Accept a strict split between disjoint CompositeProvider routing and an overlapping deep-provider registry with deterministic request, CLI, and environment selection.
Specify target binding, no-fallback lifecycle semantics, adapter-owned open options, canonical analysis profile commitments, snapshot v2 migration, and backward-compatible Evidence v2 provenance.
Document target-free candidate diagnostics, compatibility projections, rejected alternatives, and required behavior scenarios that the provider foundation and Ghidra PRs must satisfy.
Derive package, tool-family, provider, setup-client, schema-version, and CLI facts from the runtime contract sources into a deterministic checked-in catalog.
Add non-mutating generated-file checks, exact TypeDoc regenerate-and-compare validation, caller-visible documentation fact checks, and CI enforcement through docs:check.
Cover command-router parity, source-derived catalog values, deliberate documentation drift, and stale generated artifacts while preserving runtime behavior.
Align the documented tool inventory, setup client matrix, supported hosts, installation behavior, and roadmap with the 1.6.0 implementation.
Record Ghidra as the accepted next read-only provider direction without claiming shipped support, and refresh the provider admission criteria around evidence fidelity and local diagnostics.
Regenerate the committed TypeDoc site from current sources so package metadata and Process Capture v4 contracts replace the stale 1.1.0/v3 output. Add localized README coverage for every detected setup client.