Hide internal chat tool messages

[nttylock]

Summary

• filter internal reasoning/tool/MCP messages out of customer chat history
• hide live operate-card rows on chat pages as a short-term guard

Scope

• public-safe sync from private nttylock/AdClaw PR chore(deps): bump react and @types/react in /console #36
• intentionally excludes website-landing/assets/home-hero-video.mp4

Validation

• git diff --check
• changed files limited to console/src/pages/Chat/sessionApi/index.ts and console/src/styles/layout.css
• synced files match private origin/main for these two paths

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: e4f0ee5590

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Keep approval cards visible on chat pages

This selector hides every adclaw-operate-card, not just reasoning/tool trace rows, so approval UIs are also suppressed; when an MCP/tool flow emits an approval request card, users cannot see or act on it and the run can stall waiting for input. This affects any environment where approval-gated tool execution is enabled.

Useful? React with 👍 / 👎.

[chatgpt-codex-connector]

Filter all internal runtime event message types

The internal-type filter is incomplete: it excludes some tool/runtime events but leaves other non-chat event types unfiltered, so shouldRenderOutputMessage can still surface internal execution traffic in history when those message types appear. To match the stated behavior, expand this set (or switch to an explicit allowlist of user-visible message types).

Useful? React with 👍 / 👎.