Task 1 of OSS-582 (frontend parity). Bring the app chrome + beautiful-chat
byte-identical to the langgraph-python north star:
- globals.css: adopt LGP theme (@theme inline tokens + green palette)
- middleware.ts: add (was missing) — sets x-pathname like LGP
- layout.tsx: adopt LGP structure; keep FastAPI in title/log (identity carve-out)
- beautiful-chat/page.tsx: sync stale doc comment
Also fix a Dockerfile parity gap: fastapi was missing the COPY manifest.yaml
that LGP has. demos/layout.tsx reads manifest.yaml at request time via
generateMetadata (headers() -> dynamic), so without it every /demos/* route
crashed with an RSC render error (ENOENT /app/manifest.yaml).
Adds the opt-in secondary entry point @copilotkit/angular/mcp-apps for
rendering MCP Apps (MCP ext-apps) inline in the chat:
- CopilotMCPAppsActivityRenderer plus a ready-to-register
mcpAppsActivityRendererConfig for activityType mcp-apps
- CopilotMCPAppsWidget loads the app's ui:// resource from the configured
MCP server, embeds it in a sandboxed iframe, and connects an AppBridge
that relays tool input/result, size changes, links, and log messages
- provideMCPApps registers server URLs and the host identity, capabilities,
and context announced to embedded apps
- @modelcontextprotocol/sdk and @modelcontextprotocol/ext-apps are optional
peer dependencies; the main entry point stays free of MCP imports
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
## What
Fixes multi-turn chat on every mastra showcase demo, which 400s on the
2nd turn:
> `AI_APICallError: Invalid 'input[3].id': 'msg-92Y7BhMpWBhXt7dm'.
Expected an ID that contains letters, numbers, underscores, or dashes,
but this value contained additional characters.` (`INCOMPLETE_STREAM`)
## Root cause
OpenAI's Responses API actually **rejects dashes** in `input[].id`. Its
400 message misleadingly lists dashes as allowed, but empirically only
`[A-Za-z0-9_]` is accepted:
| `input[].id` | result |
|---|---|
| *(omitted)* | ✅ 200 |
| `msg_92Y7BhMpWBhXt7dm` (underscore) | ✅ 200 |
| `msg-92Y7BhMpWBhXt7dm` (**the failing client id**) | ❌ 400 |
CopilotKit mints message ids like `msg-…`, and `@ag-ui/mastra` + the AI
SDK forward them straight into `input[].id` when replaying prior-turn
history — so turn 1 works (no prior ids) and every turn after dies.
## Fix
The mastra provider already routes every outbound LLM call through
`forwardingFetch` (the header-forwarding shim). This rewrites dashes
(and any other non-`[A-Za-z0-9_]` char) in each outbound `input[].id` to
`_` there.
**Why here, not in the bridge's message conversion:** it touches only
the bytes sent to OpenAI. Mastra's in-memory `CoreMessage.id` — which
drives its upsert-by-id history **dedup** — is untouched, so dedup is
unaffected. OpenAI-issued ids (`msg_…`, `rs_…`, no dashes) pass through
unchanged, preserving server-side conversation-state references. Chat
Completions bodies (no `input[]` array) are untouched.
This **supersedes ag-ui-protocol/ag-ui#2227** — a bridge-layer charset
munge that *kept* dashes (`[^A-Za-z0-9_-] → -`), making it a no-op on
the real failing ids. That PR is being reverted.
## Tests
`tests/vitest/header-forwarding-id-sanitize.test.ts` — 8 cases: the real
failing id, valid-id no-op, full-charset mapping, in-body rewrite,
no-op/passthrough, and chat-completions-untouched. All green.
## Verification status
- ✅ Transform verified against the exact failing id; `msg_…` form
confirmed accepted by the real OpenAI Responses API.
- ✅ 8 unit tests pass in-module.
- ⚠️ Full end-to-end wasn't run locally (the showcase runtime OOMs a 16
GB box), but **every** showcase OpenAI call flows through this wrapper,
so **staging is the final check** — deploy and re-run a two-click
multi-turn on `/demos/agentic-chat`.
## Refs
- Linear **OSS-381** (mastra refresh umbrella).
- Supersedes ag-ui-protocol/ag-ui#2227 (revert incoming).
- Follow-up worth filing upstream: `@ag-ui/mastra` / AI SDK shouldn't
forward non-provider message ids into `input[].id` at all.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
## What
Two mastra showcase D6 follow-ups to #5798 (v1 bridge alpha). Both cells
went red the moment #5798 took them out of `not_supported_features` —
they were claimed supported before actually passing. **Neither is a
v1-bridge streaming regression.**
## Commits
**1. gen-ui-agent completes all 3 steps (raise step cap)** — `57afed6dd`
"Generative UI: Agent State" (gen-ui-agent) stalled at 2/3 steps:
`genUiAgent` set no stop condition, so the AI SDK default halted the
agentic loop before the 3rd step completed. Adds
`defaultOptions.stopWhen = stepCountIs(12)`. Verified 6/6 on the Node-22
+ `next start` + aimock replay rig; tool-rendering / gen-ui-tool-based
unaffected.
**2. useComponent (gen-ui-tool-based) — probe took the wrong path** —
`4640d6304`
The D5 `gen-ui-custom` probe omitted `mastra` from `CHART_INTEGRATIONS`,
so it sent the *haiku* prompt and hunted for a haiku card. mastra's demo
is the LGP-style `useComponent` chart demo (`render_pie_chart` /
`render_bar_chart`) with no haiku tool, so the assistant bubble came
back empty (*"haiku card [data-testid=copilot-assistant-message]
rendered but has no text content"*).
- Add `"mastra"` to `CHART_INTEGRATIONS`.
- Add `aimock/d6/mastra/gen-ui-custom.json` (mirrors langgraph-python;
identical pie schema `{title, description, data:[{label,value}]}`) so
the cell is deterministic under replay instead of falling through to the
live upstream.
- Repoint the probe unit test's haiku-empty-card case from `"mastra"` →
`"agno"` (a genuine haiku integration).
## Verification
- gen-ui-agent: 6/6 on the faithful rig.
- useComponent: logic-only harness + fixture changes; harness unit tests
run in CI (sparse local checkout has no vitest).
## Refs
- Follow-on to #5798. Linear **OSS-381** (mastra refresh umbrella).
- Companion `@ag-ui/mastra` PR — multi-turn Responses-API message-id 400
fix: ag-ui-protocol/ag-ui#2227.
- Sibling from the same triage (separate, not fixed here): **PNI-100** —
hitl-in-app follow-up-run gap.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
- a2ui-recovery: add opt-in createA2UIRecoveryAgent() — generate_a2ui runs a
validate->retry loop and, once the attempt cap is hit with only invalid
surfaces, returns the { code: 'a2ui_recovery_exhausted', error, attempts }
envelope the A2UI middleware paints as the graceful failure card. Wired only
into the a2ui-recovery route; createDeclarativeGenUIAgent behavior unchanged.
D6 EXHAUST turn now green.
- multimodal: add opt-in createMultimodalAgent() that flattens PDF document
parts to text server-side via unpdf (TS equivalent of LGP's pypdf) through a
new opt-in preprocessMessages hook on createBuiltInAgent (default pass-through,
other demos byte-identical). D6 PDF turn now green.
- deps: add unpdf for server-side PDF text extraction.
Both fixes opt-in; shared factory defaults unchanged. next build + Docker
rebuild + D6 probes all green.
Diffs an integration's frontend surface (all src/** UI files except
src/agents/** and src/app/api/**, tests, qa) against a reference
integration (default langgraph-python) byte-for-byte, normalizing
integration identity (manifest name/slug) so name-only differences
report as IDENTITY rather than DRIFT. Exits 0 when the frontend is
byte-identical modulo the integration's own name. Supports --md
(markdown audit), --full, --all (fleet ranking), --verbose, --ref.
Complements the structural-only validate-parity.ts. Zero-dependency;
runs on node 23+ directly or via tsx.
- shared-state-read: remove spurious turnIndex:0 on the turn-2 fixture entry
(turnIndex counts assistant msgs = 1 on turn 2, so the constraint could never
match -> turn 2 dom-missing). Now D6 GREEN.
- a2ui-recovery: register built-in-agent heal/exhaust prompts in the shared
probe PROMPTS (new demo BIA lacked) + add its aimock fixture. HEAL turn now
GREEN; EXHAUST still red pending a backend factory change (emit the
a2ui_recovery_exhausted envelope) — tracked, not fixable at fixture layer.
- multimodal: fix conversation-runner skipSend baseline (snapshot run-start
BEFORE preFill, since preFill issues the run on skipSend turns; fast
in-process runtimes else false-red done-signal-missing). Image turn now
GREEN; PDF turn still red (BIA runtime has no document/PDF flattening path).
NOTE: conversation-runner.ts is a SHARED harness helper — change is guarded to
skipSend turns (non-skipSend byte-identical) and only corrects the baseline;
flagged for harness-owner review.
BIA's globals.css was a 17-line stub missing LGP's @theme inline Tailwind-v4
token map + the :root design-token palette (--background/--card/--primary/
--muted/--accent/--radius + CopilotKit brand vars). Without it every shadcn /
AI-Elements / prompt-kit primitive fell back to unstyled — most visible on
beautiful-chat. Copy LGP's globals.css verbatim so the byte-identical demo
frontends render with the correct theme.
Kills the "📣 Social Copy Generator" bot comment that lands on every PR.
The comment (e.g.
https://github.com/CopilotKit/CopilotKit/pull/6117#issuecomment-5053084113)
is posted by the `post-comment` job in
`.github/workflows/social_copy-generator.yml`, and the
checkbox-triggered `generate` job lives in the same file — the whole
feature was self-contained there, so deleting the one workflow removes
all of it.
After removal, `git grep -i "social copy"`, `git grep -i "social media
copies"`, and `git grep "copy-generator"` all come back empty — no
scripts, prompts, or docs referenced it anywhere else.
Multi-turn chat on every mastra demo fails on the 2nd turn:
AI_APICallError: Invalid 'input[3].id': 'msg-92Y7BhMpWBhXt7dm'.
Expected an ID that contains letters, numbers, underscores, or dashes,
but this value contained additional characters. (code: INCOMPLETE_STREAM)
Root cause: OpenAI's Responses API actually REJECTS dashes in `input[].id`
(its 400 message misleadingly lists dashes as allowed — empirically only
`[A-Za-z0-9_]` is accepted; `msg-92Y7…` 400s, `msg_92Y7…` succeeds).
CopilotKit mints message ids like `msg-…`, and @ag-ui/mastra + the AI SDK
forward them straight into `input[].id` when replaying prior-turn history, so
the whole request fails. Turn 1 works (no prior ids); every turn after dies.
Fix at the HTTP boundary: the mastra provider already routes every outbound
LLM call through `forwardingFetch` (header-forwarding shim). Rewrite dashes
(and any other non-`[A-Za-z0-9_]` char) in each outbound `input[].id` to `_`
there.
Why here and not in the @ag-ui/mastra message conversion: this touches ONLY
the bytes sent to OpenAI. Mastra's in-memory `CoreMessage.id` — which drives
its upsert-by-id history dedup — is left untouched, so dedup is unaffected.
OpenAI-issued ids (`msg_…`, `rs_…`) contain no dashes and pass through
unchanged, preserving server-side conversation-state references. Chat
Completions bodies (no `input[]` array) are untouched.
Supersedes the ineffective ag-ui-protocol/ag-ui#2227 (a bridge-layer charset
munge that kept dashes — a no-op on the real failing ids; being reverted).
Tests: tests/vitest/header-forwarding-id-sanitize.test.ts (8 cases — the real
failing id, valid-id no-op, full-charset mapping, body rewrite, no-op/passthrough,
chat-completions untouched). All green.
--no-verify: sparse showcase checkout has no monorepo lefthook/commitlint binaries.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
## What
Adds a **"Show unique"** filter to the Showcase Dashboard feature grid,
mirroring the existing **"Show deprecated"** toggle. A demo is
**common** when ≥ 2 frameworks ship it; single-framework (and
zero-framework) demos are **unique**.
Both toggles default **OFF**, so the default view is **common ∩
non-deprecated** — the cross-framework gold-standard surface. Each
toggle independently widens the set (AND-combined).
This makes room for framework-specific demos (e.g. the planned Mastra
browser-use / observational-memory demos): once added they'll be hidden
by default and revealed via "Show unique".
## Why the "ships a demo" signal
"Framework supports a demo" is defined as `integration.demos.some(d =>
d.id === feature.id)` (the grid's existing `isWired` signal). The two
alternatives were rejected:
- `integration.features[]` — stale in the data (e.g.
`interrupt-headless` has demos in ~19 integrations but 0 `features[]`
declarations).
- `not_supported_features` — a brand-new single-framework demo never
appears in another integration's `not_supported_features`, so it would
be wrongly classified as common. This is exactly the Mastra case that
motivated the feature.
## UI
- `Show unique (N)` checkbox next to `Show deprecated`, rendered only
when `N > 0`. Tooltip: "N demos supported by fewer than two frameworks —
hidden by default…".
- Subtitle shows the **exact distinct hidden-row count** — `(N hidden)`
— rather than an additive per-category breakdown (a feature can be both
deprecated and unique; the per-category badges provide attribution,
faceted-filter style).
## Testing
- 6 new behavioral tests in `feature-grid.test.tsx` (default-hidden,
reveal-on-toggle, count label, accurate tooltip wording, exact distinct
subtitle count, note-drop when both filters enabled). Suite: **37/37
green**.
- `tsc --noEmit` clean; `oxlint` clean (on the changed files); `next
build` succeeds.
## Notes / follow-up
- **Column-header tallies** count the full matrix regardless of
row-visibility filters. This is pre-existing (unchanged by this PR) and
arguably correct-by-design (a coverage metric over the whole matrix, per
the `computeColumnTally` docstring). Flagged in review, deferred.
- The "unique" count uses `frameworkCount < 2`, intentionally grouping
zero-demo features with single-framework ones (approved design
decision); tooltip wording reflects this.
## Scope
Client-side view state only — no registry, catalog, props, or SSE
changes; all edits internal to `FeatureGrid`.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Per-category subtitle counts overlapped (a feature can be both deprecated
and unique), overstating hidden rows. Show the distinct total instead;
per-category counts remain on the toggle badges. CR round 1 finding F2.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Tooltip said 'only one framework' but uniqueCount is frameworkCount<2,
which includes zero-framework demos. CR round 1 finding F3.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Hides single-framework (non-common) demo rows by default, mirroring the
Show deprecated toggle. Common = shipped by >=2 frameworks (demos[]).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
## Summary
Introduces Rich Threads as the documentation front door for persistent,
resumable agent conversations and guides developers from setup through
UI choice, user scoping, production deployment, and history
synchronization.
## What changed
### Rich Threads overview
- Presents the approved Support Desk screenshot and light/dark
user-journey diagrams.
- Moves cloud-hosted Enterprise Intelligence setup near the top with
both a coding-agent prompt and direct CLI steps.
- Defines Rich Threads around durable AG-UI event history, including
messages, generative UI, multimodal inputs, tool activity, state, and
live-run continuity.
- Explains Threads Drawer versus Headless Threads and links to the
appropriate implementation guide.
- Describes production self-hosting with a direct CopilotKit Engineering
contact path.
- Adds an end-user scoping FAQ linked to detailed `identifyUser`
guidance.
### Implementation and lifecycle
- Documents Threads Drawer for both CLI-created starters and existing
CopilotKit applications.
- Keeps Headless Threads as the custom-UI path and adds user-scoping and
production self-hosting guidance.
- Adds the server-side `identifyUser` contract, separating application
identity from the project Runtime API key.
- Keeps Thread & History Lifecycle and Threads & Persistence
Architecture in the Rich Threads navigation group.
### History synchronization
- Renames the generic guide to **Import & Synchronize Thread History**
and the navigation label to **Synchronize Thread History**.
- Provides dedicated **Synchronize ADK Threads** and **Synchronize
LangGraph Threads** guides.
- Documents one-time historical import followed by future
CopilotKit-mediated persistence.
- Explains that native ADK or LangGraph persistence and analytics can
remain in place when the durable native mechanism stays connected.
- Corrects the importer destination contract: dry runs need no
destination credentials; real imports read flags or exported process
environment values.
### Framework coverage
- Applies shared Rich Threads navigation and content across root,
authored, generated, built-in, and framework-specific routes.
- Keeps existing URLs and implementation identifiers unchanged; no
redirects are required.
- Uses shared sources rather than hand-editing generated framework data.
### Measurement
- Adds conversion events for the coding-agent prompt, CLI setup command,
self-hosting contact, Drawer customization, and history synchronization.
## Validation
- [x] Formatting for all files changed by this PR
- [x] Lint (existing repository warnings only)
- [x] Typecheck
- [x] Tests (33 files, 180 tests)
- [x] Production build
- [x] Desktop/mobile and light/dark browser review across representative
root, authored, generated, built-in, ADK, and LangGraph routes
Two issues found in review after `examples/integrations/adk-angular`
merged (#6097).
## 1. Closed chat stayed keyboard-accessible off-screen
The collapsible chat panel is only translated off-screen (`transform:
translateX(100%)`), so its `copilot-chat` inputs/buttons remained in the
tab order and the accessibility tree while "closed."
**Fix:** mark the `<aside>` `inert` while closed
(`[attr.inert]="chatOpen() ? null : ''"`); removed when open.
## 2. Dev inspector shipped in the production bundle
The `cpk-web-inspector` dev aid (and its `@copilotkit/web-inspector`
dependency, ~660 kB) was statically imported, so it landed in the **4.59
MB** production initial bundle.
**Fix:** gate it behind `@defer (when isDev)` (`isDev = isDevMode()`),
splitting it into a lazy chunk that a production build (`isDev` = false)
never loads.
## Testing (live)
- **Prod build** (`ng build`): initial bundle **4.59 MB → 3.93 MB**;
`@copilotkit/web-inspector` is now a separate lazy chunk (660 kB) that
prod never loads.
- **Dev serve**: the inspector still mounts (`@defer` triggers when
`isDev`).
- **a11y**: with the chat closed, focusing a control inside the panel is
blocked (`document.activeElement` falls back to `body`); open panel
unaffected; the toggle FAB still reopens it.
- `oxlint` 0/0.
Follow-up to OSS-561.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Two issues found after the example merged:
1. The closed chat panel is only translated off-screen, so its inputs/buttons
stayed in the tab order and the a11y tree. Mark the <aside> `inert` while
closed (`[attr.inert]`), so focus/AT skip it; removed when open.
2. The dev web inspector (and its @copilotkit/web-inspector dep, ~660 kB) shipped
in the production initial bundle. Gate it behind `@defer (when isDev)` so it's
split into a lazy chunk that a prod build (isDev=false) never loads.
Verified: prod `ng build` initial bundle 4.59 MB -> 3.93 MB with web-inspector now
a lazy chunk; dev serve still mounts the inspector; closed-panel focus is blocked
(activeElement falls back to body), open panel unaffected.
## What & why
Adds the first **Angular** scaffoldable integration example:
`examples/integrations/adk-angular/` — an Angular 21 SPA wired to a
Google ADK agent over AG-UI, a peer to the React
`examples/integrations/adk`. Angular support is selective (ADK first),
so this surfaces as a new **"Angular + ADK"** entry in `copilotkit init`
(CLI wiring is a companion PR in the Intelligence repo).
## Architecture — 3 processes
Angular is a SPA, so (unlike the Next.js React example, which hosts the
runtime in an API route) the runtime lives in a standalone Node server —
the documented `@copilotkit/angular` pattern.
| Process | Port | Source |
| --- | --- | --- |
| Angular app (`ng serve`) | 4200 | `src/` |
| Copilot Runtime (`tsx server.ts`) | 8200 | `server.ts`
(`createCopilotNodeListener`) |
| Python ADK agent (`uv`) | 8000 | `agent/` — copied from
`examples/integrations/adk` |
One `npm run dev` runs all three via `concurrently`.
## Feature parity with the React ADK example
- Shared agent state (proverbs) via `injectAgentStore` +
`agent.setState`
- Generative UI (weather card) via `renderToolCalls`
- Frontend tool (`setThemeColor`) via `registerFrontendTool`
- Static suggestions (the same 5)
- Threads drawer + env-gated managed Intelligence
(`CopilotKitIntelligence` when `COPILOTKIT_LICENSE_TOKEN` is set, else
`InMemoryAgentRunner` — matching the React `route.ts` gating)
- Dev web inspector (`cpk-web-inspector`), matching the richer React
examples
### Two behaviors that required real fixes (found via live testing, not
static review)
1. **Frontend tools now reach the ADK agent.** `setThemeColor` silently
failed because the ADK agent's tools were static and `ag_ui_adk` only
forwards client tools when the agent includes an `AGUIToolset()`
placeholder. Added it (this affected the React `adk` example identically
— fixed there in a companion PR).
2. **The weather generative-UI card now renders.** A `renderToolCalls`
entry scoped with `agentId` filtered the server-side tool call out;
removed it.
## Chat UI — floating, React-`CopilotSidebar`-style
Angular has no `CopilotSidebar`, so the chat is a hand-rolled
collapsible panel that mirrors React's behavior:
- **Docks + pushes** the content when there's room (viewport ≥ 1200px:
starts expanded, content reflows beside the chat via a right margin),
and **overlays** on narrower screens so the content isn't smushed by the
threads drawer's push.
- Toggle/close match React's `CopilotChatToggleButton` /
`CopilotModalHeader`: lucide `MessageCircle` FAB (bottom-right) to open;
lucide `X` in the panel header to close; no bottom-right "X" (the open
panel covers the FAB, exactly like React).
- Layout uses a global `box-sizing: border-box` reset (React/Next get
this from Tailwind's preflight) so cards don't clip on small screens.
## Dependency
Requires **`@copilotkit/angular@0.2.0`** (published; it carries the
threads drawer + `provideCopilotChatConfiguration`).
`runtime`/`core`/`shared` pinned to `1.63.1` — matches
`@copilotkit/angular@0.2.0`'s own deps (verified: no duplicate
`@copilotkit/core`).
## Testing
`ng build` green; `oxlint` 0/0; a 4-round 7-agent CR loop converged to
zero findings.
Verified **live against the hosted Intelligence platform + a real Gemini
key**:
- **Managed Intelligence connects:** `/api/copilotkit/info` → `mode:
intelligence`, `licenseStatus: valid`, full `threadEndpoints`
(list/inspect/mutations/realtimeMetadata), realtime `wsUrl`.
- **Threads render:** the drawer loads the org's persisted threads with
pagination.
- **Shared state:** proverbs seed on load; add / update / read via chat
all round-trip and update the card.
- **Frontend tool + generative UI:** "set the theme to teal, then get
the weather in Paris" recolors the panel **and** renders a teal-themed
weather card in the chat.
- **Responsive:** dock-and-push at ≥1200px (content beside the chat, 0
overflow); overlay + starts-closed below; no clipping at 580 / 1050 /
1200 / 1400.
Not exercised: nothing outstanding — the previously-untested agent/tool
paths are now confirmed live. (`GOOGLE_API_KEY` is required for live
agent runs; the scaffold + build don't need it.)
## Follow-ups (not in this PR)
- Companion: **CopilotKit/Intelligence** CLI PR adds the `adk-angular`
framework; **CopilotKit/CopilotKit#6107** ports the `AGUIToolset` fix to
the React `adk` example.
- Inherited-from-React demo-quality items (fail-loud on missing
`INTELLIGENCE_API_KEY`, the `.sh || .bat` / `dev:debug` Windows /
`postinstall`-uv script patterns, the agent's broad `except` / dead
`ProverbsState` / prompt typos) — cross-example cleanup.
- Docs: the ADK quickstart/cookbook should note `AGUIToolset()` is
required for frontend tools.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
When the viewport is wide enough (>=1200px) the chat starts expanded and DOCKS:
.layout--pushed adds a right margin equal to the chat width so the proverbs
content reflows beside the chat instead of being covered (mirrors React's
CopilotSidebar margin-inline-end push). Below the breakpoint the chat starts
closed and OVERLAYS on open, so narrow screens aren't smushed.
- DOCK_BREAKPOINT_PX (1200) gates the initial open state; a matching
@media (min-width:1200px) rule applies the push margin
- --chat-width var keeps the panel width and push margin in sync
Verified live: 1400px starts expanded, content pushed beside the chat (right
929 <= chat left 960), 0 overflow; 1000px starts closed, opening overlays with
no push and no overflow.
Both were suspected downstream-host RED; per-demo probes against a context-scoped
aimock confirm GREEN. declarative-gen-ui: cross-slug shadowing was the sole cause
(a2ui-fixed-schema passes on the same host). mcp-apps: fixed via the create_view
elements JSON-string fixture correction. Update manifest note + PARITY_NOTES to
the resolved state.
Excalidraw's MCP create_view tool declares `elements` as a string (JSON-encoded
array) in its inputSchema; the fixtures emitted a raw JSON array. BIA declares
the injected MCP tool locally via jsonSchemaToZod -> z.string(), so the array
failed input validation, the tool never executed against excalidraw, no
ACTIVITY_SNAPSHOT fired, and the MCP Apps iframe never mounted (D6 red).
Stringify the elements arg to match the inputSchema. Verified D6 green.
Same latent fix applied to the flowchart pill in mcp-apps.json.
Previously the FAB swapped to an X when open and sat above the panel, so an open
chat showed TWO X's (header + bottom-right). React never does that: its toggle
FAB is always a MessageCircle, and the sidebar (z-1200) covers the FAB (z-1100)
when open, so the only visible close is the header X.
- FAB icon is always MessageCircle (no X swap)
- chat panel z-index 1200 > FAB 1100, so an open panel covers the FAB
Verified live: OPEN shows only the top-right header X (FAB covered); CLOSED shows
the bottom-right MessageCircle FAB to reopen. No bottom-right X in either state.
Nathan 🔶 Tarbert