errors or broken layouts.