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
55 lines
3.2 KiB
Markdown
55 lines
3.2 KiB
Markdown
# QA: Sub-Agents — AWS Strands
|
|
|
|
## Prerequisites
|
|
|
|
- Demo is deployed and accessible at `/demos/subagents` on the dashboard host
|
|
- Agent backend is healthy (`/api/health`); `OPENAI_API_KEY` is set; the Strands agent server (`agent_server.py`) is reachable at `AGENT_URL`
|
|
|
|
## Test Steps
|
|
|
|
### 1. Basic Functionality
|
|
|
|
- [ ] Navigate to `/demos/subagents`; verify the page renders within 3s with a wide delegation log on the left and a `CopilotChat` pane on the right
|
|
- [ ] Verify `data-testid="delegation-log"` is visible with heading "Sub-agent delegations"
|
|
- [ ] Verify the empty state reads "Ask the supervisor to complete a task. Every sub-agent it calls will appear here."
|
|
- [ ] Verify `data-testid="delegation-count"` reads "0 calls"
|
|
- [ ] Verify the chat input placeholder is "Give the supervisor a task..."
|
|
- [ ] Verify all 3 suggestion pills are visible: "Write a blog post", "Explain a topic", "Summarize a topic"
|
|
|
|
### 2. Feature-Specific Checks
|
|
|
|
#### Supervisor delegates to sub-agents (research → write → critique)
|
|
|
|
- [ ] Click the "Write a blog post" suggestion (sends a research/write/critique sequence prompt)
|
|
- [ ] Within 5s verify `data-testid="supervisor-running"` appears next to the heading with the pulsing indicator
|
|
- [ ] Within 60s verify `data-testid="delegation-count"` reads at least "3 calls" and at least 3 `data-testid="delegation-entry"` rows are rendered
|
|
- [ ] Verify the first entry has the `🔎 Research` badge, a non-empty `Task:` line, and a result body containing 3-5 bullet points
|
|
- [ ] Verify a subsequent entry has the `✍️ Writing` badge with a polished paragraph in the result body
|
|
- [ ] Verify a subsequent entry has the `🧐 Critique` badge with 2-3 actionable critiques
|
|
- [ ] Verify each entry shows status `completed` (green) once the sub-agent has returned
|
|
- [ ] Once the supervisor returns a final assistant text message, verify `supervisor-running` disappears
|
|
|
|
#### Live updates during the run
|
|
|
|
- [ ] Click the "Explain a topic" suggestion
|
|
- [ ] Verify entries appear ONE-AT-A-TIME (the count climbs from 0 → 1 → 2 → 3 over multiple seconds rather than all appearing at once) — this confirms each sub-agent's `state_from_result` hook emits an independent `StateSnapshotEvent`
|
|
- [ ] Verify entry numbers (`#1`, `#2`, `#3`) are sequential and stable
|
|
|
|
#### Multi-turn persistence
|
|
|
|
- [ ] After the first run completes, send "Now do the same for solar panels." — verify the delegation log GROWS (existing rows kept; new rows appended); the count should continue from where it left off (e.g. "3 calls" → "6 calls")
|
|
|
|
### 3. Error Handling
|
|
|
|
- [ ] Send an empty message — verify it is a no-op
|
|
- [ ] Send "Hello" (no task to delegate); verify the supervisor responds with a short text reply and NO new delegation entries are added
|
|
- [ ] Verify DevTools -> Console shows no uncaught errors during any flow above
|
|
|
|
## Expected Results
|
|
|
|
- Page loads within 3 seconds
|
|
- First delegation entry appears within 15s of submitting a task; full research → write → critique loop completes within 60s
|
|
- Each sub-agent invocation produces exactly one delegation entry with a non-empty `task` and `result`
|
|
- Supervisor's final summary references the work that was delegated
|
|
- No UI layout breaks, no uncaught console errors
|