Without /D, "$" also matches before a trailing "\n", so "custom_meta_telefon\n",
a color setting "5\n" (stored as sent) or a whole reference followed by "\n"
passed VariableRef. Added /D to every ^...$ pattern that validates client or
admin input:
- VariableRef META_KEY, NUMBER, WHOLE (canonical/typeOf; Placeholders::field
shares META_KEY)
- Cursor::decode, GuideRepository topic names (MCP input and filter keys)
- ExposurePolicy::sanitize ability keys and group ids, LogTab list filters
Not changed: Placeholders::PATTERN (runs on trim()), Warnings hex checks (hints
only), NodeSummary/AttrPathIndex/LogListTable (stored or Divi data, no client
input). Each fixed pattern has a test with a trailing "\n" that is rejected.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01At3V6SjwbMe6eMzVGW3Hs7
Tools tab shows one block per integration with a group mode (inherited by its
tools) and a read-only switch that disables all non-readonly abilities of the
group. ExposurePolicy resolves tool override > group override > tool default;
lit/guide keeps its default, direct-only tools fall back to direct under a
group "indirekt". Group entries live in lit_mcp_exposure under "@group:<id>"
and "@readonly:<id>"; the old flat format stays valid. The ability->group map
comes lazily from IntegrationRegistry (Divi is not loaded at plugins_loaded).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Introduces ExposurePolicy (option lit_mcp_exposure) deciding per ability
whether it is a direct MCP tool, only reachable via mcp-adapter's
execute-ability meta-tool, or disabled entirely (not registered with the
Abilities API at all). Ability::isDirect() remains the default when no
override applies. lit/guide can never be disabled or made indirect;
lit/media-preview and lit/media-download (image/embedded-resource results)
can never be made indirect, only direct or disabled.
AbilityRegistrar and ServerRegistrar take an optional ExposurePolicy and
use it to filter registered abilities / compute the direct tool list.
IntegrationRegistry::directAbilityNames() is removed (superseded by
ExposurePolicy::directNames()). InstructionsBuilder now also takes the
policy and lists the currently direct tools by name (lit-<name>), noting
the rest are reachable via mcp-adapter-execute-ability as lit/<name>.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01At3V6SjwbMe6eMzVGW3Hs7
janniclas.loosenandClaude Opus 5.5