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
2.7 KiB
2.7 KiB
QA: Shared State (Read + Write) — LangGraph (FastAPI)
Prerequisites
- Demo is deployed and accessible
- Agent backend is healthy (check
/api/copilotkitGET —agent_status: "reachable") OPENAI_API_KEYis set in the agent environment
What this demo proves
- UI -> agent (write): editing the preferences card writes the new
preferencesobject straight into agent state viaagent.setState. - agent -> UI (read): when the agent invokes its
set_notestool thenotesslice of agent state updates and the Notes card re-renders. - agent -> reads UI writes: a
PreferencesInjectorMiddlewarereadspreferencesout of state every turn and prepends it to the system prompt, so the next reply visibly adapts.
Test Steps
1. Page loads with both cards
- Navigate to
/demos/shared-state-read-write - The Preferences card (
data-testid="preferences-card") is visible - The Notes card (
data-testid="notes-card") is visible - The Notes card shows "No notes yet" (
data-testid="notes-empty") - The chat input on the right is visible
2. UI writes flow into agent state (preferences)
- Type a name into
pref-name(e.g. "Atai") — the JSON inpref-state-jsonupdates immediately - Change tone to "playful" via
pref-tone— JSON reflects it - Change language to "Spanish" via
pref-language— JSON reflects it - Click two interest pills (e.g. Cooking, Music) — JSON
interestsarray updates
3. Agent reads the UI-written preferences
- In chat, send "Say hi and introduce yourself."
- The agent reply addresses the user by the name from the card
- The reply tone matches the selected tone
- If language was changed (e.g. Spanish), the reply is in that language
4. Agent writes notes via set_notes
- Send: "Remember that I prefer morning meetings and that I don't eat dairy."
- Within ~10 seconds, the Notes card transitions away from
notes-empty - At least one
note-itemappears with each remembered fact - Subsequent unrelated chat turns leave the notes intact
5. UI can clear agent-written state
- With at least one note showing, click
notes-clear-button - The Notes card returns to
notes-emptyimmediately - No errors in the browser console
6. Error handling
- Sending an empty message is handled gracefully (no crash)
- Refreshing the page resets state to defaults; first turn re-seeds it
Expected Results
- Chat loads within 3 seconds
- Each preference edit reflects in
pref-state-jsonimmediately - Note updates land within 10 seconds of asking the agent to remember
- No UI errors or broken layouts; no React warnings in console