PR #4756 renamed langgraph-python's `byoc-hashbrown` / `byoc-json-render`
slugs to `declarative-*` but kept the legacy IDs in the registry so the
other 17 integrations (which still declare `byoc-*` in their manifests)
don't drop out of the catalog. The dashboard then showed both rows side
by side under "BYOC (Bring Your Own Components)": the legacy IDs red
for langgraph-python (no manifest declaration) and the renamed IDs
green.
Mark the two legacy IDs `"deprecated": true` so the dashboard's "Show
deprecated" toggle hides them by default. The canonical declarative-*
rows stay visible. Data stays intact for the other 17 integrations
until they migrate.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
D5 probes were red for two demos because the aimock fixtures didn't
exist or were dispatched through the wrong Responses-API path.
- `harness/fixtures/d5/mcp-apps.json` (new) — the MCP Apps probe sent
"Open Excalidraw and sketch a system diagram" with no matching
fixture, so aimock 404'd and the agent threw `NotFoundError`.
Added a two-leg fixture: leg 1 emits a `create_view` MCP tool call
with Excalidraw element JSON; leg 2 is the `hasToolResult: true`
content reply. Mirrored verbatim into `aimock/d5-all.json` so the
Docker-baked aimock has the same matches.
- `harness/fixtures/d5/tool-rendering-reasoning-chain.json` — added
non-empty `content` fields to the first-leg fixtures (Tokyo weather
+ SFO/JFK flights). aimock's Responses-API dispatch routes
tool-call-only responses (no `content`) through
`buildToolCallResponse`, which silently drops the `reasoning`
payload; with a non-empty `content`, dispatch shifts to
`buildContentWithToolCallsResponse`, which emits the
reasoning_summary events the v2 `<ReasoningBlock>` needs to mount.
Mirrored into `d5-all.json`.
- `harness/fixtures/d5/reasoning-display.json` — added a second
matcher for the `reasoning-default` e2e pill prompt ("sky appears
blue"), keyed alongside the existing D5 probe matcher ("show your
reasoning step by step"). Both responses include `reasoning` fields
so the built-in `CopilotChatReasoningMessage` "Thinking…/Thought
for…" header lands.
- `aimock/feature-parity.json` — added a fixture for the agentic-chat
multi-turn name-recall test ("What name did I just give") replying
"You said your name is Alice." The matcher is intentionally narrow
to avoid colliding with the generic showcase-assistant catch-all.
Net D5 effect: `mcp-apps` and `tool-rendering-reasoning-chain` turn 1
go from red → green. The remaining red on `tool-rendering-reasoning-
chain` turn 2 is the deeper aimock+deepagents+Responses-API multi-
turn state-management issue (production with real OpenAI works); out
of scope per the original audit's Phase F.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The specs and QA markdowns had drifted from the demos they describe.
This commit brings every test contract into line with the actual demo
source — eliminating false-greens, false-fails, and stale assertions.
False-fail spec assertions (would fail every run):
- `agentic-chat.spec.ts` — rewrote from the old `change_background` /
`weather-card` / `useAgentContext` flow that no longer exists. New
spec exercises the vanilla `<CopilotChat>` + three suggestion pills
contract the simplified demo actually exposes.
- `gen-ui-tool-based.spec.ts` — asserted on UI text ("Use the sidebar
to generate charts", "Chart Generator") that doesn't exist; switched
to suggestion-pill assertions and scoped the SVG check to inside the
assistant-message bubble (was matching CopilotChat's send-button
SVG).
- `agent-config.spec.ts` — asserted heading "Agent Config Object" but
the demo has "Agent Config".
- `multimodal.spec.ts` — asserted a non-existent "Multimodal
attachments" heading; switched to the `multimodal-demo-root` testid.
- `chat-slots.spec.ts` — asserted `[data-testid="custom-assistant-
message"]` and the bare text "slot" — neither exists. The actual
signal is `data-slot-label="MessageView.AssistantMessage"` from the
SlotMarker wrapper.
- `reasoning-default.spec.ts` — asserted `[data-testid="copilot-
reasoning-message"]` and `[data-message-role="reasoning"]`; neither
is emitted by `CopilotChatReasoningMessage`. Switched to the text-
based "Thinking…/Thought for…" header label.
False-green spec assertions (passed for the wrong reason):
- `shared-state-read.spec.ts` — was a complete false-green: asserted
on "Sales Pipeline", "Total Pipeline", "Active Deals" but the demo
has been a Recipe Editor for some time. Rewrote against the
recipe-card / ingredients-container / instructions-container testids.
- 11 specs (agent-config, beautiful-chat, frontend-tools-async,
gen-ui-tool-based, gen-ui-agent, gen-ui-interrupt, hitl-in-chat,
hitl-in-app, multimodal, readonly-state-agent-context, voice) used
`[data-role="assistant"]` to gate "agent responded" — but the v2
react-core bundle never emits that attribute (it ships
`data-testid="copilot-assistant-message"`). Mechanical sweep to the
correct testid.
- Deleted `shared-state-write.spec.ts` (route consolidated into
`shared-state-read-write` earlier on this branch — spec targeted a
removed demo) and `renderer-selector.spec.ts` (asserted on a radio-
pill UI that no longer exists; the four "Declarative UI" variants
are now separate manifest demos).
QA drift:
- `qa/gen-ui-tool-based.md` documented a "Haiku Generator" demo with
haiku-card / japanese-line / english-line / haiku-image testids — a
demo that doesn't exist anywhere on this branch. Rewrote to match
the chart-rendering demo's actual testids and pill prompts.
- `qa/chat-slots.md` referenced "Custom Slot" pill / "Welcome to the
Slots demo" heading / "This welcome card is rendered via the
welcomeScreen slot." body text — all of which the slot-wrappers
refactor on this branch removed. Updated to match the
`custom-welcome-message` sub-slot that's actually rendered. Also
fixed max-w-4xl → max-w-5xl to match the page.
- `qa/shared-state-read.md` said default instruction is "Preheat oven
to 350 F" but the source has "Preheat oven to 350°F (175°C)".
- `qa/agentic-chat.md` rewrote to match the simplified vanilla-chat
demo (the previous QA documented `change_background` / `WeatherCard`
flows that no longer exist).
- `qa/reasoning-default.md` cited `kind: "testing"` in feature-
registry.json for the `reasoning-default` entry; the registry entry
has no `kind` field. Rewrote without the false cross-file claim.
- Deleted 4 orphan QA files for demos that don't exist:
`agentic-chat-reasoning.md`, `hitl.md`, `hitl-in-chat-booking.md`,
`shared-state-write.md`.
- Renamed `qa/reasoning-default-render.md` → `qa/reasoning-default.md`
to match the manifest cell name.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
User-facing renames so the showcase reads the way a cold visitor would
expect:
- `byoc-hashbrown` → `declarative-hashbrown` (and `byoc-json-render` →
`declarative-json-render`). The display titles already said
"Declarative UI: …"; only the URL slugs and folder paths still
leaked the internal BYOC ("Bring Your Own Components") jargon.
Renamed:
/demos/byoc-hashbrown → /demos/declarative-hashbrown
/demos/byoc-json-render → /demos/declarative-json-render
/api/copilotkit-byoc-* → /api/copilotkit-declarative-*
src/app/demos/byoc-* → src/app/demos/declarative-*
qa/byoc-*.md → qa/declarative-*.md
tests/e2e/byoc-*.spec.ts → tests/e2e/declarative-*.spec.ts
Internal Python module names + langgraph graph IDs stay legacy
(`byoc_hashbrown_agent.py`, `byoc_hashbrown`) — those are not
user-facing and renaming them is a separate cross-codebase pass.
- `a2ui-fixed-schema` slug intentionally unchanged.
- Tool Rendering trio parenthetical rename (Default → Catch-all →
Custom progression reads clearly as "how much do I customize?"):
Tool Rendering (Default) — unchanged
Tool Rendering (Custom default) → Tool Rendering (Catch-all)
Tool Rendering (Specific) → Tool Rendering (Custom)
- `tool-rendering-reasoning-chain` cell renamed from
"Generative UI: Rendering multiple tools" to
"Generative UI: Tool calls + reasoning" (the demo is about combining
reasoning + tool rendering, not about quantity of tools).
- `Open Generative UI: Default` / `Open Generative UI: Custom`
descriptions expanded so a visitor understands how Open Generative UI
differs from Tool Rendering (agent composes UI from a registered
library vs. attaching a renderer to a *named* backend tool).
- Showcase index now sorts demos within each tag by `manifest.features`
order. Previously demos appeared in manifest declaration order, which
ignored the team's curated "polished flagship → simplest start →
variants" arc.
Cross-cutting registry / harness / dashboard updates that fall out of
the rename:
- `shared/feature-registry.json` adds the two new IDs alongside the
legacy `byoc-*` (so the catalog stays valid; the other 17
integrations still declare `byoc-*` in their manifests).
- `shared/constraints.yaml` adds the new IDs to the
generative-ui-approach allow-list.
- `scripts/__tests__/generate-catalog.test.ts` updates the cell-count
expectations (45 features × 18 integrations = 810; 792 after docs-
only exclusion; 45 LGP cells = 38 wired + 1 stub + 6 unshipped).
- Harness probe `d5-byoc.ts` + `d5-byoc.test.ts` now route both slug
families through `preNavigateRoute` and exercise the new branches.
- `d5-feature-mapping.ts` and `shell-dashboard/live-status.ts` mirror
the dual-ID mapping so both legacy and renamed slugs roll up under
the same `byoc` D5 featureType.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Extracts duplicated logic into shared modules so each demo file reads
as the feature it teaches, not the boilerplate around it.
Python agents:
- `_a2ui_utils.py` (new) — `sanitize_a2ui_components` and
`has_root_component`, consumed by both `a2ui_dynamic.py` and
`beautiful_chat.py` (these previously duplicated the same defensive
validator inline).
- `byoc_hashbrown_prompt.py` (new) — the 56-line system prompt extracted
from `byoc_hashbrown_agent.py` so the agent file stays focused on the
`create_agent(...)` wiring.
- `beautiful_chat.py` secondary `ChatOpenAI` now passes
`streaming=True` (matching `a2ui_dynamic.py`) so aimock's SSE-only
fixture matcher sees the call in replay mode — without it the demo
surfaced "An internal error occurred" on every load.
- `multimodal_agent.py` — top-level `from pypdf import PdfReader` (was
lazy with three layers of `# pragma: no cover` exception handling
for stages that never failed independently); kept a single log line
at the outer except so Railway logs stay triageable.
- `gen_ui_agent.py` — switched from `deepagents.create_deep_agent` (whose
planner+sub-agent middleware ate enough supersteps to trip LangGraph's
default recursion limit on this single-tool ReAct loop) to plain
`langchain.agents.create_agent`. Comment explains the math.
- `tool_rendering_agent.py` — docstring no longer claims to back the
`tool-rendering-reasoning-chain` cell (it has its own agent file).
TypeScript / TSX demos:
- `_shared/parse-json-result.ts` (new) — extracted from
`tool-rendering/parse-json-result.ts`; now consumed by three demos.
- `_shared/slot-override.ts` (new) — `makeSlotOverride<T>` centralizes
the 11 `as unknown as` casts that `chat-slots/page.tsx` previously
scattered across the slot-override block.
- `shared-state-read` — extracted `RecipeCard` component + `types.ts`,
dropped the dual-state-sync pattern that had the read-only demo
locally mutating recipe state. Page is now a thin shell that publishes
edits via `agent.setState` and reads back via `agent.state.recipe`.
Also surfaces `runAgent` rejections via `console.error` instead of
the previous silent `.catch(() => {})`.
- `headless-complete/hooks/use-auto-scroll.ts`,
`headless-complete/hooks/use-typing-indicator.ts` (new) — extracted
from `chat.tsx`. The chat file shrinks by ~40 lines. Same silent-
rejection fix on `runAgent` as shared-state-read.
- `frontend-tools-async/fake-notes-db.ts` (new) — extracted from
`page.tsx`; the demo file no longer leads with 60 lines of fake-DB
scaffolding before `useFrontendTool` (the actual feature) appears.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Real demo-time bugs in the langgraph-python integration:
- `interrupt-headless` was rendering hardcoded stale slot dates from a
`DEFAULT_SLOTS` constant instead of reading `payload.slots` that the
backend `interrupt(...)` already supplies. Sibling `gen-ui-interrupt`
does this correctly. Headless variant now matches.
- `_shared/interrupt-fallback-slots.ts` (new) — the JS fallback for
when the backend returns no `slots` array. Generates relative to
Date.now() so the picker never shows past dates. Used by both
`interrupt-headless` and `gen-ui-interrupt`. Deletes the old stale-
literal `gen-ui-interrupt/fallback-slots.ts` (dates from April that
had already decayed).
- `interrupt_agent.py` — replaced hardcoded `timezone(timedelta(-7))`
PDT with `zoneinfo.ZoneInfo("America/Los_Angeles")` so the demo
doesn't lie about offsets in winter. Also fixed a Sunday edge case
where `next_monday` collapsed to the same date as `tomorrow` (both
Python and the JS fallback) — added a `<= 1` skip-a-week guard.
- `package.json#dev` ran `uvicorn agent_server:app --port 8000` but
`src/agent_server.py` was a 3-line stub with no `app` symbol AND the
API route pointed at port 8123. Replaced with the canonical
`langgraph_cli dev --port 8123` invocation; deleted the dead stub.
- `entrypoint.sh:47` smoke-checked `src/agents/tools.py` (a file that
never existed) so every Railway boot logged a phantom ERROR. Dropped.
- `reasoning_agent.py` and `tool_rendering_reasoning_chain_agent.py`
intentionally omit `CopilotKitMiddleware` (they exercise only
reasoning-token streaming, no frontend tools / app context). Added a
one-line comment so a future maintainer doesn't cargo-cult it back in.
- `subagents._invoke_sub_agent` text-block walker had a regression
where a `{"type":"text","text":null}` payload (a known provider
quirk) would crash `"".join(parts)` with `TypeError: sequence item
N: expected str instance, NoneType found`. Restored the
`isinstance(block.get("text"), str)` guard.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
## Summary
Four LangGraph Python showcase demos updated:
- **HITL In-app**: `CopilotChat` → `CopilotPopup`
(`defaultOpen={true}`). Tickets panel fills the viewport; chat is a
popup in the corner. Approval dialog still portaled to `<body>`.
- **Shared State: Streaming**: `CopilotChat` (custom aside) →
`CopilotSidebar`. Document view fills the page; sidebar opens by
default.
- **Shared State: Read + Write**: `CopilotPopup` → `CopilotSidebar`.
Card grid breakpoint bumped from `lg:` to `xl:` so cards stack instead
of pinching when the sidebar consumes ~480px on mid-size laptops;
`overflow-y-auto` on the wrapper keeps the page scrollable.
- **Shared State: Read (Recipe)**: visual overhaul with shadcn
primitives (`Card`, `Input`, `Select`, `Textarea`, `Badge`, `Button`,
`Spinner`, `Separator`). All `data-testid` attributes and
QA-doc-asserted strings preserved verbatim ("Make Your Recipe", "AI
Recipe Assistant", "+ Add Ingredient", "+ Add Step", "Improve with AI",
default ingredients/instructions, all 7 dietary preference labels, all 5
cooking-time labels, all 3 suggestions, etc.). React state-sync logic
preserved verbatim (no behavior change).
## Why
The chat surfaces were inconsistent across demos — HITL used a full-pane
chat where the demo's premise is "approval modals appear *outside* the
chat surface", and the shared-state demos mixed `CopilotChat` and
`CopilotPopup` instead of using the prebuilt `CopilotSidebar`. The
Recipe demo was raw Tailwind while the rest of the suite uses shadcn
primitives.
## Plumbing fixes that fell out of the work
- **`clsx` + `tailwind-merge` added to `package.json`** as direct deps.
They were imported by `src/lib/utils.ts` (the `cn` helper used by all
shadcn primitives) but only transitively resolvable, which broke `next
dev --turbopack`'s stricter module resolution.
- **`globals.css` rule**: `body[data-scroll-locked] { padding-right: 0
!important }`. Radix overlays (Select, Dialog, Popover) use
`react-remove-scroll-bar`, which measures the gap between viewport and
body inner width to detect scrollbar size — and our body uses
`margin-inline-end: 480px` to make room for `<CopilotSidebar />`. The
library mis-reads that 480px as scrollbar width and "compensates" with a
matching `padding-right`, which shrinks the content area and shifts the
centered card every time a dropdown opens. We have no real scrollbar
(`body { overflow: hidden }`), so the compensation is unnecessary —
neutralize it. Comment in the diff explains the rationale.
## Test plan
- [x] `next build` clean across all 54 routes
- [x] `oxlint` reports zero new warnings (only pre-existing patterns the
diff preserved verbatim)
- [x] Manually verified `/demos/hitl-in-app`,
`/demos/shared-state-streaming`, `/demos/shared-state-read-write`,
`/demos/shared-state-read` in browser (Chrome, dev server)
- [x] Verified the Recipe page's Select dropdowns no longer shift the
card when opened (the original motivation for the `globals.css` rule)
- [ ] HITL e2e suite (`tests/e2e/hitl-in-app.spec.ts`) — selectors
preserved (`getByPlaceholder("Type a message")`, suggestion-pill
testids, approval-dialog-* testids); CopilotPopup's `defaultOpen={true}`
mounts the chat input on first paint
- [ ] Streaming and Read e2e suites are stale pre-PR (reference content
that doesn't exist in source — "AI Document Editor", "Sales Pipeline")
and remain in the same state
## CR loop
Ran `cr-loop` (Round 1, 7 agents). Reclassified one finding to bucket
(d) per user direction (npm/pnpm lockfile-convention concern is a
different PR's subject — pre-existing across all
`showcase/integrations/*` and out of scope here). Procedure 3 audit
promoted no items to bucket (a); 24 bucket (c) items confirmed as
pre-existing and routed to follow-up backlog.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
LGP probe hung on Turn 2 (Find flights from SFO to JFK) after Turn 1
(weather Tokyo) succeeded. Root cause: the SFO/JFK first-leg fixture
matched on `hasToolResult: false`, but Turn 1's tool result remains in
the conversation by Turn 2, so the matcher skipped it and fell through
to the second-leg fixture (`hasToolResult: true`), returning narration
without the search_flights tool call. The probe then timed out waiting
for the FlightListCard testid that never mounted.
Fix: switch the second-leg fixture to `toolCallId` matching (the last
message must be a tool result with the specific call_id) and drop
`hasToolResult` from the first-leg fixture. The second-leg fixture
must come BEFORE the first-leg in file order because the matcher is
first-match-wins; with `toolCallId`, it cannot accidentally swallow
first-leg requests (whose last message is the user prompt, not a
tool result).
Also adds a `content` field to the Tokyo first-leg fixtures
(`get_weather` and `get-weather` Mastra-hyphen variants) so they route
through `buildContentWithToolCallsStreamEvents` instead of
`buildToolCallStreamEvents` — the latter codepath silently drops the
`reasoning` field, which is why the reasoning-block testid never
mounted on Turn 1 either before this change.
Tokyo (Turn 1) keeps the simpler `hasToolResult` pattern because it has
no prior turns; only the SFO/JFK fixture pair needs the toolCallId
shape to survive multi-turn use.
Switch HITL In-app to CopilotPopup; Shared State Streaming and Read+Write
to CopilotSidebar; widen card-grid breakpoint and add overflow scroll on
Read+Write so content stays usable when the sidebar consumes ~480px of
viewport. Re-skin the read-only Recipe demo with shadcn primitives,
preserving every data-testid and QA-doc-asserted string.
Add clsx and tailwind-merge as direct deps (previously only transitively
resolvable, breaking turbopack dev) and a globals.css rule to neutralize
the Radix scroll-lock padding-right that react-remove-scroll-bar injects
when it mis-detects body's margin-inline-end (CopilotSidebar) as
scrollbar width.
QA docs updated to reference the new chat surfaces.
The tool-rendering-reasoning-chain D5 probe has been red since the
probe was added (PR #4743) — the reasoningMessage slot's
<ReasoningBlock> never mounts because the agent doesn't emit
reasoning summaries.
Compared to the working reasoning_agent.py (which powers
reasoning-default + reasoning-custom and is green), the only
meaningful difference was the reasoning config:
reasoning_agent.py (works):
reasoning={"effort": "medium", "summary": "detailed"}
tools=[]
tool_rendering_reasoning_chain_agent.py (was broken):
reasoning={"effort": "low", "summary": "auto"}
tools=[get_weather, search_flights, ...]
`summary: "auto"` lets the model decide whether to emit a reasoning
summary. With tools present the model often skips it (chain-of-thought
goes straight into the tool call without a summary). `summary:
"detailed"` forces emission on every response, which lights up the
ReasoningBlock slot. Bumping effort medium so the surface visible to
the user reads as a real chain-of-thought, matching reasoning-display.
Probe diagnostics from prod confirmed the toolCalls were firing fine
(WeatherCard mounted, assistant text landed) — only the reasoning
emission was missing.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Swap every ChatOpenAI / init_chat_model call across the LGP agents
from the prior mix (gpt-4o-mini, gpt-4o, gpt-4.1, gpt-5-mini) to the
unified `gpt-5.4` model. Also updates the OPENAI_REASONING_MODEL env
default in reasoning_agent.py and tool_rendering_reasoning_chain_agent.py
so reasoning demos pick up the new model unless explicitly overridden.
Verified locally with the user's gpt-5.4 OpenAI access — all 39 LGP
demos render and respond correctly. The probe sweep on prod will
confirm the model name resolves end-to-end.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The e2e-readiness probe waits for any of a compound CSS selector
covering chat-input testids. /demos/auth renders a <SignInCard>
BEFORE mounting the chat surface (the chat-input testids only appear
post-authentication), so the readiness probe was timing out at 30s
with `per-demo deadline exceeded` and the auth cell rolled up to D2
even though the demo itself works fine end-to-end.
Add `[data-testid="auth-sign-in-card"]` to READY_SELECTORS so the
probe accepts the SignInCard as a valid "demo mounted" signal. The
end-to-end auth flow (sign in -> sign out -> sign back in -> assistant
response) is still covered by auth.spec.ts under the e2e-demos
dimension, so the readiness probe shouldn't be doing that work.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Two related changes that bring the dashboard's gold-standard view in
line with the desired naming convention and surface deprecated rows
behind a toggle (instead of hiding them at catalog generation).
## Naming alignment
Applied 28 renames in feature-registry.json + 20 in LGP manifest per
the user-provided mapping. Highlights:
- "Pre-Built CopilotChat" -> "Pre-Built: CopilotChat"
- "Headless Chat (Simple/Complete)" -> "Headless UI: Simple/Complete"
- "Multi-modal / File Uploads" -> "Attachements" (intentional spelling)
- "Controlled Gen-UI (Display)" -> "Generative UI: useComponent"
- "In-Chat HITL (use*)" -> "Human In/in the Loop: In-chat / Interrupts"
- "Headless Interrupt" -> "Human in the Loop: Headless Interrupts"
- "Declarative Generative UI (A2UI - *)" -> "Declarative UI: */* A2UI"
- "Fully Open-Ended Generative UI" -> "Open Generative UI: Default"
- "Tool Rendering ..." -> "Generative UI: Tool Rendering (...)"
- "Tool Rendering + Reasoning Chain" -> "Generative UI: Rendering multiple tools"
- "Agentic Generative UI ..." -> "Generative UI: Agent State"
- "Frontend Tools (...)" -> "Frontend Tools: ..."
- "Shared State (...)" -> "Shared State: ..."
- "State Streaming" -> "Shared State: Streaming"
- "Readonly State (Agent Context)" -> "Shared State: Frontend Context"
- "BYOC Hashbrown <-> json-render" -- labels intentionally swapped per
user instruction (demos were historically reversed; new labels
reflect what they actually do).
LGP manifest demos[].name updated to match feature-registry names so
the dojo and dashboard surface the same human-readable label.
## Show Deprecated toggle (feature-grid.tsx)
Added a checkbox in the matrix header -- default OFF -- that filters
feature rows where `feature.deprecated === true`. Toggle ON shows all
deprecated features across all integrations (audit trail); toggle OFF
hides those rows entirely so the gold-standard view stays clean.
Reverted the catalog-side filter from PR #4744 (which dropped LGP
cells for deprecated features at catalog-generation time). Now the
catalog emits cells uniformly for all (integration x feature) pairs,
and visibility is controlled at the dashboard layer. Toggling on
shows complete cross-integration data without missing-cell artifacts.
Affects 4 features marked deprecated:true in feature-registry.json:
agentic-chat-reasoning, hitl, hitl-in-chat-booking,
reasoning-default-render.
LGP cell count: back to 43 (38 wired + 1 stub + 4 unshipped). The 4
unshipped rows are hidden by default; toggle to surface them.
Tests: 18/18 catalog tests + 1588/1588 harness vitest passing.
validate-fixture-tool-surface clean.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three fixes that follow up on PR #4743 to bring LGP closer to fully-green
on the dashboard:
1. tool-rendering-reasoning-chain probe: was failing with
`expected [data-testid="reasoning-block"] to mount within 30000ms`.
Root cause: the demo's `<ReasoningBlock>` slot only mounts when a
reasoning-role message lands in the transcript, which requires
aimock to emit REASONING_MESSAGE_* events, which in turn requires
the fixture's first-leg response to carry a `reasoning` field. The
weather/Tokyo and SFO/JFK first-leg fixtures were missing it.
Mirrors the convention documented in reasoning-display.json:2.
Patched both source (harness/fixtures/d5/) and bundle (aimock/d5-all.json).
2. gen-ui-interrupt source fixture: the source fixture file was missing
the resume-leg toolCallId entries that already existed in the bundle.
Cosmetic mirror so re-bundling stays consistent. Same chip prompts +
same toolCallIds as interrupt-headless.json (both probes share the
same agent and aimock fixture set; the difference is the FRONTEND
rendering — useInterrupt inline vs useHeadlessInterrupt separate-pane).
3. Dashboard gold-standard filter: 4 deprecated/legacy features
(agentic-chat-reasoning, hitl, hitl-in-chat-booking,
reasoning-default-render) used to render as X-marked rows in the
LGP gold-standard dashboard view because LGP intentionally does
NOT implement them — they were consolidated into the modern shape
(reasoning-custom + reasoning-default; hitl-in-chat with
useHumanInTheLoop). Other 17 integrations still serve those legacy
demos, so we don't yank the features from feature-registry.json
entirely. Instead: marked them `deprecated: true` and updated
generate-registry.ts to skip emitting cells when a deprecated
feature is unshipped for an integration. LGP cells: 43 → 39 (the
4 deprecated rows disappear). Other integrations: unchanged
(audit trail preserved). Catalog total: 774 → 770.
Tests:
- 1588/1588 harness vitest passing
- 19/19 generate-catalog + generate-registry tests passing
(counts updated for the 4 dropped LGP cells + new deprecated-
feature filter test)
- validate-fixture-tool-surface clean (282 fixtures × 627 demos)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
## Summary
- 3 new D5 probes (multi-turn, agentic-chat-style) for
`/demos/{interrupt-headless, shared-state-read,
tool-rendering-reasoning-chain}` — closes the demo↔probe coverage gap so
every langgraph-python demo now has its own dashboard cell.
- Driver retry-once in `e2e-deep.ts` — transient `goto-error` /
`conversation-error` failures (≥2s on attempt 1) get one retry before
recording red, cutting ~10× the dashboard flap rate. Persistent
assertion-style fails skip retry.
- Drops the legacy dual-claim where `d5-shared-state.ts` owned both
`shared-state-read` AND `shared-state-write` for a single bidirectional
probe — `shared-state-read` now belongs to the standalone recipe-editor
probe.
## Scope rationale
LGP is the north-star integration; this PR codifies its current demo
surface in the test infra. **Other integrations may flip red on the new
probes — that's expected and welcome.** Cross-integration parity follows
in a separate wave; we're using LGP as the template.
## Files
- `showcase/harness/src/probes/scripts/d5-interrupt-headless.ts` (new) —
`useHeadlessInterrupt` flow: chip → interrupt popup → slot pick →
resume.
-
`showcase/harness/src/probes/scripts/d5-tool-rendering-reasoning-chain.ts`
(new) — combines reasoning-block slot + per-tool renderer (WeatherCard /
FlightListCard).
- `showcase/harness/src/probes/scripts/d5-shared-state-read.ts` (new) —
recipe-editor with neutral default agent, asserts `recipe-card` form
mounts AND agent references recipe context across turns.
- `showcase/harness/src/probes/drivers/e2e-deep.ts` — retry-once loop
around `runFeature`.
- `d5-registry.ts` / `d5-feature-mapping.ts` / `live-status.ts`
(dashboard) / LGP `manifest.yaml` / `feature-registry.json` /
`constraints.yaml` — wire the new featureTypes and features end-to-end.
- `d5-shared-state.ts` (+test) — drops dual-claim.
- 2 pre-existing test fixes folded in: `d5-gen-ui-interrupt.test.ts`
(mock updated to current evaluate-poll resume signal) and
`conversation-runner.test.ts` (preFill ordering assertion now matches
actual deferred-cascade contract).
- aimock `d5-all.json` — +2 shared-state-read fixtures.
interrupt-headless and tool-rendering-reasoning-chain reuse existing
fixtures whose substrings already match their chip prompts.
## Test plan
- [x] `pnpm vitest run` in `showcase/harness/` → **1588 / 1588 passing**
(was 1585 / 1588 with 3 pre-existing fails before this PR; 2 are fixed
here, 1 was an obsolete-mock issue).
- [x] `npx tsx showcase/scripts/validate-fixture-tool-surface.ts` →
clean (282 fixtures × 627 demos, no drift).
- [x] `npx tsx showcase/scripts/generate-registry.ts` → clean (18
integrations, 38 wired LGP features, 756 catalog cells).
- [x] `pnpm typecheck` in `showcase/harness/` → clean.
- [x] `d5-mapping-drift.test.ts` → green (CATALOG_TO_D5_KEY mirrors
REGISTRY_TO_D5).
- [ ] After merge: watch the e2e-deep dashboard rotation — the 3 new LGP
cells should write rows on first tick (no red zombies — these are
first-time emissions).
## Known follow-up (NOT in this PR)
`auth.spec.ts` test #5 ("signing back in re-mounts a fresh chat
surface") fails on Railway. Symptom: after sign-out → sign-in cycle, the
second `Hello again` send doesn't produce an assistant response within
30s. Looks like a `react-core/v2` ref-handling regression on
`<CopilotKit>` unmount/remount — deserves its own focused investigation
rather than expanding this PR.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
The previous "multi-key D5 mapping" tests used `shared-state-read-write`
as the example, but with the dual-claim drop that registry-id is now
single-key (only `shared-state-write`). Tests still passed logically
but the names were misleading.
- Rewrote both shared-state-read-write tests to assert the new
single-key contract directly (no more `d5:lgp/shared-state-read`
row in the live map — that row belongs to a different cell now).
- Added new beautiful-chat tests as the canonical multi-key example
(5 per-pill literals) so the multi-key code path stays exercised.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Closes the demo↔probe coverage gap for /demos/{interrupt-headless,
shared-state-read, tool-rendering-reasoning-chain} so every demo
under langgraph-python (the north-star integration) now has a D5
probe writing to its own PocketBase cell — not relying on cross-
demo umbrella records.
New probes (multi-turn, mirroring the agentic-chat structure):
- d5-interrupt-headless: exercises useHeadlessInterrupt — chip
prompt → backend interrupt(...) → app-surface popup → slot pick
→ resume → assistant confirmation. Distinct from gen-ui-interrupt
(which uses inline useInterrupt).
- d5-tool-rendering-reasoning-chain: combines reasoning-block slot
+ per-tool renderer (WeatherCard, FlightListCard) on the same
chat surface. Catches a regression in either side.
- d5-shared-state-read: recipe-editor demo (neutral default agent,
no tools) — verifies recipe-card form mounts AND agent reads
shared state across turns. Drops the dual-claim that
d5-shared-state.ts had on `shared-state-read` (now write-only).
Driver retry-once (e2e-deep.ts):
Probes that fail with a transient class (`goto-error` /
`conversation-error`) AND took ≥2s on the first attempt now retry
once before recording red. Persistent assertion-style failures
(sub-2s) and intentional aborts/feature-timeouts skip retry —
retrying a deterministic mismatch just burns clock and obscures
the signal. Cuts ~10× the dashboard flap rate.
Plumbing:
- D5FeatureType enum: +interrupt-headless, +tool-rendering-reasoning-chain.
- REGISTRY_TO_D5 (harness) + CATALOG_TO_D5_KEY (dashboard) mirror
the new mappings; d5-mapping-drift test enforces this.
- LGP manifest features + demos entries + constraints allowlist.
- feature-registry.json: +shared-state-read.
- aimock d5-all.json: +2 shared-state-read fixtures (interrupt-
headless + tool-rendering-reasoning-chain reuse existing fixtures
that already match their chip prompts).
Tests: 1588/1588 harness vitest green. validate-fixture-tool-surface
clean (282 fixtures × 627 demos, no drift). Two pre-existing test
fixes folded in — d5-gen-ui-interrupt assertion mock updated to
match the current evaluate-poll resume signal; conversation-runner
preFill ordering test now asserts the actual deferred-cascade
contract instead of a stricter pre-preFill ban that the runner
never enforced.
Known follow-up (not in this PR): auth.spec.ts test #5 ("signing
back in re-mounts a fresh chat surface") fails on Railway — second
sign-in's "Hello again" never produces an assistant response. Looks
like a react-core/v2 ref-handling regression on <CopilotKit>
unmount/remount; deserves its own focused investigation.
Other integrations may flip red on the new probes — that's
expected. We're treating LGP as the template; cross-integration
parity follows in a separate wave.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Lands the Bucket A framework fix and the fixture-correctness changes
needed to flip the remaining D4/D2 cells in the langgraph-python column
to D5. Full local D5 sweep is green (1 passed, 0 failed).
Framework: every Python `ToolMessage` constructed via `Command(update=...)`
now sets `name=` and `id=str(uuid.uuid4())`. Without these, @ag-ui/langgraph
synthesises TOOL_CALL_START events with `toolCallName: null` and
`parentMessageId: null`, which @ag-ui/client@0.0.53's Zod schema rejects;
the rejection is silently swallowed by `withAbortErrorHandling -> EMPTY`,
completing the SSE observable mid-stream so post-tool state never reaches
the consumer. Fix is applied across shared_state_streaming, shared_state_read_write,
gen_ui_agent, beautiful_chat, subagents (2 sites). Single-flag change in
a2ui_dynamic flips the secondary `_design_a2ui_surface` LLM call to
`streaming=True` so aimock's record/replay (SSE-only) sees it.
Fixtures (d5-all.json):
- toolCallId follow-ups for set_steps (3), display_flight, generate_a2ui (4),
schedule_meeting (2), generateSandboxedUi (7), and revenue chart so
multi-turn probes don't recurse into recursion-limit loops
- four hand-crafted secondary `_design_a2ui_surface` fixtures so A2UI
dynamic renders without a real LLM
- mcp-apps fixture rewritten to emit `create_view` tool call with a
minimal Excalidraw element payload; runtime middleware fetches the UI
resource and the iframe mounts
- AAPL and revenue `hasToolResult: true` follow-ups tightened to
`toolCallId` so they don't match cross-turn after prior turns' tool
results
- voice fast-path content-only fixture
- beautiful-chat-schedule-meeting first-turn fixture gains content so
the conversation runner sees an assistant message before the picker
click assertion
Probes: bumped per-card waitForSelector in d5-gen-ui-headless-complete from
15s to 60s — recharts ResponsiveContainer can be slow under 4 sequential
turns.
Shell-dojo: hide CLI Start Command from the dojo navigation via
`HIDDEN_DOJO_FEATURE_IDS`. Registry/manifests untouched so
harness/parity/dashboard still see it.
Lands the Bucket A framework fix and the fixture-correctness changes
needed to flip the remaining D4/D2 cells in the langgraph-python column
to D5. Full local D5 sweep is green (1 passed, 0 failed).
Framework: every Python `ToolMessage` constructed via `Command(update=...)`
now sets `name=` and `id=str(uuid.uuid4())`. Without these, @ag-ui/langgraph
synthesises TOOL_CALL_START events with `toolCallName: null` and
`parentMessageId: null`, which @ag-ui/client@0.0.53's Zod schema rejects;
the rejection is silently swallowed by `withAbortErrorHandling -> EMPTY`,
completing the SSE observable mid-stream so post-tool state never reaches
the consumer. Fix is applied across shared_state_streaming, shared_state_read_write,
gen_ui_agent, beautiful_chat, subagents (2 sites). Single-flag change in
a2ui_dynamic flips the secondary `_design_a2ui_surface` LLM call to
`streaming=True` so aimock's record/replay (SSE-only) sees it.
Fixtures (d5-all.json):
- toolCallId follow-ups for set_steps (3), display_flight, generate_a2ui (4),
schedule_meeting (2), generateSandboxedUi (7), and revenue chart so
multi-turn probes don't recurse into recursion-limit loops
- four hand-crafted secondary `_design_a2ui_surface` fixtures so A2UI
dynamic renders without a real LLM
- mcp-apps fixture rewritten to emit `create_view` tool call with a
minimal Excalidraw element payload; runtime middleware fetches the UI
resource and the iframe mounts
- AAPL and revenue `hasToolResult: true` follow-ups tightened to
`toolCallId` so they don't match cross-turn after prior turns' tool
results
- voice fast-path content-only fixture
- beautiful-chat-schedule-meeting first-turn fixture gains content so
the conversation runner sees an assistant message before the picker
click assertion
Probes: bumped per-card waitForSelector in d5-gen-ui-headless-complete from
15s to 60s — recharts ResponsiveContainer can be slow under 4 sequential
turns.
Shell-dojo: hide CLI Start Command from the dojo navigation via
`HIDDEN_DOJO_FEATURE_IDS`. Registry/manifests untouched so
harness/parity/dashboard still see it.
The framework selector pill in the sidebar tinted its 40px icon tile
with bg-[var(--accent)]/25 when a framework was active. In light mode
that paints as soft lavender against the lavender pill -- the
canonical look. In dark mode it paints as a dark muted purple, and
the CopilotKit kite (which is itself purple-toned) blends straight
into it -- the brand mark essentially disappears.
Add dark:bg-white/10 so the active tile flips to a neutral elevated
surface in dark mode. Light mode keeps the lavender. The kite stands
out against white/10, and the other framework brand marks (Mastra,
LangGraph, CrewAI, etc.) all read cleanly against the neutral too --
no framework loses contrast in the swap.
The framework-scoped routes had two more places still rendering against
the pre-wave3 shell that the root /docs page just got migrated off of:
- FrameworkLandingPage (e.g. /mastra, /langgraph-python) used the old
240px sidebar with p-4 + bg-[var(--bg)] + browser-default scrollbar,
plus a max-w-4xl content column with no centering.
- NotAvailableForFrameworkPage (rendered when a slug exists for some
frameworks but not the URL's) used the same old shell.
Move both onto the SidebarNav + .docs-content-wrapper +
max-w-[900px] mx-auto pattern docs-page-view uses, and update RenderNav
to match the new section/page/group treatment from OverviewNavItem
(15px banner sections at depth 0, 11px text-faint demoted labels at
depth > 0, h-10 rounded-lg pill page links with dark-aware hover,
border-l tree on nested groups). Picking a different framework now
produces the same chrome as the root overview, instead of revealing
the old shell.
Tighten the gap between the page header and the body to canonical's
mb-8 (was mb-14 with a responsive ladder that opened a half-inch hole
at xl widths between the description paragraph and the first prose
paragraph).
Align the sidebar treatment to canonical:
- Section header banner uses the same Plus Jakarta default-weight
uppercase + tracking as canonical's separator, sized up to 15px so
it sits above the link list as a clear divider rather than a tiny
caption below it.
- Section divider rule uses --border (white/10 in dark, #d9d9e0 in
light) so the horizontal line survives the dark token set.
- Active-link pill picks up dark-mode contrast: --bg-hover surface
with a 1px white/10 ring instead of the near-flat --bg-surface
that read as undifferentiated against the sidebar bg in dark.
- Idle pages get a white/5 hover affordance in dark.
- Nested section separators (depth > 0) demote to a quiet 11px
uppercase label in --text-faint with no divider rule, so the
Build Generative UI > Controlled / Declarative / Open-Ended
subsection breaks read as inline labels inside their parent
group instead of competing banner headers.
Move the root /docs overview route onto the same SidebarNav +
.docs-content-wrapper + max-w-[900px] mx-auto pattern docs-page-view
uses, and rewrite OverviewNavItem so sections, pages, and groups
paint with the same tokens as the per-doc routes -- previously the
root was still rendering against the pre-wave3 shell with a 240px
sidebar, p-4 padding, browser-default scrollbar, and an off-center
max-w-4xl content column.
Rename the "Give Your App Agent Powers" main-meta section to
"Adding Agent Powers" per product copy.
The TOC scrollspy used IntersectionObserver with a -20%/-70% root
margin band, which never fires for the last heading once the user
has scrolled it past that band. The active state stayed parked on
whichever heading last entered the band even when the user had
clearly arrived at the document end.
Replace with a scroll listener on .docs-content-wrapper that walks
the heading list, picks the last heading whose top has crossed the
trigger line (~25% from the viewport top), and forces the final
heading active when the scroll container is at scrollMax. Falls back
to window scroll for routes that don't wrap content in
.docs-content-wrapper.
Add a .dark token block to globals.css mirroring canonical
docs.copilotkit.ai for every var the wave3 chrome consumes (--bg,
--bg-surface, --bg-elevated, --bg-hover, --border, --border-dim,
--sidebar, --glass-background, --text*, --accent*, --violet*, --blue,
--scrollbar-color, --scrollbar-track). The navbar already shipped a
Toggle theme button + sun/moon SVGs + documentElement.classList
.toggle('dark') + localStorage.theme persistence; this commit makes
that toggle paint the rest of the page because all wave3 chrome
(sidebar, navbar, banner, callouts, tables, TOC, content wrapper)
consumes those vars.
Add @custom-variant dark (&:is(.dark *)) so dark: Tailwind utilities
react to the .dark class instead of prefers-color-scheme. Without
this, the navbar's class-driven swap pairs (slanted-end-border-dark
vs -light, theme-moon vs theme-sun, every dark: utility) are dead
when the theme toggle runs.
Add an inline beforeInteractive script in <head> that reads
localStorage.theme (falling back to prefers-color-scheme) and applies
the class before first paint, with suppressHydrationWarning on <html>
so Next.js doesn't revert the class to match the server output.
Apply scrollbar-width: thin and scrollbar-color to .docs-content-wrapper
and the sidebar's inner scroll container so the thumb tracks the
active theme instead of paying the bright browser default that pops
against dark surfaces.
Bump dark-mode contrast on the icon-button hover surface in the
navbar (GitHub, Discord, theme toggle) to a rounded black/5 in light
and white/10 in dark so the buttons read as interactive.
The search modal renders inside SearchTrigger, which lives in the
navbar's right cluster. The cluster has backdrop-blur-lg, and
backdrop-filter creates a containing block for fixed-position
descendants. The modal's `fixed inset-0` overlay was therefore being
clamped to the cluster's bounding rect (~505x70 at 1440x900) instead
of the viewport, so the overlay+card rendered as a tiny clipped strip
under the search button.
Wrap SearchModalWrapper in createPortal mounted on document.body. The
modal now resolves position: fixed against the viewport like a normal
overlay.
The 53 hard-500 URLs in the public sitemap split into three independent
root causes, all surfaced in production-mode rendering only because the
underlying issues throw inside next-mdx-remote:
1. tutorials/ai-powered-textarea/step-2-setup-copilotkit and
tutorials/ai-todo-app/step-2-setup-copilotkit reference
<CopilotCloudConfigureCopilotKit>,
<SelfHostingCopilotRuntimeConfigureCopilotKit>, and
crewai-flows/quickstart references <CloudCopilotKit> — three
unsuffixed component names whose only registered counterparts in
docsComponents end in "Provider". MDX rendering throws "Expected
component X to be defined" and 500s. Adds the unsuffixed names as
aliases of the existing Provider stubs in mdx-registry.
deploy-agentcore (langgraph variants + aws-strands) uses
<Content framework="..." />, also unregistered. Adds Content as a
children-passthrough stub for the same reason.
2. Three langgraph tutorial pages (agent-native-app/step-6-shared-state,
ai-travel-app/step-3-setup-copilotkit,
ai-travel-app/step-4-integrate-the-agent) place a closing </Step>
tag immediately under a markdown bullet list with no blank line
separator. The remark parser treats the closing tag as a list-item
continuation, errors out with "Expected the closing tag </Step>",
and ships a 500. Adds the missing blank line before the close tag.
3. Five MDX files (llamaindex + adk shared-state/predictive-state-updates,
pydantic-ai shared-state/in-app-agent-write, plus crewai-flows and
pydantic-ai human-in-the-loop/index — last two not in the 53 but
share the bug) use {/\\* ... \\*/} where the asterisks are escaped.
Acorn cannot parse the resulting expression and the page 500s.
Replaces the escapes with proper {/* ... */} JSX comments.
Verified: a clean production build of shell-docs followed by
`npx next start` and a curl probe of all 53 URLs from
validation/test2_results.json returns 200 across the full set with
zero MDX or React errors in the server log.
Two issues found in Phase 4 validation against docs.showcase.copilotkit.ai.
1. 31 entries in seo-redirects.ts had source === destination, causing
middleware to issue infinite 301 loops on canonical URLs like
/frontend-tools, /faq, /human-in-the-loop. Remove the dead entries
and add a defense-in-depth skip-when-equal guard in middleware so
future drift cannot regress.
2. Framework-scoped paths (e.g. /agno/frontend-actions) bypassed the
redirect catalog entirely because the pathIsFrameworkScoped short-
circuit fired before any catalog lookup. Reorder middleware so the
exact-match catalog is consulted first for every request, including
framework-scoped paths. Wildcard scan still skips legacy patterns
that would hijack canonical framework URLs, but allows same-framework
wildcard rewrites (e.g. /agno/concepts/:path* -> /agno) to fire.
85 framework-scoped redirects across 18 registry slugs now resolve
instead of soft-404ing.
Verified by curl probes against localhost: all 85 framework-scoped
catalog entries 301 to the expected destination, all 31 former self-
loop URLs return 200, and canonical framework URLs (/agno, /langgraph-
python/quickstart, etc.) still pass through unchanged.
The InlineDemo Code tab constructs a feature-viewer.copilotkit.ai URL
from the integration's docs-folder name, but feature-viewer expects its
own slug scheme. Six framework slugs 404'd outright (built-in-agent,
google-adk, claude-sdk-python, claude-sdk-typescript, ms-agent-python,
ms-agent-dotnet) and two more were named differently (crewai-crews
needed crewai, llamaindex needed llama-index). Demo IDs also diverged
(gen_ui_tool_based vs tool_based_generative_ui, hitl_in_chat vs
human_in_the_loop, etc.) so even when the framework slug was right the
Code panel rendered an empty 404 page.
Add getFeatureViewerSlug() and getFeatureViewerDemoId() to registry.ts
with explicit override maps. Both return null when the integration or
demo has no feature-viewer counterpart. Update mdx-registry.tsx to use
both and to suppress the Code tab (rendering the Demo iframe alone)
whenever either helper returns null.
Verified by probing feature-viewer.copilotkit.ai for each (framework x
demo) combination using NEXT_HTTP_ERROR_FALLBACK soft-404 detection plus
inspection of the rendered code panel; all post-fix URLs that the
helpers emit resolve to real code panels for the six demos
feature-viewer ships (agentic_chat, tool_based_generative_ui,
agentic_generative_ui, predictive_state_updates, shared_state,
human_in_the_loop).
/langgraph-python/frontend-tools referenced regions
frontend-tool-registration and frontend-tool-handler which were missing
markers on the production demo. Added in-place @region markers on the
existing useFrontendTool block in
showcase/integrations/langgraph-python/src/app/demos/frontend-tools/page.tsx
since the demo is a clean teaching example.
/langgraph-python/custom-look-and-feel/slots referenced regions
register-welcome-slot, register-assistant-message-slot, and
register-disclaimer-slot. The chat-slots production demo registers ~12
slot overrides at once with `as unknown as typeof X` casts that obscure
the per-pattern teaching shape, so added a sibling
slot-overrides.snippet.tsx file (mirrors the llamaindex chat-slots
sibling pattern) with the three minimal teaching regions.
Verified by re-bundling demo-content.json, running shell-docs production
build, and curling both pages on a local server: zero Missing snippet
boxes, and the region code (change_background, CustomWelcomeScreen,
CustomDisclaimer, CustomAssistantMessage) renders on the pages.
The active-link pill in the docs sidebar rendered flush against the
scroll gutter because the inner scroll container had no right padding;
canonical adds pr-1 on its scroll container so the pill stops 4px short
of the scrollbar. Match that.
The content column used px-8 py-6 xl:px-16 xl:py-12 with a non-centered
max-w-[900px] cap, which pushed content 32px to the right of canonical
at xl widths and left a wide gap between content and the right rail.
Replace with canonical's exact pattern: px-4 py-6 md:px-6 md:pt-8
xl:px-8 xl:pt-14 outside, max-w-[900px] mx-auto inside, so the column
centers between sidebar and TOC and the h1 lands at the same x as
docs.copilotkit.ai at 1440.
Three classes of regression are now pinned:
1. Secondary-LLM tool name doesn't collide with the A2UI middleware's
default intercept list (`render_a2ui`). New
`src/agents/test_a2ui_internal_tools.py` parametrises over
`beautiful_chat._design_a2ui_surface`, `a2ui_dynamic._design_a2ui_surface`,
and `a2ui_fixed.display_flight` and asserts none match the
middleware's `a2uiToolNames` default. Catches accidental rename
reverts that would re-enable the bypass.
2. `generate_a2ui` force-pins the canonical `catalog_id` even when the
secondary LLM hallucinates a wrong one. The new test stubs
`ChatOpenAI` with a fake response carrying a bogus catalogId and
asserts the surface op carries the module's `CUSTOM_CATALOG_ID`.
3. `generate_a2ui` short-circuits with a clean error string when the
LLM emits a root component without a `component` field — never
feeds the renderer the partial tree that surfaced as the "Cannot
create component root without a type" infinite-loop.
7 unit tests, all green locally (`pytest src/agents/test_a2ui_internal_tools.py`).
E2E tests on the same fixes now also assert:
- No `A2UI render error: Catalog not found` banner on the page after
Beautiful Chat → Sales Dashboard, Declarative Gen UI → BarChart, and
A2UI Fixed Schema → Find SFO → JFK round-trips.
- No `Cannot create component … without a type` banner on the same
three pills.
- Exactly ONE flight card on A2UI Fixed Schema (was 6+ on deploy
pre-fix from the `display_flight` loop) — `Flight Details` count
pinned to 1, `Book flight` count pinned to 1.
- At most one ResponsiveContainer on the BarChart pill (loops would
stack multiple).
- At most two ResponsiveContainers on Beautiful Chat → Sales Dashboard
(one pie + one bar = single dashboard render).
agent-config: drop the "introduce yourself per your config" baseline — it
substring-matched every prefixed probe prompt (tone:, expertise:,
responseLength:), forcing byte-identical responses and masking the
per-knob behavior the cell is meant to demonstrate.
shared-state-streaming: add toolCallId-keyed follow-up fixtures
(poem/email/quantum) above each first-turn entry so the matcher returns
content-only after the tool result lands. Without these the unchanged
last user message kept re-matching the first-turn fixture, the agent
re-fired write_document, and langgraph hit its 100-step recursion
limit. The frontend state-binding regression that prevents the streamed
document from rendering is a separate framework-level issue.
Synced to showcase/aimock/d5-all.json so replay-mode picks up both
fixes.
## Summary
Follow-up to #4733. The Sales Dashboard pill on Beautiful Chat and the
KPI Dashboard pill on Declarative Gen UI were still failing on deploy
with:
- `A2UI render error: Catalog not found: declarative-gen-ui-catalog`
(beautiful-chat)
- `A2UI render error: Cannot create component root without a type`
infinite loop (declarative-gen-ui)
### Root cause
`@ag-ui/a2ui-middleware`'s default `a2uiToolNames = ["render_a2ui"]`
makes the middleware **synthesise ACTIVITY_SNAPSHOT events from the
streaming tool-call args of any matching call**, using the LLM's RAW
`catalogId` + `components` before the Python tool body runs. Both
`generate_a2ui` implementations bound a structured-output helper named
`render_a2ui` to a secondary LLM — so the secondary LLM's hallucinated
`catalogId` and malformed root components were getting emitted to the
frontend through the bypass.
The force-pin and defensive validation #4733 added were correct but ran
on the tool-result; the middleware had already fired its synthetic
events from the streaming args.
### Fix
Rename the internal helper from `render_a2ui` to `_design_a2ui_surface`
so it falls outside the middleware's intercept list. The outer
`generate_a2ui`'s `a2ui.render(operations=...)` return is then the only
path to the frontend, and the Python validation layer is authoritative
again.
Two files: `src/agents/beautiful_chat.py`, `src/agents/a2ui_dynamic.py`.
No frontend / runtime / package changes.
## Test plan
- [x] **Local — Beautiful Chat → Sales Dashboard pill**: renders
dashboard surface (Total Revenue / New Customers / etc.) with no errors.
Previously: `Catalog not found: declarative-gen-ui-catalog`.
- [x] **Local — Beautiful Chat → Search Flights pill**: still renders
FlightCards (regression check on the previous fix).
- [ ] **Deploy — Beautiful Chat → Sales Dashboard pill**: confirm no
`Catalog not found` error.
- [ ] **Deploy — Declarative Gen UI → KPI Dashboard pill**: confirm no
`Cannot create component root without a type` loop.
Two follow-up fixes layered on the previous internal-tool rename:
(1) `a2ui_fixed.py` — fixed-schema demo infinite loop on deploy. The
`display_flight` tool returns the raw `a2ui.render(...)` JSON descriptor
as its tool result. gpt-4o-mini reads that opaque blob, can't tell the
flight was rendered, and re-calls `display_flight` indefinitely (visible
on the deployed showcase as 6+ duplicate flight cards stacked under
repeated assistant text). Local was just lucky.
Hardened the docstring + system prompt to spell out: the JSON return
value is the surface descriptor, the card is already rendered, do NOT
call again, reply with one short confirmation and stop.
(2) Rename `render_a2ui` → `_design_a2ui_surface` in shared and
langgraph-python parity copies of `tools/generate_a2ui.py` (+
`tools/__init__.py` re-export `RENDER_A2UI_TOOL_SCHEMA` →
`DESIGN_A2UI_SURFACE_TOOL_SCHEMA`), and in `showcase/shared/typescript/
tools/generate-a2ui.ts`. These shared helpers were the source-of-truth
for the secondary-LLM tool name across integrations; renaming here keeps
parity with the langgraph-python agents already renamed in
`beautiful_chat.py` / `a2ui_dynamic.py`. Other framework integrations
keep their own `render_a2ui` for now (separate parity sweep).
(3) `showcase/aimock/feature-parity.json` — added a sibling fixture
matching `toolName: "_design_a2ui_surface"` for the beautiful-chat Sales
Dashboard pill so the langgraph-python e2e suite still hits a
deterministic mock on Railway. The original `render_a2ui` fixture is
kept above it so other integrations whose secondary LLM still requests
`render_a2ui` continue to match.
(4) Comment update in `beautiful-chat.spec.ts` to name the new internal
tool.
Updates the docs navbar and showcase shell-docs brand-nav so the "Talk
to engineers" CTA points at copilotkit.ai/talk-to-an-engineer instead
of the deprecated /contact-us endpoint.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The A2UI middleware (`@ag-ui/a2ui-middleware`) defaults `a2uiToolNames` to
`["render_a2ui"]` and synthesises ACTIVITY_SNAPSHOT events from the
streaming tool-call args of any matching call — using the LLM's RAW
catalogId and components verbatim, before the Python tool body has a
chance to validate or normalise.
Both `beautiful_chat.py` and `a2ui_dynamic.py` use a `generate_a2ui` tool
that internally invokes a secondary LLM bound to a structured-output
`render_a2ui` helper. Because the helper's name matched the middleware's
default intercept list, the secondary LLM's hallucinated catalogId
(`declarative-gen-ui-catalog` leaking into the beautiful-chat dashboard)
and malformed root components (no `component` field on KPI dashboard)
were emitted to the frontend bypass, surfacing as:
- "A2UI render error: Catalog not found: declarative-gen-ui-catalog" on
the beautiful-chat Sales Dashboard pill
- "A2UI render error: Cannot create component root without a type"
infinite-loop on the declarative-gen-ui KPI Dashboard pill
The earlier force-pin of `catalog_id` and the defensive component sweep
in `generate_a2ui` were correct but ran too late — they execute on the
tool-result, after the middleware has already fired surface events from
the streaming args.
Fix: rename the internal helper to `_design_a2ui_surface` (and update
`tool_choice`, prompt header, and module docstring) so it falls outside
the middleware's intercept list. The explicit `a2ui.render(...)` ops the
outer `generate_a2ui` returns are then the only path to the frontend,
and our Python validation layer is authoritative.
Verified locally: Beautiful Chat → Sales Dashboard pill renders Total
Revenue / New Customers / etc. with no errors.
## Summary
- Beautiful Chat **Search Flights** pill: restored
`_build_flight_components` so the agent emits a flat literal-children
FlightCard tree (the structural-children template form via
`flight_schema.json` + `update_data_model` doesn't expand correctly
through GenericBinder for our custom catalog — it was working until the
recent flagship-cell pass swapped it back). FlightCards render again
instead of falling through to the default tool card.
- Beautiful Chat **Sales Dashboard** pill: hardened `generate_a2ui` so
the secondary LLM gets explicit catalog-id + component-shape rules and
the resulting `catalog_id` is force-pinned to the registered catalog.
Kills the "Catalog not found: declarative-gen-ui-catalog" sibling-demo
hallucination.
- **Declarative Gen UI** (`a2ui_dynamic.py`): same `generate_a2ui`
hardening, plus a defensive sweep that drops malformed components and
bails clean when the LLM omits a typed root. Kills the "Cannot create
component root without a type" infinite-loop renderer error reported on
the KPI Dashboard pill.
Two files touched (`src/agents/beautiful_chat.py`,
`src/agents/a2ui_dynamic.py`); no frontend / runtime / package changes.
Existing aimock fixtures in `feature-parity.json` already use the
canonical catalogId and well-formed components, so e2e specs should pass
without fixture changes.
## Test plan
- [x] Verified locally: `langgraph_cli dev` + `next dev`, clicked
**Search Flights** on `/demos/beautiful-chat` — Delta DL 405 ($329) and
United UA 120 ($289) FlightCards rendered live with airline, route,
times, status, Select.
- [x] Verified locally: clicked **Show a KPI dashboard** on
`/demos/declarative-gen-ui` — REVENUE / SIGNUPS / CHURN metric tree
rendered cleanly, no "Cannot create component root without a type"
error.
- [ ] CI / `nx run @copilotkit/showcase-langgraph-python:e2e`
(beautiful-chat spec already authored against the literal-children
form).
Tyler Slaton