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
56 lines
3.7 KiB
Markdown
56 lines
3.7 KiB
Markdown
# QA: Sub-Agents — Microsoft Agent Framework (.NET)
|
|
|
|
## Prerequisites
|
|
|
|
- Demo is deployed and accessible at `/demos/subagents` on the dashboard host
|
|
- .NET agent backend is healthy (`/api/health`); `GitHubToken` (or equivalent) is set so the OpenAI client can authenticate; the `/subagents` AG-UI endpoint is mounted in `agent/Program.cs`
|
|
|
|
## Test Steps
|
|
|
|
### 1. Basic Functionality
|
|
|
|
- [ ] Navigate to `/demos/subagents`; verify the page renders within 3s with the delegation log on the left and the `CopilotChat` pane on the right
|
|
- [ ] Verify `data-testid="delegation-log"` is visible with heading "Delegation log" and an empty-state message reading "No delegations yet. Ask the supervisor to plan a deliverable."
|
|
- [ ] Verify the chat input placeholder is "Ask the supervisor to plan, draft, or critique..."
|
|
- [ ] Verify both suggestion pills are visible with verbatim titles: "Quick brief", "Marketing post"
|
|
- [ ] Send "Hello! What can you do?"; verify an assistant reply appears within 10s describing the three sub-agents
|
|
|
|
### 2. Feature-Specific Checks
|
|
|
|
#### Single Sub-Agent Delegation
|
|
|
|
- [ ] Send "Use the research sub-agent to give me 3 facts about pair programming."; within 30s verify a `data-testid="delegation-entry"` is rendered with `data-status="completed"`, the "Research" badge, and a non-empty result body containing 3 bullet-style lines
|
|
- [ ] Verify the assistant chat reply summarizes the research result in one or two short sentences
|
|
|
|
#### Live Running -> Completed Transition
|
|
|
|
- [ ] Click the "Quick brief" suggestion; immediately observe the delegation log
|
|
- [ ] Verify at least one `data-testid="delegation-entry"` appears with `data-status="running"`, the spinner is visible, and the "Sub-agent is working…" message is shown
|
|
- [ ] Within 60s verify the same entry transitions to `data-status="completed"` and the spinner is replaced with the actual result text
|
|
- [ ] Verify subsequent delegations append additional entries (the list grows; earlier entries are not removed)
|
|
|
|
#### Sequential Pipeline (Research -> Write -> Critique)
|
|
|
|
- [ ] Click the "Marketing post" suggestion; within 90s verify the delegation log contains at least 3 `data-testid="delegation-entry"` rows in this order: Research, Writing, Critique
|
|
- [ ] Verify each entry's `data-status` ends as `completed` (no `failed` rows under normal conditions)
|
|
- [ ] Verify the assistant chat reply concisely summarizes the work and references the critique output
|
|
|
|
#### Failure Path (Optional / Best Effort)
|
|
|
|
- [ ] If you can intentionally provoke an upstream failure (e.g. revoke the API key briefly, or disable network egress for the .NET backend container), trigger a delegation; verify the entry's `data-status="failed"` and the failure message is rendered in red
|
|
- [ ] Verify the assistant surfaces the failure briefly to the user instead of fabricating a result
|
|
|
|
### 3. Error Handling
|
|
|
|
- [ ] Send an empty message; verify it is a no-op (no user bubble, no assistant response, no new delegation entries)
|
|
- [ ] Send a non-task message ("hi"); verify the agent responds without invoking any sub-agent (no new delegation entries appear)
|
|
- [ ] Verify DevTools -> Console shows no uncaught errors during any flow above
|
|
|
|
## Expected Results
|
|
|
|
- Page loads within 3 seconds
|
|
- Single-sub-agent delegations complete within 30 seconds; full Research -> Write -> Critique chains complete within 90 seconds
|
|
- Each delegation row shows a visible `running` -> `completed` (or `failed`) transition; the running spinner is rendered while the secondary chat-client call is in flight
|
|
- Failed sub-agent calls are reported as `failed` rows with a structured error message — never silently turned into `completed` rows with garbage results
|
|
- No UI layout breaks, no uncaught console errors
|