mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
GeneralJerel
1dc6eee3fc
Teach-mode UX (staged on the no-op recorder shim, ready for the live hook): - Suggested-prompt pill leads the welcome screen — "Approve the $5,000 Marketing transaction" — a one-click path straight into the over-policy-limit gate (seed t-1: Google Ads -$5,000, Marketing limit $5,000 / spent $500). The same pill drives both halves of the arc: fails pre-learning, succeeds post-learning. - Pulsating violet recording vignette frames the canvas while the officer is teaching. Ref-counted around every `recordUserAction` call so it stays continuous across opened+finalized; minimum 1.2s visible duration; non-blocking; static fallback under prefers-reduced-motion. Mounted at z-1300 to read clearly even over the docked chat panel. - Inline policy-exception card replaces the popup modal: the officer's whole demonstration (see symptom → file exception → record) now happens in the chat as a single HITL card, with identical REST callers and identical `policy_exception.opened`→`finalized` recording payloads to the old modal. CK v2 provider fix: - Swap the v1 `CopilotKit` compatibility bridge for the v2-native `CopilotKitProvider`. The bridge wraps the chat in a heavier stack (ThreadsProvider + a second CopilotChatConfigurationProvider + listeners); that churn re-fires CopilotChat's /connect effect cleanup mid-run, and the cleanup calls AG-UI `detachActiveRun()` — which silently tears down the in-flight run the instant the agent emits a frontend HITL tool call. Symptom was a clean run with no error but no HITL render. With CopilotKitProvider the `/connect` storm and ERR_ABORTED are gone and runs complete cleanly. The inbox keeps working because v2 `useThreads` reads CopilotKitProvider's own context. - `reactStrictMode: false` in next.config to remove the dev double-mount that aggravates the same teardown class. Production unaffected. Other: - Switch model to `openai/gpt-5.4-mini-2026-03-17` (verified reachable; same tool-calling surface). - Add `selectCard` HITL tool + visual `CardPicker` (in-chat brand+last4 picker) so card-targeted flows (PIN, policy assign) get a visual picker instead of a text list. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
16 lines
831 B
JavaScript
16 lines
831 B
JavaScript
/** @type {import('next').NextConfig} */
|
|
const nextConfig = {
|
|
// React StrictMode intentionally double-invokes mount effects in DEV ONLY.
|
|
// For CopilotKit's AG-UI human-in-the-loop flow that double-mount tears the
|
|
// in-flight run down the instant the agent emits a HITL tool call — before
|
|
// the approval card can render and return its result — which orphans the tool
|
|
// call ("Tool result is missing for tool call …") and then poisons the thread
|
|
// so every later message fails. Production builds never double-invoke, so the
|
|
// bug is purely a `next dev` artifact; disabling StrictMode makes the live
|
|
// HITL chat (and the teach-mode demonstration arc) work when the demo is run
|
|
// via `next dev`. No effect on production behavior or correctness.
|
|
reactStrictMode: false,
|
|
};
|
|
|
|
export default nextConfig;
|