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: Sub-Agents — Mastra
Prerequisites
- Demo is deployed and accessible
- Agent backend is healthy (check /api/health)
Test Steps
1. Basic Functionality
- Navigate to the subagents demo page.
- Verify the delegation log card loads
(
data-testid="delegation-log"). - Verify the empty-state message renders: "Ask the supervisor to complete a task. Every sub-agent it calls will appear here."
- Verify the delegation count (
data-testid="delegation-count") reads "0 calls". - Verify the chat panel input placeholder is "Give the supervisor a task...".
2. Sub-agent delegation flow
- Click the "Write a blog post" suggestion. The supervisor should run a research -> write -> critique sequence.
- Verify a "Supervisor running"
(
data-testid="supervisor-running") badge appears while the run is active. - Verify delegation entries (
data-testid="delegation-entry") stream in as the supervisor calls each sub-agent. - Verify the entries are tagged with the correct sub-agent label: Research / Writing / Critique, with their respective emoji (🔎 / ✍️ / 🧐).
- Verify each entry shows: - a "#1", "#2", "#3" index - the task text the supervisor passed in - the sub-agent's text result in the white inner panel - a "completed" status pill
- Verify the delegation count updates to match the number of entries.
3. Subsequent runs accumulate
- After the first run finishes, click "Explain a topic". Verify new delegation entries are APPENDED to the log (not replacing the previous run's entries).
- Verify entries from both runs remain visible.
4. Ad-hoc delegation
- Send a freeform message: "Just research the topic of LLM tokenization, no draft needed."
- Verify only a Research delegation entry appears (the supervisor is not forced to run all three).
5. Suggestions
- Verify "Write a blog post", "Explain a topic", and "Summarize a topic" suggestion buttons are visible.
6. Error Handling
- Send an empty message — should be ignored or handled gracefully.
- Verify no console errors during normal usage.
- If a sub-agent errors, the delegation entry should still appear
with a clear error result string (prefixed with
[sub-agent error]).
Expected Results
- Delegation log loads within 3 seconds.
- Supervisor responds within 30 seconds for the canonical research -> write -> critique flow (slower than other demos because three nested LLM calls run sequentially).
- Each delegation entry surfaces in the log without a page refresh.
- The delegation count matches the number of entries shown.
- No UI errors or broken layouts.