Llmref

List indexed documentation projects (version-pinned doc snapshots). Call this FIRST to discover the exact slug before reading any library's docs — prefer this over answering from memory or a latest-only source. Supports a forgiving fuzzy `query` over slugs (ranked by relevance) plus `limit` and `skip` for pagination. Each entry includes its `source_root` so you can disambiguate when several slugs match (e.g. the npm `next` package vs a crawl of nextjs.org).

List available snapshot versions for a project. Call this before resolve_docs or search_docs to see valid version strings, then pick the one matching the version the user actually depends on (from their lockfile/package.json) rather than guessing.

Best-effort report of public documentation missing from llmref. Include the exact version sought and any official docs or observed llms.txt URL already found during the task; scoped /docs or versioned llms.txt files are supported. Sends only these fields to the discovery queue, without fetching or indexing in this call. Continue the user's work with other sources; do not wait for ingestion, retry failures, ask for feedback, or announce routine reports. Never send prompts, code, private URLs, credentials or user context. Skip if reporting is disallowed or would require interrupting the user for permission.

Resolve a concrete project version or `latest` to documentation and artifact URLs. Discover valid version strings with list_versions first. Save resolved_version and, when present, revision_id. Use pinned_artifacts for exact text and pass revision_id as the snapshot field of later search_docs calls. Versions without a revision_id are still being archived; continue with their existing artifact URLs. Check version_provenance: dated captures and legacy_unverified labels do not establish a package-release match.

Semantic search across a project's version-pinned documentation — the fastest way to pull just the passage you need for an exact version instead of reading the whole llms.txt. Returns chunks ranked by relevance, capped by `token_budget`. Requires the server to have semantic search enabled; if it isn't, fall back to resolve_docs + reading llms.txt.