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) — Spring AI
Prerequisites
- Demo is deployed and accessible
- Agent backend is healthy (check
/api/health) OPENAI_API_KEYis set on the Spring backend
Architecture under test
- The UI owns a
preferences = { name, tone, language, interests }object and writes it into agent state viaagent.setState({ preferences, notes }). - Spring's
SharedStateReadWriteControllerruns a per-requestLocalAgentsubclass that readspreferencesoff the AG-UI envelope and injects them into the system prompt every turn. - The agent has a single tool,
set_notes(notes: List<String>), that mutatesstate.notesand emits aSTATE_SNAPSHOTevent so theuseAgent({ updates: [OnStateChanged] })hook re-renders the page.
Test Steps
1. Page load
- Navigate to
/demos/shared-state-read-write. - Verify both sidebar cards render:
data-testid="preferences-card"anddata-testid="notes-card". - Verify the chat input is visible on the right.
- Confirm the preferences JSON pre block (
data-testid="pref-state-json") shows the seeded defaults:{ name: "", tone: "casual", language: "English", interests: [] }.
2. Write side (UI -> agent)
- Type "Atai" into
data-testid="pref-name". - Switch tone to "playful" via
data-testid="pref-tone". - Switch language to "Spanish" via
data-testid="pref-language". - Click two interest chips (e.g. "Cooking", "Music").
- Confirm the JSON pre block updates live to reflect every edit.
- Send the message "Greet me." and verify the assistant's reply:
- addresses the user as "Atai",
- is in Spanish,
- has a playful tone (exclamations / light humor OK),
- and references at least one selected interest if natural.
3. Read side (agent -> UI)
- Send: "Remember that I prefer morning meetings and that I don't eat dairy."
- Verify the agent calls
set_notes(visible briefly in the chat stream) and that the Notes card shows two list items shortly after. - Verify
data-testid="notes-list"is present and contains twodata-testid="note-item"entries. - Send another remember-style message: "Also remember I'm vegetarian."
- Verify the notes list grows (the agent should pass the FULL list, not a diff), now showing three items.
4. Bidirectional clear
- Click
data-testid="notes-clear-button"in the Notes card. - Verify the list is cleared and
data-testid="notes-empty"appears. - Send "What did I tell you to remember?" — agent should not hallucinate removed notes (memory persists in chat history but the notes panel is canonical).
5. Error handling
- Send an empty message — UI should handle gracefully.
- Disconnect briefly: verify reconnect does not corrupt state.
- No console errors during normal usage.
Expected Results
- Page loads within 3 seconds.
- Preferences edits show in the JSON pre block instantly (local state).
- Agent replies adapt to preferences within 10 seconds.
- Notes panel reflects
set_notescalls within 1 second after the tool result event lands (driven by the STATE_SNAPSHOT emission). - No UI errors, no orphaned state across renders.