Follow Discord
Sweep 10 Nov 2026 · 02:18Z Build v2.1.322 539 read Stable v2.1.311 Latest v2.1.322 Next v2.1.322 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.268 ·

Tool permission prompts can show a structured explanation card

Permission-ask dialogs can now show a structured 'card' explaining the decision, and addon tools can supply one.

Group of 2 You'll notice No documentation found Internal Changes
JSON All of v2.1.268
You'll noticeTier: how much it should matter to you
3Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
ElsewhereArea: what it touches
Internal ChangesKind: in v2.1.268,
ImprovementsSection of the release

Unclear What permissionCard controls and what the wrapping helper (B_t) actually does are not specified in the finding.

What

  • Tool-permission prompt info can now include an optional structured card (with a question, lines, and values) shown when the permission decision reason is a safety check or similar, there's no matched ask-rule, and no denial-limit fallback applies. The card content comes from the tool's own permissionCard callback.
  • The generic addon-tool factory now includes a permissionCard property in the tool definition it builds, and wraps the finished tool object with a helper before returning it, so addon tools can supply this card.

Why This gives you a clearer, structured explanation (instead of plain text) when Claude Code asks permission to run a tool for safety reasons, and extends that capability to addon tools.

Read from
Names in the bundlepermissionCard
How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtWhat permissionCard controls and what the wrapping helper (B_t) actually does are not specified in the finding.

See this entry in the whole of v2.1.268 →

Feedback