Syncs the branch with main (304 commits) to resolve CI type-check failure.
main changed extractForwardableHeaders to require a forwarding policy and
added the mergeForwardableHeaders helper (#5712); handle-suggest now uses
mergeForwardableHeaders(agent.headers, request, runtime.forwardHeadersPolicy ??
resolveForwardHeadersPolicy(undefined)) to match the run handler — fixing the
drift and adopting the server-headers-win / infra-header denylist behavior.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Rework the stateless /suggest transport to reuse the AG-UI SSE pipeline
instead of a buffered JSON response, resolving the streaming + state review
feedback:
- server runs the provider agent directly and streams its events via
createSseEventResponse (the runner's event pipeline minus GLOBAL_STORE
persistence), gated with captureTelemetry:false so suggestions stay out of
run telemetry
- client drives a stock HttpAgent against /agent/:id/suggest, so chips stream
progressively via onMessagesChanged and the run never routes through the
Intelligence websocket delegate (still no thread persistence)
- forward the consumer's deep-cloned messages + state onto the suggestion run
(was state: {}), matching the clone fallback
Net -68 LOC of production code; the stateless and fallback paths now share one
runAgent flow.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Addresses PR #5823 review (MikeRyanDev + marthakelly):
- core/threads.ts: a full-list refetch (filter-change / retry) now clears
fetchMoreError on both listRequested and listSucceeded, so the inline
'couldn't load more - retry' banner no longer survives onto a fresh list.
- web-components: Escape while the confirm-delete <dialog> is open is now
consumed by a confirm guard in the host keydown handler; previously the
bubbled keydown fell through to the mobile branch and closed the whole drawer
along with the confirmation.
- web-components: an open kebab popover now shields the rest of the list -
.list.menu-open .row:not(.menu-open) gets pointer-events:none so other rows
no longer reveal their kebab or paint a host ::part(row):hover background
around/behind the menu. Click-away dismissal is preserved via the existing
document pointerdown handler.
- README: drop the removed --cpk-drawer-rail-width from the documented tokens.
Tests: core clears-fetchMoreError-on-refetch; web-components Escape-while-
confirming, confirm-dialog backdrop-click, menu-open row shield; Angular
scoped-chat-input focus (ancestor copilot-chat-view over the global fallback).
Menu-shield verified live in the langgraph-js example (:3002).
D2 — wire fetchMoreError end-to-end:
- core: add a dedicated `fetchMoreError` channel to the thread store, tracked
separately from the initial-list `error`. `nextPageFailed` now writes
`fetchMoreError` (was `error`), so a paginated-load failure preserves the
loaded list and drives the element's inline "couldn't load more — retry"
panel instead of a full-panel error. Cleared on fetch-more request (retry),
on success, and reset on context change / stop. New symbols:
* `ThreadState.fetchMoreError`
* `ThreadSelectors.fetchMoreError` + `ɵselectFetchMoreError`
Call sites of `ɵselectFetchMoreError`:
* packages/core/src/threads.ts (export)
* packages/react-core/src/v2/hooks/use-threads.tsx (selector read)
* packages/vue/src/v2/hooks/use-threads.ts (bindThreadStoreSelector)
* packages/angular/src/lib/threads.ts (bridge to signal)
* packages/vue/src/v2/hooks/__tests__/use-threads.test.ts (core mock)
Call sites of `ThreadSelectors.fetchMoreError` (mock objects updated):
* packages/core/src/__tests__/core-thread-store-auto-unregister.test.ts
* packages/core/src/__tests__/thread-store-registry.test.ts
- react/vue/angular: expose `fetchMoreError` on the hook/composable/store and
push it onto `el.fetchMoreError`, making the dead `retry{scope:"fetch-more"}`
handler reachable. Initial-list error behavior unchanged.
D1 — Angular wrapper open-state coordination: drive `el.open` from the config's
`drawerOpen` (default CLOSED) so the element no longer springs open full-screen
and scroll-locks on mobile load; handle `(open-change)` -> `config.setDrawerOpen`
with a provider-less local-state fallback; call `config.registerDrawer()` with
cleanup on destroy. The config's drawer members were fully functional (only
marked "RESERVED/unwired") — wiring them makes them consumed, so their comments
were updated accordingly (no reservation conflict).
D3 — Angular focus-return: add a `findChatInput` scoped to the Angular chat
selectors (`copilot-chat-view` container, `textarea[copilotChatTextarea]`) and
focus it on thread select, mirroring React/Vue.
A6 — react wrapper comment rot: "nine outbound events" -> "eleven" (2 spots).
DEFAULT_AGENT_ID parity (react): import `DEFAULT_AGENT_ID` from
`@copilotkit/shared` instead of hardcoding `"default"` (equal value).
Angular test isolation: three list-path tests now set `licenseStatusSignal`
explicitly instead of relying on inherited module-level state.
Tests: core 552, react-core 1417, vue 1068, angular 176 — all pass;
check-types passes for all four packages.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Resolve the single conflict in packages/web-inspector/src/index.ts by keeping
both additions: this branch's CpkMemoryList memory-tab element and main's
ɵCpkThreadDetails back-compat alias (independent top-level declarations).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The inspector subscribed to AG-UI events only through onAgentsChanged, which
skips per-thread clones, leaving the event timeline empty during runs
(regression of #3872). Subscribe to the run instance reported by
onAgentRunStarted so its events are recorded.
Add an onAgentRunStarted subscriber event fired from RunHandler.runAgent and
connectAgent with the instance that actually runs. Per-thread clones (from
useAgent) are not in the agent registry, so onAgentsChanged never fires for
them and subscribers that only track registry agents can't observe their run.
Final naming decision. Renames the public component + element across the
board: React/Angular CopilotDrawer -> CopilotThreadsDrawer, the Lit element
copilotkit-drawer -> copilotkit-threads-drawer (tag, CopilotKitThreadsDrawer
class, COPILOTKIT_THREADS_DRAWER_TAG, defineCopilotKitThreadsDrawer), the
@copilotkit/web-components/drawer subpath -> /threads-drawer (+ src dir),
the CopilotThreadsDrawerRow directive / copilotThreadsDrawerRow input, and
all prose/test references. Generic types (DrawerThread, DrawerFilter),
--cpk-drawer-* tokens, and ::part names are unchanged. Behavior unchanged.
Three snapshot tests (lines 751/771/789) call test() while the file uses
explicit vitest named imports. They pass at runtime via vitest's global
but fail tsc check-types (TS2593). Add test to the import.
Memory, NewMemory, MemoryChanges, MemoryKind, and MemoryScope are the
memory types surfaced by the useMemories / injectMemories hook result
shapes, so export them unprefixed as supported public API instead of
behind the ɵ "internal" marker. Internal memory plumbing (MemoryStore,
the selectMemories* selectors, state/context/event types,
createMemoryStore) keeps the ɵ prefix.
Updates the react-core and angular hook signatures, the web-inspector
Memories tab, and the affected tests to the unprefixed names.
Add three flat test cases verifying the silent-degrade contract:
404/501 list response sets available:false with no error; 500 response
sets error and keeps available:true; 404 subscribe response is silent
with no console.warn emitted.
Adds listUnavailable and credentialsUnavailable to memoryRestEvents, adds
available: boolean to MemoryState (defaulting to true), resets available to
true on contextChanged and listRequested, and handles listUnavailable by
clearing memories and setting available: false with a session guard.
The memory store's socket effect created the `user_meta:memories:<code>`
channel and observed its events, but never subscribed the join-outcome
stream — and `ɵphoenixChannel$` only calls `channel.join()` when that stream
is subscribed. So the socket connected but no `phx_join` was ever sent: the
gateway saw the connection, the channel was never joined, and saved memories
never pushed to the client (REST snapshot worked; live deltas silently never
arrived). The thread store joins because its merged `joinOutcome$` subscribes
the stream.
Merge `ɵjoinPhoenixChannel$(channel$)` into the socket effect's output so the
join actually fires; swallow a failed/timed-out join so a transient rejection
doesn't tear down the metadata stream (Phoenix re-attempts on reconnect). Add
a `joinCount` spy to MockChannel and assert the realtime test actually joins —
this regression passed before because the mock delivered events without a join.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The @copilotkit/core build (tsdown with dts generation) has a working set
of about 3.45GB. Node's default old-space ceiling is roughly 4GB and CI pins
NODE_OPTIONS to 4096, leaving almost no headroom. Under nx run-many the build
competes for CPU with sibling builds, GC falls behind, and the process tips
over the heap limit. nx flags it as a flaky task and pre-commit/CI builds fail
intermittently with a V8 heap OOM.
Bake the ceiling into the core build script with cross-env so every invocation
path gets consistent headroom: local lefthook hooks, nx run-many, CI, and
direct pnpm build, on every platform including Windows. 8192 matches the value
already used by the e2e workflow and gives roughly 2x headroom over the working
set.
Scoped to core only; it is the single package that OOMs.
tylerslaton