xberg

Alef-managed generated bindings in packages/* and binding crates — the regeneration workflow (task alef:generate / alef:verify), the alef.toml section layout, the core-side edits that break a regen, and the FFI bridge's JSON marshalling requirement. Load before editing anything under packages/* or a binding crate, before adding a trait method or extractor, or when regenerating or verifying Alef output.

REST API server and MCP protocol integration

Use when extracting from many files at once with shared config, bounded parallelism, per-file overrides, and error recovery. Covers the `batch` command, `--file-configs`, `--max-concurrent`, and output layout.

Run, diagnose, or change Xberg extraction benchmarks, quality scoring, benchmark fixtures, artifact contracts, and independently sourced ground truth. Load for the Benchmarks workflow or benchmark-harness work, not ordinary unit tests.

Use when splitting extracted text into chunks for LLM context windows or RAG ingestion. Covers chunk size, overlap, markdown/yaml/semantic chunkers, tokenizer-based sizing, and the standalone `chunk` command.

Chunking, embeddings, and RAG pipeline integration

How Xberg resolves configuration — CLI-mode and server/MCP-mode precedence orders, config file auto-discovery (xberg.toml walk-up, then the user config dir), field-level inline JSON merge (merge_json_into_config), the ExtractionOverrides CLI layer, and the two mechanisms that make a config change silently do nothing. Load when adding a config flag or env var, changing config precedence, or debugging why a setting is or isn't taking effect.

The Xberg workspace layout — the version source of truth (root Cargo.toml [workspace.package] version), the 19 workspace members and 3 excluded crates, the distribution packages under packages/, the tools/ directory, and the ignore-file allowlists a new workspace member must be added to. Load when navigating the repo, deciding where code belongs, or wiring a new crate or binding package.

Use when extracting keywords (YAKE/RAKE) from documents — and, secondarily, when detecting document language or generating embeddings for RAG and search. Covers the keyword config (and its feature gating), `--detect-language`, and the standalone `embed` command with real flags.

Change or diagnose Xberg's core extraction orchestration, cache semantics, extractor fallback, post-processing, concurrency defaults, or format-wide quality invariants. Load for pipeline work, not a single parser's syntax.

Cargo feature flags for crates/xberg — ORT-incompatible targets (WASM, Android x86_64 emulator), type-only and tract inference companion features, WASM/Android-safe variants, PDF backend, mutually-exclusive ORT variants, platform-conditional deps, aggregate feature sets, and build profiles. Load when adding, wiring, or debugging a Cargo feature, or when reasoning about what compiles on WASM/Android/Windows/macOS-intel targets.

Format-specific document extraction workflows

MIME type detection and extractor routing in core/mime.rs — the FORMATS registry that EXT_TO_MIME and SUPPORTED_MIME_TYPES are derived from, the path-based and bytes-based detection functions, priority-based registry selection, wildcard MIME families, and the real procedure for adding a format. Load when adding a format, wiring an extractor to a MIME type, or debugging why a file routes to the wrong (or no) extractor.

Change or evaluate Xberg OCR backends, preprocessing, caching, page acceptance, geometry, hOCR structure, table reconstruction, or cross-backend quality. Load for OCR behavior and A/B quality work, not ordinary PDF text extraction.

Change or diagnose Xberg PDF extraction, native/Pdfium backend selection, PDF rendering sessions, encrypted documents, OCR fallback, or backend-specific capability gaps. Load for PDF engine work, not generic image OCR.

Design, implement, or diagnose Xberg plugin traits, typed registries, priority collisions, lifecycle, native extractors, and Alef-generated Python plugin bridges. Load for plugin-system work, not ordinary extractor parsing.

Decide which xberg-io repository owns a cross-repository fix or API, and coordinate compatible changes across Xberg, Alef, enterprise, crawler, LLM, and OCR repositories. Load when work spans sibling repos; do not use for a self-contained Xberg edit.

Audit Xberg before a push or release by reconciling CI, Publish Release dry-run, Benchmarks, generated freshness, changelog, and remote branch state. Load for release-readiness work, not routine local commits.

How xberg versions are synced and released — Cargo.toml is the single source of truth, `task version:sync` propagates it to alef-managed binding manifests AND the integrations under integrations/, which are versioned and published in lockstep with core (including -rc.N). Load before bumping a version, editing the version-sync task, or touching an integration's version/xberg dependency.

The test_documents submodule is a bucket-fetched fixture corpus that is not committed. This skill covers read_test_fixture, missing fixtures, valid A/B controls, and submodule push order. Load before running Rust tests on a fresh clone, setting up an A/B control, adding a fixture-backed test, or diagnosing missing-fixture failures.

WASM build constraints for the crates/xberg-wasm crate — the wasm-target feature set, no-tokio sync-only internal APIs, the crate-private SyncExtractor trait, the 2 MB HTML size limit, size-optimized build config (opt-level="z"), and the async-wrapper/sync-internal API pattern. Load when building for wasm32, adding or modifying a WASM-compatible extractor, or debugging WASM build/runtime failures.

Work on Xberg TypeScript or JavaScript packages with the repository's actual poly, pnpm, npm, Vitest, napi-rs, wasm-pack, and integration-package boundaries. Load for TS/JS tooling or package changes, not Rust-only binding generation.