Source Intelligence

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

All of v2.1.193 Home All releases olderv2.1.191 v2.1.195newer
Claude Code v2.1.193

Trust Dialog Enforcement for Settings Permissions

What

Permission allow-rules and additional directory grants from .claude/settings.json and .claude/settings.local.json are now silently ignored when the workspace has not yet been trusted via the interactive trust dialog.

Details
  • Logs to stderr: "Ignoring N permissions.allow entries from .claude/settings.json: this workspace has not been trusted. Run Claude Code interactively here once and accept the trust dialog, or set projects[\"...\"].hasTrustDialogAccepted: true in ~/.claude/settings.json."
  • Only applies before the trust dialog has been accepted for this workspace; once trusted, all settings are applied normally.
  • Managed (policy-level) settings are still honored regardless of trust state.
Evidence

New enforcement logic (search for "this workspace has not been trusted. Run Claude Code interactively here once")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

See this entry in the whole of v2.1.193 →