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
61 lines
3.7 KiB
Markdown
61 lines
3.7 KiB
Markdown
# QA: Sub-Agents — Claude Agent SDK (Python)
|
|
|
|
## Prerequisites
|
|
|
|
- Demo is deployed and accessible at `/demos/subagents` on the dashboard host
|
|
- Agent backend is healthy (`/api/health`); `ANTHROPIC_API_KEY` is set on Railway; the FastAPI backend exposes `POST /subagents`
|
|
|
|
## Test Steps
|
|
|
|
### 1. Basic Functionality
|
|
|
|
- [ ] Navigate to `/demos/subagents`; verify the page renders within 3s with a left-side delegation log and a right-side `CopilotChat` pane
|
|
- [ ] Verify `data-testid="delegation-log"` is visible with heading "Sub-agent delegations"
|
|
- [ ] Verify `data-testid="delegation-count"` reads "0 calls" on first load
|
|
- [ ] Verify the empty-state placeholder reads "Ask the supervisor to complete a task. Every sub-agent it calls will appear here."
|
|
- [ ] Verify the chat input placeholder is "Give the supervisor a task..."
|
|
- [ ] Verify all 3 suggestion pills are visible with verbatim titles: "Write a blog post", "Explain a topic", "Summarize a topic"
|
|
|
|
### 2. Feature-Specific Checks
|
|
|
|
#### Multi-stage Delegation Flow
|
|
|
|
- [ ] Click the "Write a blog post" suggestion (cold-exposure training prompt)
|
|
- [ ] Within 5s verify `data-testid="supervisor-running"` appears with the "Supervisor running" pulse indicator
|
|
- [ ] Within 30s verify at least one `data-testid="delegation-entry"` appears with badge "Research" and `data-testid="delegation-status"` initially reading `running`
|
|
- [ ] Verify the entry's status flips to `completed` once the sub-agent returns and the `result` text is visible inside the entry's white inner panel
|
|
- [ ] Within 60s total verify additional delegation entries appear in order: Research -> Writing -> Critique (3 entries total in most cases)
|
|
- [ ] Verify `data-testid="delegation-count"` updates to match the number of entries (e.g. "3 calls")
|
|
- [ ] Verify the supervisor's final chat reply includes a brief summary of the produced deliverable
|
|
|
|
#### Delegation Entry Layout
|
|
|
|
- [ ] Each `data-testid="delegation-entry"` shows: a `#N` index, a sub-agent badge with the correct emoji (🔎 Research / ✍️ Writing / 🧐 Critique), a status chip, the task text after "Task:", and the sub-agent's result rendered with whitespace preserved
|
|
- [ ] Hover the supervisor running chip while a delegation is in flight — verify the pulse animation is present (no static-only state)
|
|
|
|
#### Sub-Agent Independence
|
|
|
|
- [ ] Click "Explain a topic" (LLM tool calling prompt) and wait for completion
|
|
- [ ] Verify the writing entry's `result` is a single polished paragraph (the writing sub-agent's signature)
|
|
- [ ] Verify the research entry's `result` is a bulleted list of 3-5 facts (the research sub-agent's signature)
|
|
- [ ] Verify the critique entry's `result` contains 2-3 actionable critiques
|
|
|
|
#### Supervisor State Reset Across Tasks
|
|
|
|
- [ ] After the first run completes, click "Summarize a topic" (reusable rockets)
|
|
- [ ] Verify NEW delegation entries are appended to the existing list (count keeps growing) — confirms `state["delegations"]` accumulates across turns within the same thread
|
|
|
|
### 3. Error Handling
|
|
|
|
- [ ] Send an empty message; verify it is a no-op
|
|
- [ ] If a sub-agent call fails (e.g. due to upstream rate limit), verify the failing entry is rendered with status `failed` and a result line starting with "sub-agent call failed:" — confirms the fail-loud path
|
|
- [ ] Verify DevTools -> Console shows no uncaught errors during any flow above
|
|
|
|
## Expected Results
|
|
|
|
- Page loads within 3 seconds
|
|
- First delegation entry appears within 30 seconds of submitting a non-trivial task
|
|
- Each delegation entry transitions from `running` -> `completed` (or `failed`) and the count badge stays in sync with `state["delegations"].length`
|
|
- Supervisor's final chat reply summarises the work and arrives within 90 seconds of submission
|
|
- No UI layout breaks, no uncaught console errors
|