fix(vision): preserve adaptive OCR fallbacks

feat(vision): adaptively fuse native and OCR text
fix(vision): validate native recovery coverage
2026-08-16 21:42:45 -07:00 · 2026-08-16 21:42:45 -07:00 · 2026-08-16 21:42:45 -07:00 · 2026-08-16 21:42:45 -07:00 · 2026-08-16 21:42:45 -07:00 · 2026-08-16 21:42:45 -07:00
38 changed files with 384 additions and 4056 deletions
@@ -1,2 +0,0 @@
-*.pdf binary
-tests/snapshots/*.md text eol=lf
@@ -9,9 +9,6 @@ on:
 env:
  CARGO_TERM_COLOR: always

-permissions:
-  contents: read
-
 jobs:
  test:
    name: Test
@@ -71,12 +68,9 @@ jobs:
        with:
          key: clippy

-      - name: Run default clippy
+      - name: Run clippy
        run: cargo clippy -- -D warnings

-      - name: Run OCR clippy
-        run: cargo clippy --features ocr -- -D warnings
-
  build:
    name: Build
    runs-on: ${{ matrix.os }}
@@ -99,183 +93,6 @@ jobs:
      - name: Build
        run: cargo build --release --verbose

-  ocr:
-    name: OCR (${{ matrix.os }})
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [ubuntu-latest, macos-latest, windows-latest]
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
-
-      - name: Install Rust
-        uses: dtolnay/rust-toolchain@4cda84d5c5c54efe2404f9d843567869ab1699d4 # stable
-        with:
-          toolchain: stable
-
-      - name: Cache cargo
-        uses: Swatinem/rust-cache@c19371144df3bb44fab255c43d04cbc2ab54d1c4 # v2.9.1
-        with:
-          key: ocr-${{ matrix.os }}
-
-      - name: Test optional OCR feature
-        run: cargo test --features ocr
-
-  ocr-runtime:
-    name: OCR runtime smoke
-    runs-on: ubuntu-latest
-    timeout-minutes: 30
-    steps:
-      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
-
-      - name: Install Rust
-        uses: dtolnay/rust-toolchain@4cda84d5c5c54efe2404f9d843567869ab1699d4 # stable
-        with:
-          toolchain: stable
-
-      - uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
-        with:
-          python-version: '3.12'
-
-      - uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6 # v2.2.0
-        with:
-          bun-version: latest
-
-      - name: Cache cargo
-        uses: Swatinem/rust-cache@c19371144df3bb44fab255c43d04cbc2ab54d1c4 # v2.9.1
-        with:
-          key: ocr-runtime
-          workspaces: |
-            . -> target
-            napi -> target
-
-      - name: Install PDFium
-        shell: bash
-        run: |
-          archive="$RUNNER_TEMP/firecrawl-pdfium-linux-x64.tgz"
-          directory="$RUNNER_TEMP/firecrawl-pdfium"
-          curl --fail --location --silent --show-error \
-            https://github.com/firecrawl/pdfium-rs/releases/download/native-v7988/firecrawl-pdfium-linux-x64.tgz \
-            --output "$archive"
-          echo "6248189e07bbc33cdeb31976c539a88614307c8a19f3276dbd018efbe5b4a2a2  $archive" | sha256sum --check
-          mkdir -p "$directory"
-          tar -xzf "$archive" -C "$directory"
-          pdfium_path="$(find "$directory" -type f -name 'libpdfium.so' -print -quit)"
-          test -n "$pdfium_path"
-          echo "PDFIUM_LIB_PATH=$pdfium_path" >> "$GITHUB_ENV"
-
-      - name: Install ONNX Runtime
-        shell: bash
-        run: |
-          archive="$RUNNER_TEMP/onnxruntime-linux-x64-1.27.0.tgz"
-          directory="$RUNNER_TEMP/onnxruntime"
-          curl --fail --location --silent --show-error \
-            https://github.com/microsoft/onnxruntime/releases/download/v1.27.0/onnxruntime-linux-x64-1.27.0.tgz \
-            --output "$archive"
-          echo "547e40a48f1fe73e3f812d7c88a948612c23f896b91e4e2ee1e232d7b468246f  $archive" | sha256sum --check
-          mkdir -p "$directory"
-          tar -xzf "$archive" -C "$directory"
-          ort_path="$(find "$directory" -type f -name 'libonnxruntime.so*' -print -quit)"
-          test -n "$ort_path"
-          echo "ORT_DYLIB_PATH=$ort_path" >> "$GITHUB_ENV"
-
-      - name: Configure isolated model cache
-        shell: bash
-        run: echo "PDF_INSPECTOR_MODEL_CACHE=$RUNNER_TEMP/pdf-inspector-models" >> "$GITHUB_ENV"
-
-      - name: Build OCR CLI
-        run: cargo build --features ocr --bin pdf2md
-
-      - name: Test PDFium runtime
-        run: cargo test --features ocr --test local_render_tests
-
-      - name: Provision OCR model cache
-        shell: bash
-        run: |
-          target/debug/pdf2md \
-            tests/fixtures/scan_with_native_header_text.pdf \
-            --ocr force \
-            --json > /dev/null
-
-      - name: Run OCR CLI
-        shell: bash
-        run: |
-          target/debug/pdf2md \
-            tests/fixtures/scan_with_native_header_text.pdf \
-            --ocr auto \
-            --ocr-offline \
-            --json > "$RUNNER_TEMP/ocr-result.json"
-
-      - name: Validate OCR JSON contract
-        shell: bash
-        run: |
-          python3 - <<'PY'
-          import json
-          import os
-          from pathlib import Path
-
-          result = json.loads(
-              (Path(os.environ["RUNNER_TEMP"]) / "ocr-result.json").read_text()
-          )
-          assert result["schema_version"] == 1
-          assert result["pages_routed_to_ocr"] == [1]
-          assert result["pages_recommending_hosted"] == []
-          assert result["pages"][0]["source"] in {"ocr", "fused"}
-          assert result["pages"][0]["markdown"].strip()
-          assert "layout_ms" not in result["pages"][0]["timings"]
-          PY
-
-      - name: Run OCR launch smoke set
-        shell: bash
-        run: |
-          export PDF_INSPECTOR_OCR_TEST_MODELS="$PDF_INSPECTOR_MODEL_CACHE/pp-ocrv6-small/oar-ocr-v0.7.0"
-          cargo test --features ocr --test ocr_tests -- --nocapture
-
-      - name: Build Node binding
-        working-directory: napi
-        run: |
-          bun install --frozen-lockfile
-          bunx napi build --platform --release
-
-      - name: Run Node OCR binding
-        shell: bash
-        run: |
-          node --input-type=module - <<'JS'
-          import { readFileSync } from 'node:fs'
-          import { processPdfWithOcr } from './napi/index.js'
-
-          const pdf = readFileSync('tests/fixtures/scan_with_native_header_text.pdf')
-          const result = await processPdfWithOcr(pdf, { offline: true })
-          if (JSON.stringify(result.pagesRoutedToOcr) !== '[1]') throw new Error('unexpected OCR route')
-          if (result.pagesRecommendingHosted.length !== 0) throw new Error('unexpected hosted recommendation')
-          if (!['Ocr', 'Fused'].includes(result.pages[0].provenance.source)) throw new Error('unexpected source')
-          if (!result.pages[0].markdown.trim()) throw new Error('empty OCR markdown')
-          JS
-
-      - name: Build and install Python binding
-        shell: bash
-        run: |
-          python -m pip install 'maturin>=1,<2'
-          maturin build --release --out "$RUNNER_TEMP/python-wheels"
-          python -m pip install "$RUNNER_TEMP"/python-wheels/*.whl
-
-      - name: Run Python OCR binding
-        shell: bash
-        run: |
-          python - <<'PY'
-          import pdf_inspector
-
-          result = pdf_inspector.process_pdf_with_ocr(
-              "tests/fixtures/scan_with_native_header_text.pdf",
-              offline=True,
-          )
-          assert result.pages_routed_to_ocr == [1]
-          assert result.pages_recommending_hosted == []
-          assert result.pages[0].provenance.source in {"ocr", "fused"}
-          assert result.pages[0].markdown.strip()
-          PY
-
  wasm:
    name: WebAssembly
    runs-on: ubuntu-latest
@@ -86,14 +86,12 @@ jobs:
    name: Build ${{ matrix.target }}
    runs-on: ${{ matrix.os }}
    strategy:
-      fail-fast: false
      matrix:
        include:
          - os: ubuntu-latest
            target: x86_64-unknown-linux-gnu
          - os: ubuntu-latest
            target: aarch64-unknown-linux-gnu
-            docker-options: -e CFLAGS_aarch64_unknown_linux_gnu=-D__ARM_ARCH=8
          # macos-13 was retired by GitHub; macos-15-intel is the remaining
          # Intel runner label (available through 2027).
          - os: macos-15-intel
@@ -115,9 +113,6 @@ jobs:
          target: ${{ matrix.target }}
          args: --release --out dist
          manylinux: auto
-          # The manylinux AArch64 GCC omits this macro while preprocessing
-          # ring's assembly. AArch64 is ARMv8 by definition.
-          docker-options: ${{ matrix.docker-options }}

      - name: Upload wheel
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
@@ -60,7 +60,6 @@ jobs:
    name: Build ${{ matrix.target }}
    runs-on: ${{ matrix.os }}
    strategy:
-      fail-fast: false
      matrix:
        include:
          - os: ubuntu-latest
@@ -71,7 +70,6 @@ jobs:
          - os: ubuntu-latest
            target: aarch64-unknown-linux-gnu
            build-flags: --use-napi-cross
-            cflags: -D__ARM_ARCH=8
          - os: ubuntu-latest
            target: x86_64-unknown-linux-musl
            build-flags: -x
@@ -128,10 +126,6 @@ jobs:

      - name: Build native addon
        working-directory: napi
-        env:
-          # napi-cross's old AArch64 GCC omits this predefined macro while
-          # preprocessing ring's assembly. AArch64 is ARMv8 by definition.
-          CFLAGS_aarch64_unknown_linux_gnu: ${{ matrix.cflags }}
        run: bunx napi build --platform --release --target ${{ matrix.target }} ${{ matrix.build-flags }}

      - name: Upload native binary
@@ -1,6 +1,6 @@
 [package]
 name = "pdf-inspector"
-version = "1.15.0"
+version = "1.14.2"
 edition = "2021"
 autobins = false
 authors = ["Firecrawl Team"]
@@ -80,7 +80,7 @@ tempfile = "3.3"

 [features]
 default = []
-python = ["pyo3", "ocr"]
+python = ["pyo3"]
 vision = []
 model-cache = ["vision", "dep:dirs", "dep:fs2", "dep:sha2", "dep:windows-sys"]
 model-download = ["model-cache", "dep:ureq"]
@@ -5,7 +5,7 @@
 [![PyPI](https://img.shields.io/pypi/v/pdf-inspector.svg)](https://pypi.org/project/pdf-inspector/)
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)

-Fast Rust library for PDF classification and text extraction. By default it detects whether a PDF is text-based or scanned, extracts text with position awareness, and converts to clean Markdown without OCR. Native Rust and CLI consumers can opt into selective OCR. Includes bindings for [Python](docs/python.md), [Node.js](napi/README.md), and [browser WebAssembly](wasm/README.md).
+Fast Rust library for PDF classification and text extraction. Detects whether a PDF is text-based or scanned, extracts text with position awareness, and converts to clean Markdown — all without OCR. Includes bindings for [Python](docs/python.md), [Node.js](napi/README.md), and [browser WebAssembly](wasm/README.md).

 Built by [Firecrawl](https://firecrawl.dev) to handle text-based PDFs locally in under 200ms, skipping expensive OCR services for the ~54% of PDFs that don't need them.

@@ -18,10 +18,9 @@ Built by [Firecrawl](https://firecrawl.dev) to handle text-based PDFs locally in
 - **CID font support** — ToUnicode CMap decoding for Type0/Identity-H fonts, UTF-16BE, UTF-8, and Latin-1 encodings.
 - **Multi-column layout** — Automatic detection of newspaper-style columns, sequential reading order, and RTL text support.
 - **Encoding issue detection** — Automatically flags broken font encodings so callers can fall back to OCR.
- **Selective OCR** — Rust, CLI, Python, and Node can render only pages that need OCR, run PP-OCRv6 Small locally, and preserve per-page provenance and hosted-fallback recommendations.
 - **Single document load** — The document is parsed once and shared between detection and extraction, avoiding redundant I/O.
 - **Browser WebAssembly** — Run the same Rust parser locally in browsers and Web Workers, with embedded CMaps and no server round trip.
- **Lightweight by default** — The default Rust and browser builds remain pure extraction. Native Python and Node packages include the OCR integration, but PDFium, ONNX Runtime, and model files remain external and are touched only when a page is routed to OCR.
+- **Lightweight** — Pure Rust, no ML models, no external services. Single dependency on `lopdf` for PDF parsing.

 ## Benchmark

@@ -48,7 +47,8 @@ Use the [paired benchmark harness](docs/benchmarking.md) to compare two local bu
 ### Python

 ```bash
-pip install pdf-inspector
+pip install maturin
+maturin develop --release
 ```

 ```python
@@ -57,10 +57,6 @@ import pdf_inspector
 result = pdf_inspector.process_pdf("document.pdf")
 print(result.pdf_type)   # "text_based", "scanned", "image_based", "mixed"
 print(result.markdown)   # Markdown string or None
-
-# Selective OCR; clean text PDFs do not load the external OCR runtime.
-ocr = pdf_inspector.process_pdf_with_ocr("document.pdf")
-print(ocr.pages_routed_to_ocr)
 ```

 > Full API reference: [docs/python.md](docs/python.md)
@@ -73,15 +69,11 @@ npm install @firecrawl/pdf-inspector

 ```javascript
 import { readFileSync } from 'fs';
-import { processPdf, processPdfWithOcr } from '@firecrawl/pdf-inspector';
+import { processPdf, classifyPdf } from '@firecrawl/pdf-inspector';

-const pdf = readFileSync('document.pdf');
-const result = processPdf(pdf);
+const result = processPdf(readFileSync('document.pdf'));
 console.log(result.pdfType);   // "TextBased", "Scanned", "ImageBased", "Mixed"
 console.log(result.markdown);  // Markdown string or null
-
-const ocr = await processPdfWithOcr(pdf); // selective OCR, off the event loop
-console.log(ocr.pagesRoutedToOcr);
 ```

 > Full API reference: [napi/README.md](napi/README.md)
@@ -168,23 +160,6 @@ detect-pdf document.pdf --json
 detect-pdf document.pdf --analyze --json
 ```

-Rust and CLI consumers opt into OCR at build time:
-
-```bash
-cargo install pdf-inspector --features ocr --bin pdf2md
-PDFIUM_LIB_PATH=/path/to/libpdfium ORT_DYLIB_PATH=/path/to/libonnxruntime \
-  pdf2md scan.pdf --ocr auto --json
-```
-
-The OCR JSON envelope is versioned and reports routed pages, per-page source
-and confidence, warnings, and pages recommended for the hosted document
-pipeline. Native Python and Node packages expose the same pipeline without a
-source-build feature. All native entry points still require separately
-installed PDFium and ONNX Runtime libraries only when OCR is routed. See the
-[OCR runtime setup guide](docs/ocr-runtime.md) for pinned downloads, platform
-support, model-cache behavior, and hosted-fallback integration. See the
-[Rust API guide](docs/rust-api.md#complete-ocr-api) for lower-level controls.
-
 From a source checkout, use `cargo run --bin pdf2md -- document.pdf` or `cargo run --bin detect-pdf -- document.pdf` instead.

 ## Architecture
@@ -1,97 +0,0 @@
-# OCR runtime setup
-
-Selective OCR is available from the Rust library and CLI, Python, and Node.js.
-Clean native-text documents do not load an OCR dependency or download a model.
-When `auto` routes at least one page, the process needs PDFium, ONNX Runtime,
-and the pinned PP-OCRv6 Small model set.
-
-## Validated versions
-
-The reproducible runtime path uses these builds:
-
- [Firecrawl PDFium `native-v7988`](https://github.com/firecrawl/pdfium-rs/releases/tag/native-v7988),
-  containing PDFium `153.0.7988.0`
- [ONNX Runtime `1.27.0`](https://github.com/microsoft/onnxruntime/releases/tag/v1.27.0)
- PP-OCRv6 Small artifact revision `oar-ocr-v0.7.0`
-
-Use these versions for the reproducible path. Other compatible shared-library
-builds may work, but are not part of the release smoke test.
-
-## Install the shared libraries
-
-Download and extract the matching archives:
-
-| Platform | PDFium asset | ONNX Runtime asset |
-|---|---|---|
-| Linux x64 | `firecrawl-pdfium-linux-x64.tgz` | `onnxruntime-linux-x64-1.27.0.tgz` |
-| Linux ARM64 | `firecrawl-pdfium-linux-arm64.tgz` | `onnxruntime-linux-aarch64-1.27.0.tgz` |
-| macOS Apple Silicon | `firecrawl-pdfium-mac-arm64.tgz` | `onnxruntime-osx-arm64-1.27.0.tgz` |
-| Windows x64 | `firecrawl-pdfium-win-x64.tgz` | `onnxruntime-win-x64-1.27.0.zip` |
-
-The PDFium release publishes `SHA256SUMS`, build provenance, license files,
-and an SPDX document for every platform archive. GitHub publishes a SHA-256
-digest with each ONNX Runtime asset.
-
-Point pdf-inspector at the extracted shared libraries when they are not on the
-platform library search path:
-
-```bash
-export PDFIUM_LIB_PATH=/absolute/path/to/libpdfium.so
-export ORT_DYLIB_PATH=/absolute/path/to/libonnxruntime.so
-pdf2md scan.pdf --ocr auto --json
-```
-
-On macOS the filenames end in `.dylib`. On Windows, use PowerShell and point
-the variables at `pdfium.dll` and `onnxruntime.dll`:
-
-```powershell
-$env:PDFIUM_LIB_PATH = "C:\absolute\path\to\pdfium.dll"
-$env:ORT_DYLIB_PATH = "C:\absolute\path\to\onnxruntime.dll"
-pdf2md scan.pdf --ocr auto --json
-```
-
-The native extraction packages also support platforms without these exact
-runtime assets. In particular, the Python package has an Intel macOS wheel,
-but ONNX Runtime 1.27.0 does not publish an Intel macOS archive; local OCR on
-that target requires a compatible custom ONNX Runtime build.
-
-The full OCR path is exercised end to end on Linux x64 in CI. macOS and
-Windows compile and run the feature's platform-independent tests, while their
-external-runtime paths should be treated as preview until equivalent smoke
-jobs are added.
-
-## Model cache and offline mode
-
-The first routed page downloads and SHA-256-verifies three pinned artifacts:
-the detection model, recognition model, and character dictionary. Together
-they are about 31 MB. They are stored below the platform cache directory.
-Set `PDF_INSPECTOR_MODEL_CACHE` to choose a managed cache root.
-
-For hermetic deployments, populate the model directory ahead of time and use
-the language-specific offline option:
-
- CLI: `--ocr-offline --ocr-model-dir /models/pp-ocrv6-small`
- Rust: `ModelDownloadPolicy::Offline` with `OcrOptions::model_directory`
- Python: `offline=True, model_directory="/models/pp-ocrv6-small"`
- Node.js: `offline: true, modelDirectory: "/models/pp-ocrv6-small"`
-
-The model artifacts come from
-[`GreatV/oar-ocr`](https://github.com/GreatV/oar-ocr/releases/tag/v0.7.0),
-whose OCR implementation and upstream PaddleOCR project use Apache-2.0
-licensing. Models are downloaded at runtime and are not embedded in any
-pdf-inspector package.
-
-## Hosted fallback boundary
-
-`pages_recommending_hosted` is available after the local pipeline completes.
-It marks pages whose completed OCR result is empty, low-confidence, or still
-appears incomplete.
-
-Setup and execution failures happen before that result exists. A missing or
-incompatible PDFium/ONNX Runtime library, failed model acquisition, or OCR
-execution error is returned as an error. A downstream integration that has a
-hosted parser should catch that error and route the document to the hosted
-path. This keeps deployment problems distinct from page-quality judgments.
-
-In `auto`, documents with no routed pages return successfully without touching
-PDFium, ONNX Runtime, the model cache, or the network.
@@ -1,6 +1,6 @@
 # pdf-inspector

-Fast PDF classification, text extraction, and selective OCR. Detects whether a PDF is text-based or scanned, extracts text with position awareness, and converts clean native and OCR results to Markdown. Python bindings via [PyO3](https://pyo3.rs) for the [pdf-inspector](https://github.com/firecrawl/pdf-inspector) Rust library.
+Fast PDF classification and text extraction. Detects whether a PDF is text-based or scanned, extracts text with position awareness, and converts to clean Markdown — all without OCR. Python bindings via [PyO3](https://pyo3.rs) for the [pdf-inspector](https://github.com/firecrawl/pdf-inspector) Rust library.

 Built by [Firecrawl](https://firecrawl.dev) to handle text-based PDFs locally in under 200ms, skipping expensive OCR services for the ~54% of PDFs that don't need them.

@@ -10,8 +10,7 @@ Built by [Firecrawl](https://firecrawl.dev) to handle text-based PDFs locally in
 - **Markdown conversion** — headings, lists, code blocks, bold/italic, URL linking, and dual-mode table detection (PDF drawing ops + text-alignment heuristics).
 - **Layout-aware extraction** — multi-column reading order, position and font info per text item, RTL support.
 - **Robust text decoding** — CID/Type0 fonts via ToUnicode CMaps, plus automatic flagging of broken encodings so callers can fall back to OCR.
- **Selective OCR** — `auto` routes only pages rejected by native extraction; `force` OCRs every selected page; `off` keeps the result/provenance contract without external runtime work.
- **External artifacts** — the wheel embeds no OCR models, PDFium, or ONNX Runtime; clean `auto` requests never load or download them.
+- **Lightweight** — native Rust core, no ML models, no external services; ships type stubs.

 ## Benchmark

@@ -40,14 +39,6 @@ pip install maturin
 maturin develop --release
 ```

-OCR calls that route work require compatible PDFium and ONNX Runtime shared
-libraries. Set `PDFIUM_LIB_PATH` and `ORT_DYLIB_PATH` when they are not on the
-platform library search path. The pinned OCR model set is downloaded and
-checksum-verified on the first routed page; use `offline=True` with a warm
-cache or `model_directory` to prohibit network access. See the
-[OCR runtime setup guide](https://github.com/firecrawl/pdf-inspector/blob/main/docs/ocr-runtime.md)
-for pinned downloads, supported platforms, and hosted-fallback behavior.
-
 ## Usage

 ```python
@@ -90,19 +81,6 @@ for page in result.pages:
 # Restrict to specific 0-indexed pages (preserves caller order)
 result = pdf_inspector.extract_pages_markdown("document.pdf", pages=[0, 2])

-# One-call selective OCR. This releases the GIL while processing.
-ocr = pdf_inspector.process_pdf_with_ocr("document.pdf")
-for page in ocr.pages:
-    print(page.page_number, page.provenance.source)
-
-# Restrict OCR processing to 1-indexed PDF pages and prohibit downloads.
-ocr = pdf_inspector.process_pdf_with_ocr(
-    "document.pdf",
-    page_numbers=[1, 3],
-    model_directory="/opt/models/pp-ocrv6-small",
-    offline=True,
-)
-
 # Structure-tree elements from tagged PDFs (empty list when untagged).
 # Pages are 1-indexed to match TextItem.page, so (page, mcid) joins directly
 # against extract_text_with_positions — e.g. to recover real heading levels:
@@ -121,8 +99,6 @@ headings = [
 |---|---|
 | `process_pdf(path, pages=None)` | Full processing (detect + extract + markdown) |
 | `process_pdf_bytes(data, pages=None)` | Full processing from bytes |
-| `process_pdf_with_ocr(path, **options)` | Native extraction + selective OCR with provenance |
-| `process_pdf_with_ocr_bytes(data, **options)` | Native extraction + selective OCR from bytes |
 | `detect_pdf(path)` | Fast detection only (returns PdfResult) |
 | `detect_pdf_bytes(data)` | Fast detection from bytes |
 | `classify_pdf(path)` | Lightweight classification (returns PdfClassification) |
@@ -161,45 +137,6 @@ class PageOcrReasons:                # per-page OCR diagnostics
    page: int                        # 1-indexed
    reasons: list[str]               # machine-readable reason identifiers

-class OcrModelIdentity:
-    name: str                        # model family/name
-    revision: str                    # immutable artifact-set revision
-
-class OcrTimings:                    # per-page processing stages
-    render_ms: int
-    ocr_ms: int
-    assembly_ms: int
-
-class OcrPageProvenance:
-    page_number: int                 # 1-indexed
-    source: Literal["native", "ocr", "fused"]
-    ocr_model: OcrModelIdentity | None
-    render_dpi: float | None
-    ocr_confidence: float | None
-    timings: OcrTimings
-    warnings: list[str]
-    hosted_recommended: bool
-
-class OcrPageResult:
-    page_number: int                 # 1-indexed
-    markdown: str
-    provenance: OcrPageProvenance
-
-class OcrPdfResult:                  # process_pdf_with_ocr / bytes
-    markdown: str
-    pages: list[OcrPageResult]
-    page_count: int
-    pages_recommended_for_ocr: list[int]
-    pages_routed_to_ocr: list[int]
-    pages_recommending_hosted: list[int]
-    ocr_reasons_by_page: list[PageOcrReasons]
-    pages_with_tables: list[int]
-    pages_with_columns: list[int]
-    is_complex: bool
-    processing_time_ms: int
-    render_time_ms: int
-    ocr_time_ms: int
-
 class PdfClassification:             # classify_pdf
    pdf_type: str
    page_count: int
@@ -1,6 +1,6 @@
 # pdf-inspector

-Fast PDF classification and text extraction. The default build detects whether a PDF is text-based or scanned, extracts text with position awareness, and converts to clean Markdown without OCR. It is pure Rust, has no ML models or external services, and uses [lopdf](https://crates.io/crates/lopdf) for PDF parsing. Native Rust and CLI consumers can opt into selective OCR. Also available for [Python](https://pypi.org/project/pdf-inspector/) and [Node.js](https://www.npmjs.com/package/@firecrawl/pdf-inspector/).
+Fast PDF classification and text extraction. Detects whether a PDF is text-based or scanned, extracts text with position awareness, and converts to clean Markdown — all without OCR. The default build is pure Rust, has no ML models or external services, and uses [lopdf](https://crates.io/crates/lopdf) for PDF parsing. Also available for [Python](https://pypi.org/project/pdf-inspector/) and [Node.js](https://www.npmjs.com/package/@firecrawl/pdf-inspector/).

 Built by [Firecrawl](https://firecrawl.dev) to handle text-based PDFs locally in under 200ms, skipping expensive OCR services for the ~54% of PDFs that don't need them.

@@ -123,10 +123,10 @@ The native-only `vision` feature exposes the stable seam used by OCR
 integrations without selecting or embedding an inference runtime. The
 separate `model-cache` feature adds pinned artifact management:

- `PageRenderer` and `OcrEngine` traits;
+- `PageRenderer`, `OcrEngine`, and `LayoutEngine` traits;
 - renderer-neutral owned page buffers and affine pixel↔PDF transforms;
 - `OcrOptions` and opt-in `Off`/`Auto`/`Force` routing modes;
- positioned OCR results and per-page provenance types; and
+- positioned OCR/layout results and per-page provenance types; and
 - a versioned PP-OCRv6 Small manifest with checksum-verified, locked, atomic
  model-cache installation and explicit offline-directory overrides.

@@ -135,9 +135,9 @@ separate `model-cache` feature adds pinned artifact management:
 pdf-inspector = { version = "1", features = ["vision", "model-cache"] }
 ```

-The OCR contracts preserve existing behavior by default: OCR is `Off` and
-model resolution is never reached. `ModelStore` itself does not access the
-network. The optional `model-download` feature provides an
+The OCR contracts preserve existing behavior by default: OCR is `Off`, learned
+layout is disabled, and model resolution is never reached. `ModelStore` itself
+does not access the network. The optional `model-download` feature provides an
 HTTPS downloader that streams pinned artifacts into the checksum-verified
 cache only after routing has selected OCR work. Offline consumers set an
 explicit model directory and `ModelDownloadPolicy::Offline`. Renderer-only
@@ -171,10 +171,9 @@ and `PdfiumRenderer` implements the renderer-neutral `PageRenderer` trait.
 pdf-inspector = { version = "1", features = ["render-pdfium"] }
 ```

-PDFium is loaded at runtime and is not bundled into the crate. Set
-`PDFIUM_LIB_PATH` to the platform shared library, place that library next to
-the executable, or use another discovery route supported by
-`firecrawl-pdfium`. A load failure reports this prerequisite directly.
+PDFium is loaded at runtime. Set `PDFIUM_LIB_PATH`, place its shared library
+next to the executable, or use another discovery route supported by
+`firecrawl-pdfium`.

 ```rust
 use pdf_inspector::vision::{PdfiumRenderer, RenderOptions};
@@ -206,11 +205,9 @@ The native-only `ocr-oar` feature adds a CPU PP-OCRv6 Small implementation of
 not enable model auto-download, ONNX Runtime download, or PDF rendering. Model
 files remain external, must match the pinned manifest, and are opened only
 after `ModelStore` verifies their exact size and SHA-256 digest. Install an
-ONNX Runtime shared library separately and set `ORT_DYLIB_PATH` to its full
-path when it is not available through the platform library search path. The
-runtime is resolved only when an OCR engine is first constructed; clean
-`Auto` requests do not require it. The feature currently requires Rust 1.95
-or newer, matching OAR 0.9.1's MSRV.
+ONNX Runtime shared library separately and set `ORT_DYLIB_PATH` when it is not
+available through the platform library search path. The feature currently
+requires Rust 1.95 or newer, matching OAR 0.9.1's MSRV.

 ```toml
 [dependencies]
@@ -332,10 +329,7 @@ let fused = fuse_ocr_pages(
 for page in &fused.pages {
    println!("{}", page.markdown);
    if page.provenance.hosted_recommended {
-        eprintln!(
-            "page {} needs the hosted document pipeline",
-            page.page_number,
-        );
+        eprintln!("page {} needs the hosted document pipeline", page.page + 1);
    }
 }
 ```
@@ -360,11 +354,15 @@ pdf-inspector = { version = "1", features = ["ocr"] }
 ```

 ```rust
-use pdf_inspector::vision::{process_pdf_with_ocr, OcrPdfOptions};
+use pdf_inspector::vision::{
+    process_pdf_with_ocr, OcrMode, OcrPdfOptions,
+};

 let result = process_pdf_with_ocr(
    "document.pdf",
-    OcrPdfOptions::auto().page_numbers([1, 2, 3]),
+    OcrPdfOptions::new()
+        .mode(OcrMode::Auto)
+        .pages([1, 2, 3]),
 )?;

 println!("{}", result.markdown);
@@ -379,25 +377,17 @@ Native extraction always runs first. In `Auto`, a clean PDF returns before
 PDFium loading, model-cache access, HTTP, or OAR initialization. Model files
 remain external and the default crate feature set remains unchanged. `Off`
 provides the same native-only behavior through the OCR result/provenance
-shape; `Force` renders every selected page. OCR uses the existing deterministic
-table, column, reading-order, and Markdown assembly path; no learned layout
-model is included.
-
-The [OCR runtime setup guide](https://github.com/firecrawl/pdf-inspector/blob/main/docs/ocr-runtime.md)
-lists the pinned PDFium and ONNX Runtime builds, environment variables, model
-cache behavior, and the error boundary downstream hosted fallbacks should use.
+shape; `Force` renders every selected page. Learned layout intentionally
+returns an explicit unsupported error in this lightweight pipeline.

 For ambiguous mixed pages, `Auto` privately retains clean native fragments
 instead of discarding them when OCR is selected. After recognition it compares
 script-agnostic text quality, OCR confidence, character overlap, and material
 new coverage. Exact native text wins over a duplicate or weak OCR hypothesis;
 complementary image-backed text is fused; and pages where both candidates are
-weak recommend the hosted document pipeline. A page routed because native
-coverage appeared incomplete also recommends hosted processing when confident
-OCR only duplicates the retained fragment: the agreement preserves trustworthy
-text, but neither hypothesis proves full-page coverage. Public native-only
-extraction continues to suppress pages marked unreliable, and clean text
-documents pay no renderer or model-initialization cost.
+weak recommend the hosted document pipeline. Public native-only extraction
+continues to suppress pages marked unreliable, and clean text documents pay no
+renderer or model-initialization cost.

 In `Auto`, pages routed only for suspicious font encoding or vectorized text
 first get a bounded positioned-text probe through PDFium. A credible recovered
@@ -417,13 +407,11 @@ not hot-reload a running process; restart the process when intentionally
 replacing files at the same paths. CPU inference uses at most four intra-op
 threads per ONNX session so a single small page does not oversubscribe larger
 hosts, and recognizes variable-width line crops individually to avoid
-padding-heavy CPU batches. The high-level pipeline renders and fuses at most
-four routed pages at a time, bounding bitmap memory on long documents.
+padding-heavy CPU batches.

 Build the CLI with the same opt-in feature:

 ```bash
-cargo install pdf-inspector --features ocr --bin pdf2md
 cargo build --release --features ocr --bin pdf2md
 pdf2md document.pdf --ocr auto --raw
 pdf2md document.pdf --ocr auto --json
@@ -432,11 +420,10 @@ pdf2md document.pdf --ocr auto --ocr-offline --ocr-model-dir /opt/models/pp-ocrv

 CLI controls include `--ocr-dpi`, `--ocr-min-confidence`,
 `--ocr-hosted-threshold`, `--select-pages`, and the existing encrypted-PDF
-`--password` option. JSON output has `schema_version: 1` and includes per-page Markdown, source/model
+`--password` option. JSON output includes per-page Markdown, source/model
 provenance, confidence, timings, warnings, routed pages, and hosted-fallback
 recommendations. Page numbers in `OcrPdfResult` and its per-page provenance
-are 1-indexed, matching the PDF page numbers accepted by
-`OcrPdfOptions::page_numbers`.
+are 1-indexed, matching the PDF page numbers accepted by `OcrPdfOptions::pages`.

 Extract per-page Markdown (one string per page, plus document-wide layout
 metadata):
@@ -1,13 +1,13 @@
 [package]
 name = "pdf-inspector-napi"
-version = "1.15.0"
+version = "1.14.2"
 edition = "2021"

 [lib]
 crate-type = ["cdylib"]

 [dependencies]
-pdf-inspector = { path = "..", features = ["ocr"] }
+pdf-inspector = { path = ".." }
 napi = { version = "3.0.0", features = ["serde-json"] }
 napi-derive = "3.0.0"

@@ -10,8 +10,7 @@ Built by [Firecrawl](https://firecrawl.dev) for hybrid OCR pipelines — extract
 - **Region-based extraction** — pull text from bounding boxes with per-region quality checks (`needsOcr`).
 - **Layout-aware** — multi-column reading order, position and font info per text item, RTL support.
 - **Robust text decoding** — CID/Type0 fonts via ToUnicode CMaps, plus automatic flagging of broken encodings so callers can fall back to OCR.
- **Selective OCR** — `Auto` routes only pages rejected by native extraction and returns source/model provenance plus hosted-fallback recommendations.
- **External artifacts** — the native package embeds no OCR models, PDFium, or ONNX Runtime; clean `Auto` requests never load or download them.
+- **Lightweight** — native Rust core via napi-rs, no ML models, no external services; ~5–6 MB platform binary, TypeScript definitions included.

 ## Benchmark

@@ -37,42 +36,8 @@ bun add @firecrawl/pdf-inspector

 Prebuilt binaries for **Linux x64/ARM64** (glibc and musl/Alpine), **macOS ARM64**, and **Windows x64** — npm installs only the one matching your platform. No Rust toolchain needed.

-OCR calls that route work require compatible PDFium and ONNX Runtime shared
-libraries. Set `PDFIUM_LIB_PATH` and `ORT_DYLIB_PATH` when they are not on the
-platform library search path. The pinned OCR model set is downloaded and
-checksum-verified on the first routed page; use `offline: true` with a warm
-cache or `modelDirectory` to prohibit network access. See the
-[OCR runtime setup guide](https://github.com/firecrawl/pdf-inspector/blob/main/docs/ocr-runtime.md)
-for pinned downloads, supported platforms, and hosted-fallback behavior.
-
 ## API

-### `processPdfWithOcr(buffer: Buffer, options?: OcrOptions): Promise<OcrPdfResult>`
-
-Run native extraction first and OCR only the pages selected by its quality
-signals. The default mode is `Auto`; `Off` returns the same detailed result
-shape without external runtime work, and `Force` OCRs every selected page.
-The work runs on the libuv thread pool and never blocks Node's event loop.
-
-```typescript
-import { OcrMode, processPdfWithOcr } from '@firecrawl/pdf-inspector'
-
-const result = await processPdfWithOcr(pdf, {
-  mode: OcrMode.Auto,
-  pageNumbers: [1, 3], // 1-indexed
-})
-
-for (const page of result.pages) {
-  console.log(page.pageNumber, page.provenance.source)
-}
-console.log(result.pagesRoutedToOcr)
-console.log(result.pagesRecommendingHosted)
-```
-
-For offline deployments, pass `modelDirectory` and `offline: true`. Other
-controls include `dpi`, `minimumConfidence`,
-`hostedRecommendationConfidence`, and `password`.
-
 ### `classifyPdf(buffer: Buffer): PdfClassification`

 Classify a PDF as TextBased, Scanned, Mixed, or ImageBased (~10-50ms). Returns which pages need OCR.
@@ -159,22 +124,6 @@ interface RegionText {
  needsOcr: boolean         // true when text is unreliable
  ocrReason?: string        // "suspected_garbled_text" when known
 }
-
-interface OcrPdfResult {
-  markdown: string
-  pages: OcrPageResult[]              // 1-indexed pages + provenance
-  pageCount: number
-  pagesRecommendedForOcr: number[]
-  pagesRoutedToOcr: number[]
-  pagesRecommendingHosted: number[]
-  ocrReasonsByPage: PageOcrReasons[]
-  pagesWithTables: number[]
-  pagesWithColumns: number[]
-  isComplex: boolean
-  processingTimeMs: number
-  renderTimeMs: number
-  ocrTimeMs: number
-}
 ```

 ## Platforms
@@ -8,12 +8,12 @@
        "@napi-rs/cli": "^3.4.1",
      },
      "optionalDependencies": {
-        "@firecrawl/pdf-inspector-darwin-arm64": "1.15.0",
-        "@firecrawl/pdf-inspector-linux-arm64-gnu": "1.15.0",
-        "@firecrawl/pdf-inspector-linux-arm64-musl": "1.15.0",
-        "@firecrawl/pdf-inspector-linux-x64-gnu": "1.15.0",
-        "@firecrawl/pdf-inspector-linux-x64-musl": "1.15.0",
-        "@firecrawl/pdf-inspector-win32-x64-msvc": "1.15.0",
+        "@firecrawl/pdf-inspector-darwin-arm64": "1.14.2",
+        "@firecrawl/pdf-inspector-linux-arm64-gnu": "1.14.2",
+        "@firecrawl/pdf-inspector-linux-arm64-musl": "1.14.2",
+        "@firecrawl/pdf-inspector-linux-x64-gnu": "1.14.2",
+        "@firecrawl/pdf-inspector-linux-x64-musl": "1.14.2",
+        "@firecrawl/pdf-inspector-win32-x64-msvc": "1.14.2",
      },
    },
  },
@@ -1,6 +1,6 @@
 {
  "name": "@firecrawl/pdf-inspector",
-  "version": "1.15.0",
+  "version": "1.14.2",
  "description": "Fast PDF classification and text extraction. Detect text-based vs scanned PDFs, extract text by region with quality checks. Native Rust performance via napi-rs.",
  "main": "index.js",
  "types": "index.d.ts",
@@ -52,11 +52,11 @@
    "@napi-rs/cli": "^3.4.1"
  },
  "optionalDependencies": {
-    "@firecrawl/pdf-inspector-linux-x64-gnu": "1.15.0",
-    "@firecrawl/pdf-inspector-linux-x64-musl": "1.15.0",
-    "@firecrawl/pdf-inspector-linux-arm64-gnu": "1.15.0",
-    "@firecrawl/pdf-inspector-linux-arm64-musl": "1.15.0",
-    "@firecrawl/pdf-inspector-darwin-arm64": "1.15.0",
-    "@firecrawl/pdf-inspector-win32-x64-msvc": "1.15.0"
+    "@firecrawl/pdf-inspector-linux-x64-gnu": "1.14.2",
+    "@firecrawl/pdf-inspector-linux-x64-musl": "1.14.2",
+    "@firecrawl/pdf-inspector-linux-arm64-gnu": "1.14.2",
+    "@firecrawl/pdf-inspector-linux-arm64-musl": "1.14.2",
+    "@firecrawl/pdf-inspector-darwin-arm64": "1.14.2",
+    "@firecrawl/pdf-inspector-win32-x64-msvc": "1.14.2"
  }
 }
@@ -27,26 +27,6 @@ pub enum ItemType {
    FormField,
 }

-/// Selects when OCR runs.
-#[napi(string_enum)]
-#[derive(Clone, Copy)]
-pub enum OcrMode {
-    /// Never run OCR; return the native extraction in the OCR result shape.
-    Off,
-    /// Run OCR only on pages selected by the native quality signals.
-    Auto,
-    /// Run OCR on every selected page.
-    Force,
-}
-
-/// How final page content was sourced.
-#[napi(string_enum)]
-pub enum PageContentSource {
-    Native,
-    Ocr,
-    Fused,
-}
-
 // ---------------------------------------------------------------------------
 // Result types
 // ---------------------------------------------------------------------------
@@ -148,84 +128,6 @@ pub struct VectorGridDetectionJs {
    pub cell_bboxes: Vec<Vec<f64>>,
 }

-/// Options for one-call native extraction with selective OCR.
-#[napi(object)]
-#[derive(Clone)]
-pub struct OcrOptions {
-    /// OCR routing behavior. Defaults to Auto.
-    pub mode: Option<OcrMode>,
-    /// Optional 1-indexed page selection.
-    pub page_numbers: Option<Vec<u32>>,
-    /// Password for an encrypted PDF.
-    pub password: Option<String>,
-    /// Page rasterization resolution. Defaults to 150 DPI.
-    pub dpi: Option<f64>,
-    /// Drop OCR spans below this inclusive 0-1 threshold.
-    pub minimum_confidence: Option<f64>,
-    /// Recommend hosted parsing below this inclusive 0-1 page confidence.
-    pub hosted_recommendation_confidence: Option<f64>,
-    /// Directory containing an offline OCR model set.
-    pub model_directory: Option<String>,
-    /// Disable model downloads and require a model directory or warm cache.
-    pub offline: Option<bool>,
-}
-
-/// Exact OCR model identity retained in page provenance.
-#[napi(object)]
-pub struct OcrModelIdentity {
-    pub name: String,
-    pub revision: String,
-}
-
-/// Per-page OCR processing timings.
-#[napi(object)]
-pub struct OcrTimings {
-    pub render_ms: u32,
-    pub ocr_ms: u32,
-    pub assembly_ms: u32,
-}
-
-/// Source, model, confidence, and fallback metadata for one page.
-#[napi(object)]
-pub struct OcrPageProvenance {
-    /// 1-indexed page number.
-    pub page_number: u32,
-    pub source: PageContentSource,
-    pub ocr_model: Option<OcrModelIdentity>,
-    pub render_dpi: Option<f64>,
-    pub ocr_confidence: Option<f64>,
-    pub timings: OcrTimings,
-    pub warnings: Vec<String>,
-    pub hosted_recommended: bool,
-}
-
-/// Final Markdown and provenance for one page.
-#[napi(object)]
-pub struct OcrPageResult {
-    /// 1-indexed page number.
-    pub page_number: u32,
-    pub markdown: String,
-    pub provenance: OcrPageProvenance,
-}
-
-/// Complete native/OCR Markdown output.
-#[napi(object)]
-pub struct OcrPdfResult {
-    pub markdown: String,
-    pub pages: Vec<OcrPageResult>,
-    pub page_count: u32,
-    pub pages_recommended_for_ocr: Vec<u32>,
-    pub pages_routed_to_ocr: Vec<u32>,
-    pub pages_recommending_hosted: Vec<u32>,
-    pub ocr_reasons_by_page: Vec<PageOcrReasons>,
-    pub pages_with_tables: Vec<u32>,
-    pub pages_with_columns: Vec<u32>,
-    pub is_complex: bool,
-    pub processing_time_ms: u32,
-    pub render_time_ms: u32,
-    pub ocr_time_ms: u32,
-}
-
 // ---------------------------------------------------------------------------
 // Helpers
 // ---------------------------------------------------------------------------
@@ -266,103 +168,6 @@ fn to_napi_page_ocr_reasons(reasons: Vec<pdf_inspector::PageOcrReasons>) -> Vec<
        .collect()
 }

-fn to_core_ocr_options(options: Option<OcrOptions>) -> pdf_inspector::vision::OcrPdfOptions {
-    let mut result = pdf_inspector::vision::OcrPdfOptions::auto();
-    let Some(options) = options else {
-        return result;
-    };
-
-    if let Some(mode) = options.mode {
-        result.ocr.mode = match mode {
-            OcrMode::Off => pdf_inspector::vision::OcrMode::Off,
-            OcrMode::Auto => pdf_inspector::vision::OcrMode::Auto,
-            OcrMode::Force => pdf_inspector::vision::OcrMode::Force,
-        };
-    }
-    if let Some(pages) = options.page_numbers {
-        result = result.page_numbers(pages);
-    }
-    if let Some(password) = options.password {
-        result = result.password(password);
-    }
-    if let Some(dpi) = options.dpi {
-        result.render.dpi = dpi as f32;
-    }
-    if let Some(minimum_confidence) = options.minimum_confidence {
-        result.ocr.minimum_confidence = minimum_confidence as f32;
-    }
-    if let Some(confidence) = options.hosted_recommendation_confidence {
-        result.hosted_recommendation_confidence = confidence as f32;
-    }
-    if let Some(directory) = options.model_directory {
-        result.ocr.model_directory = Some(directory.into());
-    }
-    if options.offline.unwrap_or(false) {
-        result.ocr.model_downloads = pdf_inspector::vision::ModelDownloadPolicy::Offline;
-    }
-    result
-}
-
-fn convert_page_content_source(
-    source: pdf_inspector::vision::PageContentSource,
-) -> PageContentSource {
-    match source {
-        pdf_inspector::vision::PageContentSource::Native => PageContentSource::Native,
-        pdf_inspector::vision::PageContentSource::Ocr => PageContentSource::Ocr,
-        pdf_inspector::vision::PageContentSource::Fused => PageContentSource::Fused,
-        _ => PageContentSource::Native,
-    }
-}
-
-fn timing_ms(value: u64) -> u32 {
-    u32::try_from(value).unwrap_or(u32::MAX)
-}
-
-fn to_napi_ocr_result(result: pdf_inspector::vision::OcrPdfResult) -> OcrPdfResult {
-    OcrPdfResult {
-        markdown: result.markdown,
-        pages: result
-            .pages
-            .into_iter()
-            .map(|page| {
-                let provenance = page.provenance;
-                OcrPageResult {
-                    page_number: page.page_number,
-                    markdown: page.markdown,
-                    provenance: OcrPageProvenance {
-                        page_number: provenance.page_number,
-                        source: convert_page_content_source(provenance.source),
-                        ocr_model: provenance.ocr_model.map(|model| OcrModelIdentity {
-                            name: model.name,
-                            revision: model.revision,
-                        }),
-                        render_dpi: provenance.render_dpi.map(f64::from),
-                        ocr_confidence: provenance.ocr_confidence.map(f64::from),
-                        timings: OcrTimings {
-                            render_ms: timing_ms(provenance.timings.render_ms),
-                            ocr_ms: timing_ms(provenance.timings.ocr_ms),
-                            assembly_ms: timing_ms(provenance.timings.assembly_ms),
-                        },
-                        warnings: provenance.warnings,
-                        hosted_recommended: provenance.hosted_recommended,
-                    },
-                }
-            })
-            .collect(),
-        page_count: result.page_count,
-        pages_recommended_for_ocr: result.pages_recommended_for_ocr,
-        pages_routed_to_ocr: result.pages_routed_to_ocr,
-        pages_recommending_hosted: result.pages_recommending_hosted,
-        ocr_reasons_by_page: to_napi_page_ocr_reasons(result.ocr_reasons_by_page),
-        pages_with_tables: result.pages_with_tables,
-        pages_with_columns: result.pages_with_columns,
-        is_complex: result.is_complex,
-        processing_time_ms: timing_ms(result.processing_time_ms),
-        render_time_ms: timing_ms(result.render_time_ms),
-        ocr_time_ms: timing_ms(result.ocr_time_ms),
-    }
-}
-
 fn convert_item_type(t: &pdf_inspector::types::ItemType) -> (ItemType, Option<String>) {
    match t {
        pdf_inspector::types::ItemType::Text => (ItemType::Text, None),
@@ -414,13 +219,6 @@ fn process_pdf_impl(bytes: &[u8], pages: Option<Vec<u32>>) -> Result<PdfResult>
    Ok(to_napi_result(result))
 }

-fn process_pdf_with_ocr_impl(bytes: &[u8], options: Option<OcrOptions>) -> Result<OcrPdfResult> {
-    let options = to_core_ocr_options(options);
-    let result = pdf_inspector::vision::process_pdf_with_ocr_mem(bytes, options)
-        .map_err(|error| to_napi_err(error, "process_pdf_with_ocr"))?;
-    Ok(to_napi_ocr_result(result))
-}
-
 fn classify_pdf_impl(bytes: &[u8]) -> Result<PdfClassification> {
    let result =
        pdf_inspector::classify_pdf_mem(bytes).map_err(|e| to_napi_err(e, "classify_pdf"))?;
@@ -1020,45 +818,6 @@ pub fn process_pdf_async(buffer: Buffer, pages: Option<Vec<u32>>) -> AsyncTask<P
    })
 }

-pub struct ProcessPdfWithOcrTask {
-    bytes: Vec<u8>,
-    options: Option<OcrOptions>,
-}
-
-impl Task for ProcessPdfWithOcrTask {
-    type Output = OcrPdfResult;
-    type JsValue = OcrPdfResult;
-
-    fn compute(&mut self) -> Result<Self::Output> {
-        let bytes = std::mem::take(&mut self.bytes);
-        let options = self.options.take();
-        catch_panic(
-            "process_pdf_with_ocr",
-            panic::AssertUnwindSafe(move || process_pdf_with_ocr_impl(&bytes, options)),
-        )
-    }
-
-    fn resolve(&mut self, _env: Env, output: Self::Output) -> Result<Self::JsValue> {
-        Ok(output)
-    }
-}
-
-/// Process a PDF with selective OCR on the libuv thread pool.
-///
-/// OCR defaults to Auto, which only loads PDFium, ONNX Runtime, and the OCR
-/// model if native extraction routes at least one page. The input buffer is
-/// copied before the promise is returned and is safe to reuse immediately.
-#[napi(ts_return_type = "Promise<OcrPdfResult>")]
-pub fn process_pdf_with_ocr(
-    buffer: Buffer,
-    options: Option<OcrOptions>,
-) -> AsyncTask<ProcessPdfWithOcrTask> {
-    AsyncTask::new(ProcessPdfWithOcrTask {
-        bytes: buffer.to_vec(),
-        options,
-    })
-}
-
 pub struct ClassifyPdfTask {
    bytes: Vec<u8>,
 }
@@ -3,7 +3,6 @@ import { strict as assert } from 'assert';
 import {
  processPdf,
  processPdfAsync,
-  processPdfWithOcr,
  detectPdf,
  classifyPdf,
  classifyPdfAsync,
@@ -221,37 +220,6 @@ const fromMutated = await inFlight;
 assert.equal(fromMutated.markdown, result.markdown);
 console.log('  processPdfAsync input copied at call time: OK');

-// --- Selective OCR ---
-console.log('Testing processPdfWithOcr...');
-
-// Off exercises the complete result/provenance contract without loading
-// external PDFium, ONNX Runtime, or model artifacts.
-const ocrOff = await processPdfWithOcr(fixture, { mode: 'Off' });
-assert.equal(ocrOff.pageCount, 3);
-assert.equal(ocrOff.pages.length, 3);
-assert.deepEqual(ocrOff.pagesRoutedToOcr, []);
-assert.ok(ocrOff.pages.every(page => page.provenance.source === 'Native'));
-assert.ok(ocrOff.pages.every(page => page.provenance.ocrModel === undefined));
-assert.ok(ocrOff.markdown.length > 0);
-
-// Auto must preserve the lightweight path for clean text PDFs.
-const ocrAuto = await processPdfWithOcr(fixture);
-assert.deepEqual(ocrAuto.pagesRoutedToOcr, []);
-assert.equal(ocrAuto.renderTimeMs, 0);
-assert.equal(ocrAuto.ocrTimeMs, 0);
-
-const ocrSelected = await processPdfWithOcr(fixture, {
-  mode: 'Off',
-  pageNumbers: [2],
-});
-assert.deepEqual(ocrSelected.pages.map(page => page.pageNumber), [2]);
-
-await assert.rejects(
-  processPdfWithOcr(fixture, { mode: 'Off', pageNumbers: [0] }),
-  /page 0/,
-);
-console.log('  processPdfWithOcr: OK');
-
 // concurrent async calls all settle
 const [c1, c2, c3] = await Promise.all([
  processPdfAsync(fixture),
@@ -1,6 +1,6 @@
 """Type stubs for pdf_inspector."""

-from typing import Literal, Optional
+from typing import Optional

 class PdfResult:
    """Result of processing a PDF file."""
@@ -27,53 +27,6 @@ class PageOcrReasons:
    reasons: list[str]
    """Machine-readable OCR reason identifiers."""

-class OcrModelIdentity:
-    """Exact OCR model identity retained in page provenance."""
-    name: str
-    revision: str
-
-class OcrTimings:
-    """Per-page OCR processing timings."""
-    render_ms: int
-    ocr_ms: int
-    assembly_ms: int
-
-class OcrPageProvenance:
-    """Source, model, confidence, and fallback metadata for one page."""
-    page_number: int
-    """1-indexed page number."""
-    source: Literal["native", "ocr", "fused"]
-    """'native', 'ocr', or 'fused'."""
-    ocr_model: Optional[OcrModelIdentity]
-    render_dpi: Optional[float]
-    ocr_confidence: Optional[float]
-    timings: OcrTimings
-    warnings: list[str]
-    hosted_recommended: bool
-
-class OcrPageResult:
-    """Final Markdown and provenance for one page."""
-    page_number: int
-    """1-indexed page number."""
-    markdown: str
-    provenance: OcrPageProvenance
-
-class OcrPdfResult:
-    """Complete native/OCR Markdown output."""
-    markdown: str
-    pages: list[OcrPageResult]
-    page_count: int
-    pages_recommended_for_ocr: list[int]
-    pages_routed_to_ocr: list[int]
-    pages_recommending_hosted: list[int]
-    ocr_reasons_by_page: list[PageOcrReasons]
-    pages_with_tables: list[int]
-    pages_with_columns: list[int]
-    is_complex: bool
-    processing_time_ms: int
-    render_time_ms: int
-    ocr_time_ms: int
-
 class PdfClassification:
    """Lightweight PDF classification result."""
    pdf_type: str
@@ -161,39 +114,6 @@ def process_pdf_bytes(data: bytes, pages: Optional[list[int]] = None) -> PdfResu
    """Process a PDF from bytes in memory."""
    ...

-def process_pdf_with_ocr(
-    path: str,
-    *,
-    mode: Literal["off", "auto", "force"] = "auto",
-    page_numbers: Optional[list[int]] = None,
-    password: Optional[str] = None,
-    dpi: float = 150.0,
-    minimum_confidence: float = 0.0,
-    hosted_recommendation_confidence: float = 0.5,
-    model_directory: Optional[str] = None,
-    offline: bool = False,
-) -> OcrPdfResult:
-    """Process a PDF through native extraction and selective OCR.
-
-    Page numbers are 1-indexed. OCR runs without holding the Python GIL.
-    """
-    ...
-
-def process_pdf_with_ocr_bytes(
-    data: bytes,
-    *,
-    mode: Literal["off", "auto", "force"] = "auto",
-    page_numbers: Optional[list[int]] = None,
-    password: Optional[str] = None,
-    dpi: float = 150.0,
-    minimum_confidence: float = 0.0,
-    hosted_recommendation_confidence: float = 0.5,
-    model_directory: Optional[str] = None,
-    offline: bool = False,
-) -> OcrPdfResult:
-    """Process PDF bytes through native extraction and selective OCR."""
-    ...
-
 def detect_pdf(path: str) -> PdfResult:
    """Fast detection only — no text extraction."""
    ...
@@ -6,7 +6,7 @@ build-backend = "maturin"
 name = "pdf-inspector"
 # Keep package versions in sync with `python3 scripts/version.py <version>`.
 # CI publishes automatically when the synchronized change lands on main.
-version = "1.15.0"
+version = "1.14.2"
 description = "Fast PDF inspection, classification, and text extraction with smart scanned vs text-based detection"
 readme = "docs/python.md"
 license = { text = "MIT" }
@@ -975,7 +975,7 @@ result = pdf_inspector.<span class="fn">process_pdf</span>(<span class="str">"do
 <script>
  (() => {
    const MAX_FILE_SIZE = 25 * 1024 * 1024;
-    const WASM_MODULE_URL = "https://cdn.jsdelivr.net/npm/@firecrawl/pdf-inspector-wasm@1.15.0/pdf_inspector_wasm.js";
+    const WASM_MODULE_URL = "https://cdn.jsdelivr.net/npm/@firecrawl/pdf-inspector-wasm@1.14.2/pdf_inspector_wasm.js";
    const input = document.querySelector("#pdf-input");
    const dropZone = document.querySelector("#drop-zone");
    const filePanel = document.querySelector("#demo-file");
@@ -165,8 +165,8 @@ fn format_ocr_json(result: &OcrPdfResult) -> String {
                .collect::<Vec<_>>()
                .join(",");
            format!(
-                r#"{{"page":{},"source":"{}","markdown":"{}","ocr_model":{},"render_dpi":{},"ocr_confidence":{},"hosted_recommended":{},"timings":{{"render_ms":{},"ocr_ms":{},"assembly_ms":{}}},"warnings":[{}]}}"#,
-                provenance.page_number,
+                r#"{{"page":{},"source":"{}","markdown":"{}","ocr_model":{},"render_dpi":{},"ocr_confidence":{},"hosted_recommended":{},"timings":{{"render_ms":{},"ocr_ms":{},"layout_ms":{},"assembly_ms":{}}},"warnings":[{}]}}"#,
+                provenance.page,
                source,
                json_escape(&page.markdown),
                model,
@@ -175,6 +175,7 @@ fn format_ocr_json(result: &OcrPdfResult) -> String {
                provenance.hosted_recommended,
                provenance.timings.render_ms,
                provenance.timings.ocr_ms,
+                provenance.timings.layout_ms,
                provenance.timings.assembly_ms,
                warnings,
            )
@@ -195,7 +196,7 @@ fn format_ocr_json(result: &OcrPdfResult) -> String {
        .join(",");
    let ocr_reasons = format_ocr_reasons_by_page(&result.ocr_reasons_by_page);
    format!(
-        r#"{{"schema_version":1,"page_count":{},"processing_time_ms":{},"render_time_ms":{},"ocr_time_ms":{},"pages_recommended_for_ocr":[{}],"pages_routed_to_ocr":[{}],"pages_recommending_hosted":[{}],"ocr_reasons_by_page":[{}],"is_complex":{},"pages_with_tables":[{}],"pages_with_columns":[{}],"pages":[{}],"markdown":"{}"}}"#,
+        r#"{{"page_count":{},"processing_time_ms":{},"render_time_ms":{},"ocr_time_ms":{},"pages_recommended_for_ocr":[{}],"pages_routed_to_ocr":[{}],"pages_recommending_hosted":[{}],"ocr_reasons_by_page":[{}],"is_complex":{},"pages_with_tables":[{}],"pages_with_columns":[{}],"pages":[{}],"markdown":"{}"}}"#,
        result.page_count,
        result.processing_time_ms,
        result.render_time_ms,
@@ -223,19 +224,6 @@ fn argument_value<'a>(args: &'a [String], name: &str) -> Result<Option<&'a str>,
        .transpose()
 }

-fn format_ocr_error_json(error: &str) -> String {
-    format!(r#"{{"schema_version":1,"error":"{}"}}"#, json_escape(error))
-}
-
-fn exit_ocr_error(error: &str, json_output: bool) -> ! {
-    if json_output {
-        println!("{}", format_ocr_error_json(error));
-    } else {
-        eprintln!("Error: {error}");
-    }
-    process::exit(1);
-}
-
 #[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
 fn float_argument(args: &[String], name: &str, default: f32) -> Result<f32, String> {
    argument_value(args, name)?
@@ -259,9 +247,7 @@ fn extract_items_json(

 #[cfg(test)]
 mod tests {
-    use super::{extract_items_json, format_items_json, format_ocr_error_json};
-    #[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
-    use super::{format_ocr_json, process_pdf_with_ocr, OcrPdfOptions};
+    use super::{extract_items_json, format_items_json};
    use pdf_inspector::extractor::ItemType;
    use pdf_inspector::TextItem;

@@ -311,27 +297,6 @@ mod tests {
            "decrypted item JSON should contain fixture text, got {json}"
        );
    }
-
-    #[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
-    #[test]
-    fn ocr_json_has_a_versioned_stable_envelope() {
-        let result =
-            process_pdf_with_ocr("tests/fixtures/thermo-freon12.pdf", OcrPdfOptions::new())
-                .unwrap();
-        let json = format_ocr_json(&result);
-
-        assert!(json.starts_with(r#"{"schema_version":1,"page_count":3,"#));
-        assert!(json.contains(r#""page":1,"source":"native""#));
-        assert!(!json.contains("layout_ms"));
-    }
-
-    #[test]
-    fn ocr_json_errors_use_the_same_versioned_envelope() {
-        assert_eq!(
-            format_ocr_error_json("bad \"value\""),
-            r#"{"schema_version":1,"error":"bad \"value\""}"#
-        );
-    }
 }

 /// Parse a page specification like "1,3,5-10,20" into a HashSet of page numbers.
@@ -476,27 +441,23 @@ fn main() {
    .iter()
    .any(|option| args.iter().any(|argument| argument == option));
    if ocr_mode_argument.is_none() && has_ocr_only_option {
-        exit_ocr_error(
-            "OCR options require --ocr off, --ocr auto, or --ocr force",
-            json_output,
-        );
+        eprintln!("Error: OCR options require --ocr off, --ocr auto, or --ocr force");
+        process::exit(1);
    }

    if let Some(mode) = ocr_mode_argument {
        if items_json_output || detect_only || analyze {
-            exit_ocr_error(
-                "--ocr cannot be combined with --items-json, --detect-only, or --analyze",
-                json_output,
+            eprintln!(
+                "Error: --ocr cannot be combined with --items-json, --detect-only, or --analyze"
            );
+            process::exit(1);
        }

        #[cfg(not(all(feature = "ocr", not(target_arch = "wasm32"))))]
        {
            let _ = mode;
-            exit_ocr_error(
-                "this pdf2md build does not include OCR; rebuild with --features ocr",
-                json_output,
-            );
+            eprintln!("Error: this pdf2md build does not include OCR; rebuild with --features ocr");
+            process::exit(1);
        }

        #[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
@@ -506,26 +467,28 @@ fn main() {
                "auto" => OcrMode::Auto,
                "force" => OcrMode::Force,
                value => {
-                    exit_ocr_error(
-                        &format!("invalid --ocr mode {value:?}; expected off, auto, or force"),
-                        json_output,
-                    );
+                    eprintln!("Error: invalid --ocr mode {value:?}; expected off, auto, or force");
+                    process::exit(1);
                }
            };
            let dpi = float_argument(&args, "--ocr-dpi", 150.0).unwrap_or_else(|error| {
-                exit_ocr_error(&error, json_output);
+                eprintln!("Error: {error}");
+                process::exit(1);
            });
            let minimum_confidence = float_argument(&args, "--ocr-min-confidence", 0.0)
                .unwrap_or_else(|error| {
-                    exit_ocr_error(&error, json_output);
+                    eprintln!("Error: {error}");
+                    process::exit(1);
                });
            let hosted_threshold = float_argument(&args, "--ocr-hosted-threshold", 0.5)
                .unwrap_or_else(|error| {
-                    exit_ocr_error(&error, json_output);
+                    eprintln!("Error: {error}");
+                    process::exit(1);
                });
            let model_directory =
                argument_value(&args, "--ocr-model-dir").unwrap_or_else(|error| {
-                    exit_ocr_error(&error, json_output);
+                    eprintln!("Error: {error}");
+                    process::exit(1);
                });

            let mut ocr = OcrOptions::new()
@@ -548,7 +511,7 @@ fn main() {
                .markdown(markdown)
                .hosted_recommendation_confidence(hosted_threshold);
            if let Some(pages) = page_filter.clone() {
-                pdf_options = pdf_options.page_numbers(pages);
+                pdf_options = pdf_options.pages(pages);
            }
            if let Some(password) = password.clone() {
                pdf_options = pdf_options.password(password);
@@ -586,7 +549,12 @@ fn main() {
                    }
                }
                Err(error) => {
-                    exit_ocr_error(&error.to_string(), json_output);
+                    if json_output {
+                        println!(r#"{{"error":"{}"}}"#, json_escape(&error.to_string()));
+                    } else {
+                        eprintln!("Error: {error}");
+                    }
+                    process::exit(1);
                }
            }
            return;
@@ -561,11 +561,7 @@ pub(crate) fn extract_page_text_items(
                                y,
                                width,
                                height: rendered_size,
-                                font: crate::extractor::fonts::item_font_name(
-                                    &current_font,
-                                    base_font,
-                                )
-                                .to_string(),
+                                font: current_font.clone(),
                                font_size: rendered_size,
                                page: page_num,
                                is_bold: is_bold_font(base_font) || desc_bold,
@@ -749,11 +745,7 @@ pub(crate) fn extract_page_text_items(
                                    y,
                                    width,
                                    height: rendered_size,
-                                    font: crate::extractor::fonts::item_font_name(
-                                        &current_font,
-                                        base_font,
-                                    )
-                                    .to_string(),
+                                    font: current_font.clone(),
                                    font_size: rendered_size,
                                    page: page_num,
                                    is_bold: is_bold_font(base_font) || desc_bold,
@@ -860,11 +852,7 @@ pub(crate) fn extract_page_text_items(
                                y,
                                width,
                                height: rendered_size,
-                                font: crate::extractor::fonts::item_font_name(
-                                    &current_font,
-                                    base_font,
-                                )
-                                .to_string(),
+                                font: current_font.clone(),
                                font_size: rendered_size,
                                page: page_num,
                                is_bold: is_bold_font(base_font) || desc_bold,
@@ -1017,11 +1005,7 @@ pub(crate) fn extract_page_text_items(
                                    y,
                                    width,
                                    height: rendered_size,
-                                    font: crate::extractor::fonts::item_font_name(
-                                        &current_font,
-                                        base_font,
-                                    )
-                                    .to_string(),
+                                    font: current_font.clone(),
                                    font_size: rendered_size,
                                    page: page_num,
                                    is_bold: is_bold_font(base_font) || desc_bold,
@@ -225,26 +225,6 @@ pub(crate) fn build_type3_scales(
    scales
 }

-/// The name a `TextItem` carries for its font: the `/BaseFont` family name
-/// ("ABCDEF+CMMI10"), which identifies the actual face, rather than the
-/// arbitrary per-page resource tag ("F2").
-///
-/// Exception: resource names using Distiller's CID convention (`C2_0`,
-/// `C0_1`) are kept as-is — `text_utils::is_cid_font` keys on that prefix
-/// for micro-gap joining, and the family name carries no CID marker to
-/// replace it. This is a known, deliberate wart: `TextItem::font` is the
-/// face name except for this one producer convention. The clean fix is an
-/// explicit CID flag on `TextItem`, which touches its ~29 construction
-/// sites; do that migration when `TextItem` next changes shape, and delete
-/// this carve-out with it.
-pub(crate) fn item_font_name<'a>(resource_name: &'a str, base_font: &'a str) -> &'a str {
-    if crate::text_utils::is_cid_font(resource_name) {
-        resource_name
-    } else {
-        base_font
-    }
-}
-
 /// Parse font widths from a font dictionary, dispatching by Subtype
 pub(crate) fn parse_font_widths(
    doc: &Document,
@@ -1684,17 +1664,6 @@ fn score_text(text: &str) -> i32 {
 #[cfg(test)]
 mod tests {

-    #[test]
-    fn item_font_name_prefers_family_over_resource_tag() {
-        use super::item_font_name;
-        assert_eq!(item_font_name("F2", "ABCDEF+CMMI10"), "ABCDEF+CMMI10");
-        assert_eq!(item_font_name("T22", "Times-Roman"), "Times-Roman");
-        // Distiller CID-convention resources keep the resource name:
-        // is_cid_font keys on the C2_/C0_ prefix for micro-gap joining.
-        assert_eq!(item_font_name("C2_0", "ABCDEE+SimSun"), "C2_0");
-        assert_eq!(item_font_name("C0_1", "ABCDEE+MSMincho"), "C0_1");
-    }
-
    #[test]
    fn type3_scale_resolves_indirect_matrix_and_bbox_numbers() {
        use lopdf::{dictionary, Document, Object};
@@ -620,11 +620,7 @@ fn extract_form_xobject_text_inner(
                                y,
                                width,
                                height: rendered_size,
-                                font: crate::extractor::fonts::item_font_name(
-                                    &current_font,
-                                    base_font,
-                                )
-                                .to_string(),
+                                font: current_font.clone(),
                                font_size: rendered_size,
                                page: page_num,
                                is_bold: is_bold_font(base_font) || desc_bold,
@@ -779,11 +775,7 @@ fn extract_form_xobject_text_inner(
                                    y,
                                    width,
                                    height: rendered_size,
-                                    font: crate::extractor::fonts::item_font_name(
-                                        &current_font,
-                                        base_font,
-                                    )
-                                    .to_string(),
+                                    font: current_font.clone(),
                                    font_size: rendered_size,
                                    page: page_num,
                                    is_bold: is_bold_font(base_font) || desc_bold,
@@ -203,42 +203,9 @@ pub(crate) fn is_code_like(text: &str) -> bool {
    false
 }

-/// True when a line's text is essentially all monospace (≥90% by character
-/// count). Code lines are wholly monospace; anything less is prose carrying
-/// mono-styled fragments — a URL sidebar, or a sentence quoting an inline
-/// code literal — and fencing it would split paragraphs mid-sentence.
-/// Any-item matching was safe only while items carried opaque font resource
-/// names that never matched the monospace patterns; items now carry real
-/// family names.
-pub(crate) fn line_is_monospace(line: &crate::types::TextLine) -> bool {
-    let mut monospace_chars = 0usize;
-    let mut total_chars = 0usize;
-    for item in &line.items {
-        let text = item.text.trim();
-        let chars = text.chars().count();
-        total_chars += chars;
-        // Hyperlinks and underlined text set in a mono face are link
-        // styling, not code — a URL sidebar must not fence lyric lines.
-        let looks_like_link = item.is_underline
-            || matches!(item.item_type, crate::types::ItemType::Link(_))
-            || text.contains("://")
-            || text.starts_with("www.");
-        if is_monospace_font(&item.font) && !looks_like_link {
-            monospace_chars += chars;
-        }
-    }
-    total_chars > 0 && monospace_chars * 10 >= total_chars * 9
-}
-
 /// Check if font name indicates monospace
 pub(crate) fn is_monospace_font(font_name: &str) -> bool {
    let lower = font_name.to_lowercase();
-    // "Monotype" is a foundry prefix on proportional faces (Monotype
-    // Corsiva, Monotype Garamond) — it must not satisfy the generic "mono"
-    // token below.
-    if lower.contains("monotype") {
-        return false;
-    }
    let patterns = [
        "courier",
        "consolas",
@@ -263,17 +230,6 @@ pub(crate) fn is_monospace_font(font_name: &str) -> bool {
 mod tests {
    use super::*;

-    #[test]
-    fn monotype_foundry_faces_are_not_monospace() {
-        // "Monotype" is a foundry prefix on proportional faces; the generic
-        // "mono" token must not classify them as code fonts.
-        assert!(!is_monospace_font("MonotypeCorsiva"));
-        assert!(!is_monospace_font("ABCDEF+Monotype-Garamond"));
-        assert!(is_monospace_font("RobotoMono-Regular"));
-        assert!(is_monospace_font("PTMono"));
-        assert!(is_monospace_font("Courier"));
-    }
-
    #[test]
    fn format_list_item_plain_bullet() {
        assert_eq!(format_list_item("● Item"), "- Item");
@@ -11,7 +11,9 @@ use super::analysis::{
    detect_header_level, font_size_rarity, has_dot_leaders, is_heading_fragment, is_toc_entry_line,
    is_toc_marker_heading,
 };
-use super::classify::{format_list_item, is_caption_line, is_list_item, starts_with_bullet_marker};
+use super::classify::{
+    format_list_item, is_caption_line, is_list_item, is_monospace_font, starts_with_bullet_marker,
+};
 use super::heading::classify_heading_sequences;
 use super::postprocess::clean_markdown;
 use super::preprocess::{merge_drop_caps, merge_heading_lines};
@@ -769,27 +771,7 @@ pub(super) fn to_markdown_from_lines_with_tables_and_images(
    let mut in_list = false;
    let mut in_paragraph = false;
    let mut last_list_x: Option<f32> = None;
-    // Code lines accumulate here and the fence is emitted only when the
-    // block flushes with content — an empty ``` ``` pair can never appear.
-    fn flush_code_block(output: &mut String, pending_code: &mut String) {
-        let trimmed = pending_code.trim();
-        // A fragment too short to be code — a lone ® or stray glyph set in
-        // a mono face — reads better as plain text than as a fenced block.
-        if trimmed.chars().count() < 3 {
-            if !trimmed.is_empty() {
-                output.push_str(trimmed);
-                output.push_str("\n\n");
-            }
-        } else {
-            output.push_str("```\n");
-            output.push_str(pending_code);
-            output.push_str("```\n");
-        }
-        pending_code.clear();
-    }
-
    let mut in_code_block = false;
-    let mut pending_code = String::new();
    let mut prev_had_dot_leaders = false;
    let mut paragraph_in_wrapped_bold_run = false;
    let mut toc_suppress_page: Option<u32> = None;
@@ -823,7 +805,7 @@ pub(super) fn to_markdown_from_lines_with_tables_and_images(
            // Flush current page's remaining tables and images
            if current_page > 0 {
                if in_code_block {
-                    flush_code_block(&mut output, &mut pending_code);
+                    output.push_str("```\n");
                    in_code_block = false;
                }
                flush_page_tables_and_images(
@@ -885,14 +867,6 @@ pub(super) fn to_markdown_from_lines_with_tables_and_images(
                    PositionedBlockKind::Image => inserted_images.contains(&(current_page, idx)),
                };
                if positioned_block_precedes_line(block, line) && !already_inserted {
-                    // Code lines buffer until their block closes; flush them
-                    // first so this block cannot jump ahead of code that
-                    // precedes it in reading order. A code line after the
-                    // block reopens a new fence naturally.
-                    if in_code_block {
-                        flush_code_block(&mut output, &mut pending_code);
-                        in_code_block = false;
-                    }
                    if in_paragraph {
                        output.push_str("\n\n");
                        in_paragraph = false;
@@ -963,22 +937,15 @@ pub(super) fn to_markdown_from_lines_with_tables_and_images(
        // These should be on their own line followed by a paragraph break
        let struct_role = struct_roles.and_then(|roles| resolve_line_struct_role(line, roles));

-        // Determine if this line is code (struct-tree or font-based) for
-        // block accumulation. Font-based detection only opens a block at a
-        // paragraph boundary: a mono-set line that continues an open prose
-        // paragraph is the producer smearing an inline code literal's style
-        // across a wrapped line (HTML-to-PDF exports do this), and fencing
-        // it would cut the sentence in three.
+        // Determine if this line is code (struct-tree or font-based) for block accumulation
        let is_code_line = struct_role
            .as_ref()
            .is_some_and(|r| matches!(r, StructRole::Code))
-            || (options.detect_code
-                && (in_code_block || !in_paragraph)
-                && super::classify::line_is_monospace(line));
+            || (options.detect_code && line.items.iter().any(|i| is_monospace_font(&i.font)));

        // Close code block when transitioning to non-code
        if in_code_block && !is_code_line {
-            flush_code_block(&mut output, &mut pending_code);
+            output.push_str("```\n");
            in_code_block = false;
        }

@@ -1212,9 +1179,12 @@ pub(super) fn to_markdown_from_lines_with_tables_and_images(
                in_paragraph = false;
                paragraph_in_wrapped_bold_run = false;
            }
-            in_code_block = true;
-            pending_code.push_str(plain_trimmed);
-            pending_code.push('\n');
+            if !in_code_block {
+                output.push_str("```\n");
+                in_code_block = true;
+            }
+            output.push_str(plain_trimmed);
+            output.push('\n');
            continue;
        }

@@ -1239,7 +1209,7 @@ pub(super) fn to_markdown_from_lines_with_tables_and_images(

    // Close any trailing code block
    if in_code_block {
-        flush_code_block(&mut output, &mut pending_code);
+        output.push_str("```\n");
    }

    // Flush current page and any remaining pages with tables/images
@@ -1400,7 +1370,7 @@ pub fn to_markdown_from_lines(lines: Vec<TextLine>, options: MarkdownOptions) ->
            && !is_toc_entry_line(plain_trimmed)
            && !is_heading_fragment(plain_trimmed)
            && toc_suppress_page != Some(line.page)
-            && !(options.detect_code && super::classify::line_is_monospace(line))
+            && !(options.detect_code && line.items.iter().any(|i| is_monospace_font(&i.font)))
        {
            let line_font_size = line.items.first().map(|i| i.font_size).unwrap_or(base_size);
            if let Some(header_level) = detect_header_level(
@@ -1501,13 +1471,19 @@ pub fn to_markdown_from_lines(lines: Vec<TextLine>, options: MarkdownOptions) ->
            }
        }

-        // Detect code blocks by font. Only at a paragraph boundary — a
-        // mono-set line continuing an open prose paragraph is an inline
-        // code literal's style smeared across a wrapped line, not code.
-        if options.detect_code && !in_paragraph && super::classify::line_is_monospace(line) {
-            // Use plain text for code blocks
-            output.push_str(&format!("```\n{}\n```\n", plain_trimmed));
-            continue;
+        // Detect code blocks by font
+        if options.detect_code {
+            let is_mono = line.items.iter().any(|i| is_monospace_font(&i.font));
+            if is_mono {
+                if in_paragraph {
+                    output.push_str("\n\n");
+                    in_paragraph = false;
+                    paragraph_in_wrapped_bold_run = false;
+                }
+                // Use plain text for code blocks
+                output.push_str(&format!("```\n{}\n```\n", plain_trimmed));
+                continue;
+            }
        }

        // Regular text - join lines within same paragraph with space
@@ -85,107 +85,6 @@ impl PyPageOcrReasons {
    }
 }

-/// Exact OCR model identity retained in page provenance.
-#[pyclass(name = "OcrModelIdentity")]
-#[derive(Clone)]
-pub struct PyOcrModelIdentity {
-    #[pyo3(get)]
-    pub name: String,
-    #[pyo3(get)]
-    pub revision: String,
-}
-
-/// Per-page OCR processing timings.
-#[pyclass(name = "OcrTimings")]
-#[derive(Clone)]
-pub struct PyOcrTimings {
-    #[pyo3(get)]
-    pub render_ms: u64,
-    #[pyo3(get)]
-    pub ocr_ms: u64,
-    #[pyo3(get)]
-    pub assembly_ms: u64,
-}
-
-/// Source, model, confidence, and fallback metadata for one page.
-#[pyclass(name = "OcrPageProvenance")]
-#[derive(Clone)]
-pub struct PyOcrPageProvenance {
-    /// 1-indexed page number.
-    #[pyo3(get)]
-    pub page_number: u32,
-    /// "native", "ocr", or "fused".
-    #[pyo3(get)]
-    pub source: String,
-    #[pyo3(get)]
-    pub ocr_model: Option<PyOcrModelIdentity>,
-    #[pyo3(get)]
-    pub render_dpi: Option<f32>,
-    #[pyo3(get)]
-    pub ocr_confidence: Option<f32>,
-    #[pyo3(get)]
-    pub timings: PyOcrTimings,
-    #[pyo3(get)]
-    pub warnings: Vec<String>,
-    #[pyo3(get)]
-    pub hosted_recommended: bool,
-}
-
-/// Final Markdown and provenance for one page.
-#[pyclass(name = "OcrPageResult")]
-#[derive(Clone)]
-pub struct PyOcrPageResult {
-    /// 1-indexed page number.
-    #[pyo3(get)]
-    pub page_number: u32,
-    #[pyo3(get)]
-    pub markdown: String,
-    #[pyo3(get)]
-    pub provenance: PyOcrPageProvenance,
-}
-
-/// Complete native/OCR Markdown output.
-#[pyclass(name = "OcrPdfResult")]
-#[derive(Clone)]
-pub struct PyOcrPdfResult {
-    #[pyo3(get)]
-    pub markdown: String,
-    #[pyo3(get)]
-    pub pages: Vec<PyOcrPageResult>,
-    #[pyo3(get)]
-    pub page_count: u32,
-    #[pyo3(get)]
-    pub pages_recommended_for_ocr: Vec<u32>,
-    #[pyo3(get)]
-    pub pages_routed_to_ocr: Vec<u32>,
-    #[pyo3(get)]
-    pub pages_recommending_hosted: Vec<u32>,
-    #[pyo3(get)]
-    pub ocr_reasons_by_page: Vec<PyPageOcrReasons>,
-    #[pyo3(get)]
-    pub pages_with_tables: Vec<u32>,
-    #[pyo3(get)]
-    pub pages_with_columns: Vec<u32>,
-    #[pyo3(get)]
-    pub is_complex: bool,
-    #[pyo3(get)]
-    pub processing_time_ms: u64,
-    #[pyo3(get)]
-    pub render_time_ms: u64,
-    #[pyo3(get)]
-    pub ocr_time_ms: u64,
-}
-
-#[pymethods]
-impl PyOcrPdfResult {
-    fn __repr__(&self) -> String {
-        format!(
-            "OcrPdfResult(pages={}, routed_to_ocr={:?}, recommending_hosted={:?})",
-            self.page_count, self.pages_routed_to_ocr, self.pages_recommending_hosted
-        )
-    }
-}
-
 // ---------------------------------------------------------------------------
 // Classification wrapper (lightweight)
 // ---------------------------------------------------------------------------
@@ -463,101 +362,6 @@ fn to_py_err(e: crate::PdfError) -> PyErr {
    PyValueError::new_err(e.to_string())
 }

-struct PythonOcrOptions {
-    mode: String,
-    page_numbers: Option<Vec<u32>>,
-    password: Option<String>,
-    dpi: f32,
-    minimum_confidence: f32,
-    hosted_recommendation_confidence: f32,
-    model_directory: Option<String>,
-    offline: bool,
-}
-
-fn build_ocr_options(binding: PythonOcrOptions) -> PyResult<crate::vision::OcrPdfOptions> {
-    let mode = match binding.mode.trim().to_ascii_lowercase().as_str() {
-        "off" => crate::vision::OcrMode::Off,
-        "auto" => crate::vision::OcrMode::Auto,
-        "force" => crate::vision::OcrMode::Force,
-        _ => {
-            return Err(PyValueError::new_err(
-                "mode must be 'off', 'auto', or 'force'",
-            ));
-        }
-    };
-
-    let mut options = crate::vision::OcrPdfOptions::new().mode(mode);
-    options.render.dpi = binding.dpi;
-    options.ocr.minimum_confidence = binding.minimum_confidence;
-    options.hosted_recommendation_confidence = binding.hosted_recommendation_confidence;
-    if let Some(pages) = binding.page_numbers {
-        options = options.page_numbers(pages);
-    }
-    if let Some(password) = binding.password {
-        options = options.password(password);
-    }
-    if let Some(directory) = binding.model_directory {
-        options.ocr.model_directory = Some(directory.into());
-    }
-    if binding.offline {
-        options.ocr.model_downloads = crate::vision::ModelDownloadPolicy::Offline;
-    }
-    Ok(options)
-}
-
-fn page_content_source_str(source: crate::vision::PageContentSource) -> String {
-    match source {
-        crate::vision::PageContentSource::Native => "native".into(),
-        crate::vision::PageContentSource::Ocr => "ocr".into(),
-        crate::vision::PageContentSource::Fused => "fused".into(),
-    }
-}
-
-fn to_py_ocr_result(result: crate::vision::OcrPdfResult) -> PyOcrPdfResult {
-    PyOcrPdfResult {
-        markdown: result.markdown,
-        pages: result
-            .pages
-            .into_iter()
-            .map(|page| {
-                let provenance = page.provenance;
-                PyOcrPageResult {
-                    page_number: page.page_number,
-                    markdown: page.markdown,
-                    provenance: PyOcrPageProvenance {
-                        page_number: provenance.page_number,
-                        source: page_content_source_str(provenance.source),
-                        ocr_model: provenance.ocr_model.map(|model| PyOcrModelIdentity {
-                            name: model.name,
-                            revision: model.revision,
-                        }),
-                        render_dpi: provenance.render_dpi,
-                        ocr_confidence: provenance.ocr_confidence,
-                        timings: PyOcrTimings {
-                            render_ms: provenance.timings.render_ms,
-                            ocr_ms: provenance.timings.ocr_ms,
-                            assembly_ms: provenance.timings.assembly_ms,
-                        },
-                        warnings: provenance.warnings,
-                        hosted_recommended: provenance.hosted_recommended,
-                    },
-                }
-            })
-            .collect(),
-        page_count: result.page_count,
-        pages_recommended_for_ocr: result.pages_recommended_for_ocr,
-        pages_routed_to_ocr: result.pages_routed_to_ocr,
-        pages_recommending_hosted: result.pages_recommending_hosted,
-        ocr_reasons_by_page: to_py_page_ocr_reasons(result.ocr_reasons_by_page),
-        pages_with_tables: result.pages_with_tables,
-        pages_with_columns: result.pages_with_columns,
-        is_complex: result.is_complex,
-        processing_time_ms: result.processing_time_ms,
-        render_time_ms: result.render_time_ms,
-        ocr_time_ms: result.ocr_time_ms,
-    }
-}
-
 fn item_type_str(t: &ItemType) -> String {
    match t {
        ItemType::Text => "text".into(),
@@ -698,99 +502,6 @@ fn process_pdf_bytes(data: &[u8], pages: Option<Vec<u32>>) -> PyResult<PyPdfResu
    Ok(to_py_result(result))
 }

-/// Process a PDF file through native extraction and selective OCR.
-///
-/// OCR defaults to ``auto`` and only initializes its external runtime and
-/// model when native quality signals route at least one page. Page numbers
-/// are 1-indexed. The GIL is released for the complete processing call.
-#[pyfunction]
-#[pyo3(signature = (
-    path,
-    *,
-    mode="auto",
-    page_numbers=None,
-    password=None,
-    dpi=150.0,
-    minimum_confidence=0.0,
-    hosted_recommendation_confidence=0.5,
-    model_directory=None,
-    offline=false
-))]
-#[allow(clippy::too_many_arguments)]
-fn process_pdf_with_ocr(
-    py: Python<'_>,
-    path: String,
-    mode: &str,
-    page_numbers: Option<Vec<u32>>,
-    password: Option<String>,
-    dpi: f32,
-    minimum_confidence: f32,
-    hosted_recommendation_confidence: f32,
-    model_directory: Option<String>,
-    offline: bool,
-) -> PyResult<PyOcrPdfResult> {
-    let options = build_ocr_options(PythonOcrOptions {
-        mode: mode.to_string(),
-        page_numbers,
-        password,
-        dpi,
-        minimum_confidence,
-        hosted_recommendation_confidence,
-        model_directory,
-        offline,
-    })?;
-    let result = py
-        .allow_threads(move || crate::vision::process_pdf_with_ocr(path, options))
-        .map_err(|error| PyValueError::new_err(error.to_string()))?;
-    Ok(to_py_ocr_result(result))
-}
-
-/// Process PDF bytes through native extraction and selective OCR.
-///
-/// See [`process_pdf_with_ocr`] for options and result semantics.
-#[pyfunction]
-#[pyo3(signature = (
-    data,
-    *,
-    mode="auto",
-    page_numbers=None,
-    password=None,
-    dpi=150.0,
-    minimum_confidence=0.0,
-    hosted_recommendation_confidence=0.5,
-    model_directory=None,
-    offline=false
-))]
-#[allow(clippy::too_many_arguments)]
-fn process_pdf_with_ocr_bytes(
-    py: Python<'_>,
-    data: &[u8],
-    mode: &str,
-    page_numbers: Option<Vec<u32>>,
-    password: Option<String>,
-    dpi: f32,
-    minimum_confidence: f32,
-    hosted_recommendation_confidence: f32,
-    model_directory: Option<String>,
-    offline: bool,
-) -> PyResult<PyOcrPdfResult> {
-    let options = build_ocr_options(PythonOcrOptions {
-        mode: mode.to_string(),
-        page_numbers,
-        password,
-        dpi,
-        minimum_confidence,
-        hosted_recommendation_confidence,
-        model_directory,
-        offline,
-    })?;
-    let data = data.to_vec();
-    let result = py
-        .allow_threads(move || crate::vision::process_pdf_with_ocr_mem(&data, options))
-        .map_err(|error| PyValueError::new_err(error.to_string()))?;
-    Ok(to_py_ocr_result(result))
-}
-
 /// Fast detection only — no text extraction or markdown.
 #[pyfunction]
 fn detect_pdf(path: &str) -> PyResult<PyPdfResult> {
@@ -993,11 +704,6 @@ fn extract_structure_elements_bytes(
 fn pdf_inspector(m: &Bound<'_, PyModule>) -> PyResult<()> {
    m.add_class::<PyPdfResult>()?;
    m.add_class::<PyPageOcrReasons>()?;
-    m.add_class::<PyOcrModelIdentity>()?;
-    m.add_class::<PyOcrTimings>()?;
-    m.add_class::<PyOcrPageProvenance>()?;
-    m.add_class::<PyOcrPageResult>()?;
-    m.add_class::<PyOcrPdfResult>()?;
    m.add_class::<PyPdfClassification>()?;
    m.add_class::<PyTextItem>()?;
    m.add_class::<PyStructureElement>()?;
@@ -1007,8 +713,6 @@ fn pdf_inspector(m: &Bound<'_, PyModule>) -> PyResult<()> {
    m.add_class::<PyPagesExtractionResult>()?;
    m.add_function(wrap_pyfunction!(process_pdf, m)?)?;
    m.add_function(wrap_pyfunction!(process_pdf_bytes, m)?)?;
-    m.add_function(wrap_pyfunction!(process_pdf_with_ocr, m)?)?;
-    m.add_function(wrap_pyfunction!(process_pdf_with_ocr_bytes, m)?)?;
    m.add_function(wrap_pyfunction!(detect_pdf, m)?)?;
    m.add_function(wrap_pyfunction!(detect_pdf_bytes, m)?)?;
    m.add_function(wrap_pyfunction!(classify_pdf, m)?)?;
@@ -1,4 +1,4 @@
-//! Public contracts between rendering, OCR, and orchestration.
+//! Public contracts between rendering, OCR, layout, and orchestration.

 use std::error::Error;
 use std::path::PathBuf;
@@ -18,6 +18,19 @@ pub enum OcrMode {
    Force,
 }

+/// Resource/quality profile for the OCR engine.
+#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
+#[non_exhaustive]
+pub enum OcrProfile {
+    /// Lowest latency and memory footprint.
+    Edge,
+    /// OCR-oriented balance of quality and CPU cost.
+    #[default]
+    Balanced,
+    /// Highest quality within the lightweight model family.
+    Quality,
+}
+
 /// Controls whether missing model artifacts may be fetched.
 #[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
 #[non_exhaustive]
@@ -34,8 +47,12 @@ pub enum ModelDownloadPolicy {
 pub struct OcrOptions {
    /// Page-level routing behavior.
    pub mode: OcrMode,
+    /// Local quality/resource profile.
+    pub profile: OcrProfile,
    /// Drop recognition spans below this confidence threshold.
    pub minimum_confidence: f32,
+    /// Optional language hints understood by the selected engine.
+    pub languages: Vec<String>,
    /// Optional directory containing an offline model set.
    pub model_directory: Option<PathBuf>,
    /// Whether a missing pinned artifact may be downloaded.
@@ -46,7 +63,9 @@ impl Default for OcrOptions {
    fn default() -> Self {
        Self {
            mode: OcrMode::Off,
+            profile: OcrProfile::Balanced,
            minimum_confidence: 0.0,
+            languages: Vec::new(),
            model_directory: None,
            model_downloads: ModelDownloadPolicy::IfMissing,
        }
@@ -65,12 +84,24 @@ impl OcrOptions {
        self
    }

+    /// Sets the local resource/quality profile.
+    pub fn profile(mut self, profile: OcrProfile) -> Self {
+        self.profile = profile;
+        self
+    }
+
    /// Sets the minimum accepted recognition confidence.
    pub fn minimum_confidence(mut self, minimum_confidence: f32) -> Self {
        self.minimum_confidence = minimum_confidence;
        self
    }

+    /// Replaces the language hints passed to the OCR engine.
+    pub fn languages(mut self, languages: impl IntoIterator<Item = impl Into<String>>) -> Self {
+        self.languages = languages.into_iter().map(Into::into).collect();
+        self
+    }
+
    /// Uses an explicit model directory, suitable for offline packaging.
    pub fn model_directory(mut self, directory: impl Into<PathBuf>) -> Self {
        self.model_directory = Some(directory.into());
@@ -84,6 +115,55 @@ impl OcrOptions {
    }
 }

+/// Configuration for an optional learned layout engine.
+///
+/// Layout inference is disabled by default. Existing deterministic layout,
+/// table, and Markdown logic remains the assembly path when this is disabled.
+#[derive(Debug, Clone, PartialEq)]
+pub struct LayoutOptions {
+    /// Whether the learned layout extension may run.
+    pub enabled: bool,
+    /// Drop layout regions below this confidence threshold.
+    pub minimum_confidence: f32,
+    /// Optional directory containing an offline layout model set.
+    pub model_directory: Option<PathBuf>,
+}
+
+impl Default for LayoutOptions {
+    fn default() -> Self {
+        Self {
+            enabled: false,
+            minimum_confidence: 0.0,
+            model_directory: None,
+        }
+    }
+}
+
+impl LayoutOptions {
+    /// Creates layout options with learned layout disabled.
+    pub fn new() -> Self {
+        Self::default()
+    }
+
+    /// Enables or disables learned layout inference.
+    pub fn enabled(mut self, enabled: bool) -> Self {
+        self.enabled = enabled;
+        self
+    }
+
+    /// Sets the minimum accepted region confidence.
+    pub fn minimum_confidence(mut self, minimum_confidence: f32) -> Self {
+        self.minimum_confidence = minimum_confidence;
+        self
+    }
+
+    /// Uses an explicit layout model directory.
+    pub fn model_directory(mut self, directory: impl Into<PathBuf>) -> Self {
+        self.model_directory = Some(directory.into());
+        self
+    }
+}
+
 /// A point in bitmap space, measured from the top-left in pixels.
 #[derive(Debug, Clone, Copy, Default, PartialEq)]
 pub struct ImagePoint {
@@ -150,7 +230,7 @@ pub struct OcrSpan {
 #[derive(Debug, Clone, PartialEq)]
 pub struct OcrPage {
    /// 1-indexed PDF page number.
-    pub page_number: u32,
+    pub page: u32,
    /// Positioned recognition spans.
    pub spans: Vec<OcrSpan>,
    /// Mean confidence across accepted spans, when available.
@@ -163,6 +243,54 @@ pub struct OcrPage {
    pub warnings: Vec<String>,
 }

+/// Normalized semantic class emitted by a learned layout engine.
+#[derive(Debug, Clone, PartialEq, Eq)]
+#[non_exhaustive]
+pub enum LayoutRegionKind {
+    /// Body or other prose text.
+    Text,
+    /// Document heading or title.
+    Heading,
+    /// Table region.
+    Table,
+    /// Figure/image region.
+    Figure,
+    /// Figure or table caption.
+    Caption,
+    /// Header/footer/page furniture.
+    Furniture,
+    /// Model-specific class retained without changing the common taxonomy.
+    Other(String),
+}
+
+/// One learned layout region in bitmap coordinates.
+#[derive(Debug, Clone, PartialEq)]
+pub struct LayoutRegion {
+    /// Normalized semantic class.
+    pub kind: LayoutRegionKind,
+    /// Region polygon in the original rendered page's pixel space.
+    pub polygon: ImageQuad,
+    /// Model confidence in the inclusive range 0–1.
+    pub confidence: f32,
+    /// Optional model-provided reading-order position.
+    pub reading_order: Option<u32>,
+}
+
+/// Learned layout output for one 1-indexed page.
+#[derive(Debug, Clone, PartialEq)]
+pub struct LayoutPage {
+    /// 1-indexed PDF page number.
+    pub page: u32,
+    /// Semantic regions.
+    pub regions: Vec<LayoutRegion>,
+    /// Exact model identity used for this result.
+    pub model: ModelIdentity,
+    /// Layout inference wall time for this page.
+    pub processing_time_ms: u64,
+    /// Non-fatal engine warnings.
+    pub warnings: Vec<String>,
+}
+
 /// How final page content was sourced.
 #[derive(Debug, Clone, Copy, PartialEq, Eq)]
 #[non_exhaustive]
@@ -182,6 +310,8 @@ pub struct VisionTimings {
    pub render_ms: u64,
    /// OCR wall time.
    pub ocr_ms: u64,
+    /// Optional learned layout wall time.
+    pub layout_ms: u64,
    /// Native/OCR fusion and assembly wall time.
    pub assembly_ms: u64,
 }
@@ -190,11 +320,13 @@ pub struct VisionTimings {
 #[derive(Debug, Clone, PartialEq)]
 pub struct PageProvenance {
    /// 1-indexed PDF page number.
-    pub page_number: u32,
+    pub page: u32,
    /// Final page-content source.
    pub source: PageContentSource,
    /// OCR model, when OCR ran.
    pub ocr_model: Option<ModelIdentity>,
+    /// Learned layout model, when layout inference ran.
+    pub layout_model: Option<ModelIdentity>,
    /// Render resolution used for local vision.
    pub render_dpi: Option<f32>,
    /// Mean accepted OCR confidence, when available.
@@ -239,6 +371,23 @@ pub trait OcrEngine: Send + Sync {
    ) -> Result<Vec<OcrPage>, Self::Error>;
 }

+/// Optional learned semantic layout extension.
+pub trait LayoutEngine: Send + Sync {
+    /// Engine-specific failure type.
+    type Error: Error + Send + Sync + 'static;
+
+    /// Exact model identity used by this engine instance.
+    fn model(&self) -> &ModelIdentity;
+
+    /// Analyzes rendered pages, optionally using their OCR spans.
+    fn analyze(
+        &self,
+        pages: &[RenderedPage],
+        ocr: &[OcrPage],
+        options: &LayoutOptions,
+    ) -> Result<Vec<LayoutPage>, Self::Error>;
+}
+
 #[cfg(test)]
 mod tests {
    use super::*;
@@ -74,7 +74,7 @@ impl OcrFusionOptions {
 #[derive(Debug, Clone, PartialEq)]
 pub struct FusedPageMarkdown {
    /// 1-indexed document page number, matching OCR and provenance fields.
-    pub page_number: u32,
+    pub page: u32,
    /// Final page Markdown.
    pub markdown: String,
    /// Native/OCR source, model, timing, and fallback metadata.
@@ -184,9 +184,8 @@ pub fn ocr_page_to_markdown(
 /// OCR replaces pages whose native extraction was already rejected. On clean
 /// native pages (for example in `Force` mode), normalized duplicate OCR blocks
 /// are removed and only genuinely additional blocks are appended. Pages that
-/// needed OCR but still have no credible OCR result, or whose confident OCR
-/// only repeats an incomplete native fragment, recommend the hosted document
-/// pipeline instead of silently presenting partial content as final.
+/// needed OCR but still have no credible OCR result recommend the hosted
+/// document pipeline instead of silently presenting an empty result as final.
 pub fn fuse_ocr_pages(
    native_pages: &[PageMarkdown],
    ocr_run: &OcrRun,
@@ -331,12 +330,13 @@ fn fuse_ocr_pages_impl(
            };

        pages.push(FusedPageMarkdown {
-            page_number,
+            page: page_number,
            markdown,
            provenance: PageProvenance {
-                page_number,
+                page: page_number,
                source,
                ocr_model,
+                layout_model: None,
                render_dpi: ocr_by_page
                    .contains_key(&page_number)
                    .then_some(options.render_dpi),
@@ -344,6 +344,7 @@ fn fuse_ocr_pages_impl(
                timings: VisionTimings {
                    render_ms: render_by_page.get(&page_number).copied().unwrap_or(0),
                    ocr_ms,
+                    layout_ms: 0,
                    assembly_ms: elapsed_ms(assembly_started),
                },
                warnings,
@@ -404,11 +405,7 @@ fn choose_adaptive_content(
                "kept trustworthy {} because OCR added no material coverage",
                native.origin.description()
            ),
-            // The candidate exists only because this page was routed with
-            // incomplete native coverage. Agreement between two partial
-            // hypotheses preserves trustworthy text, but does not prove that
-            // the rest of the page was recovered.
-            recommend_hosted: true,
+            recommend_hosted: false,
        };
    }

@@ -1014,7 +1011,7 @@ mod tests {
        RoutedOcrPage {
            rendered: rendered_page(page),
            ocr: OcrPage {
-                page_number: page,
+                page,
                spans,
                mean_confidence: confidence,
                model: ModelIdentity::new("test-ocr", "v1"),
@@ -1069,11 +1066,8 @@ mod tests {
                < result.pages[0].markdown.find("Second").unwrap()
        );
        assert_eq!(result.pages[0].provenance.source, PageContentSource::Ocr);
-        assert_eq!(result.pages[0].page_number, 1);
-        assert_eq!(
-            result.pages[0].page_number,
-            result.pages[0].provenance.page_number
-        );
+        assert_eq!(result.pages[0].page, 1);
+        assert_eq!(result.pages[0].page, result.pages[0].provenance.page);
        assert_eq!(
            result.pages[0].provenance.ocr_model.as_ref().unwrap().name,
            "test-ocr"
@@ -1249,7 +1243,7 @@ mod tests {
                .unwrap();

        assert_eq!(result.pages[0].provenance.source, PageContentSource::Native);
-        assert!(result.pages[0].provenance.hosted_recommended);
+        assert!(!result.pages[0].provenance.hosted_recommended);
        assert_eq!(result.pages[0].markdown.matches("Invoice").count(), 1);
        assert!(result.pages[0].provenance.warnings[0].contains("no material coverage"));
    }
@@ -30,8 +30,9 @@ mod pdfium;

 #[cfg(all(feature = "vision", not(target_arch = "wasm32")))]
 pub use contracts::{
-    ImagePoint, ImageQuad, ModelDownloadPolicy, ModelIdentity, OcrEngine, OcrMode, OcrOptions,
-    OcrPage, OcrSpan, PageContentSource, PageProvenance, PageRenderer, VisionTimings,
+    ImagePoint, ImageQuad, LayoutEngine, LayoutOptions, LayoutPage, LayoutRegion, LayoutRegionKind,
+    ModelDownloadPolicy, ModelIdentity, OcrEngine, OcrMode, OcrOptions, OcrPage, OcrProfile,
+    OcrSpan, PageContentSource, PageProvenance, PageRenderer, VisionTimings,
 };
 #[cfg(all(feature = "model-download", not(target_arch = "wasm32")))]
 pub use download::{HttpModelDownloadError, HttpModelDownloader, DEFAULT_MODEL_DOWNLOAD_TIMEOUT};
@@ -49,9 +49,7 @@ pub enum OarOcrError {
        page: u32,
    },
    /// The external ONNX Runtime shared library could not be loaded.
-    #[error(
-        "failed to load ONNX Runtime from {path}; install a compatible ONNX Runtime shared library or set ORT_DYLIB_PATH to its path: {source}"
-    )]
+    #[error("failed to load ONNX Runtime from {path}: {source}")]
    OnnxRuntimeLoad {
        /// Requested shared-library path or platform library name.
        path: PathBuf,
@@ -145,6 +143,10 @@ impl OarOcrEngine {
        }

        let mut warnings = Vec::new();
+        if !options.languages.is_empty() {
+            warnings
+                .push("language hints are not used by the PP-OCRv6 Small OAR backend".to_string());
+        }
        if missing_recognition > 0 {
            warnings.push(format!(
                "discarded {missing_recognition} regions without usable recognition output"
@@ -164,7 +166,7 @@ impl OarOcrEngine {
        let processing_time_ms = u64::try_from(started.elapsed().as_millis()).unwrap_or(u64::MAX);

        Ok(OcrPage {
-            page_number: page.page(),
+            page: page.page(),
            spans,
            mean_confidence,
            model: self.model.clone(),
@@ -49,15 +49,6 @@ pub enum RenderError {
        /// Number of pages in the document.
        page_count: usize,
    },
-    /// The PDFium shared library could not be discovered or loaded.
-    #[error(
-        "failed to load PDFium; install a compatible PDFium shared library or set PDFIUM_LIB_PATH to its path"
-    )]
-    PdfiumLoad {
-        /// Dynamic loading failure.
-        #[source]
-        source: firecrawl_pdfium::Error,
-    },
    /// PDFium loading, document parsing, form setup, or rendering failed.
    #[error(transparent)]
    Pdfium(#[from] firecrawl_pdfium::Error),
@@ -89,15 +80,14 @@ impl PdfiumRenderer {
    /// Loads PDFium using `firecrawl-pdfium`'s documented discovery chain.
    pub fn load() -> Result<Self, RenderError> {
        Ok(Self {
-            pdfium: Pdfium::load().map_err(|source| RenderError::PdfiumLoad { source })?,
+            pdfium: Pdfium::load()?,
        })
    }

    /// Loads PDFium from an explicit native library path.
    pub fn load_from_path(path: impl AsRef<Path>) -> Result<Self, RenderError> {
        Ok(Self {
-            pdfium: Pdfium::load_from_path(path)
-                .map_err(|source| RenderError::PdfiumLoad { source })?,
+            pdfium: Pdfium::load_from_path(path)?,
        })
    }

@@ -11,7 +11,7 @@ use crate::text_quality::{
    analyze_text_quality, detect_encoding_issues, is_cid_garbage, is_garbage_text,
 };
 use crate::{
-    MarkdownOptions, PageMarkdown, PageOcrReasons, PdfError, OCR_REASON_SUSPECTED_GARBLED_TEXT,
+    MarkdownOptions, PageOcrReasons, PdfError, OCR_REASON_SUSPECTED_GARBLED_TEXT,
    OCR_REASON_VECTOR_TEXT,
 };

@@ -22,15 +22,12 @@ use super::fusion::{
 use super::oar::onnx_runtime_library_path;
 use super::pdfium::PdfiumTextPage;
 use super::{
-    route_ocr_pages, run_ocr_pages, FusedPageMarkdown, FusedPages, HttpModelDownloadError,
-    HttpModelDownloader, ModelAcquireError, ModelStore, ModelStoreError, OarOcrEngine, OarOcrError,
-    OcrEngine, OcrFusionError, OcrFusionOptions, OcrMode, OcrOptions, OcrRoutingError, OcrRun,
-    OcrRunError, PageRenderer, PdfiumRenderer, RenderError, RenderOptions, PP_OCR_V6_SMALL,
+    route_ocr_pages, run_ocr_pages, FusedPageMarkdown, HttpModelDownloadError, HttpModelDownloader,
+    ModelAcquireError, ModelStore, ModelStoreError, OarOcrEngine, OarOcrError, OcrFusionError,
+    OcrFusionOptions, OcrMode, OcrOptions, OcrRoutingError, OcrRun, OcrRunError, PdfiumRenderer,
+    RenderError, RenderOptions, PP_OCR_V6_SMALL,
 };

-/// Bounds live rendered-page memory while preserving small OCR batches.
-const OCR_PAGE_CHUNK_SIZE: usize = 4;
-
 #[derive(Debug, Clone, PartialEq, Eq)]
 struct OcrEngineCacheKey {
    model_root: PathBuf,
@@ -59,13 +56,10 @@ pub struct OcrPdfOptions {
    /// Markdown formatting shared by native and OCR assembly.
    pub markdown: MarkdownOptions,
    /// Optional 1-indexed page selection. `None` processes the full document.
-    pub page_numbers: Option<BTreeSet<u32>>,
+    pub page_filter: Option<BTreeSet<u32>>,
    /// Password for an encrypted PDF.
    pub password: Option<String>,
    /// Weak OCR threshold for recommending the hosted pipeline.
-    ///
-    /// Pages with incomplete native coverage may also recommend the hosted
-    /// pipeline when confident OCR only duplicates the retained fragment.
    pub hosted_recommendation_confidence: f32,
 }

@@ -75,7 +69,7 @@ impl Default for OcrPdfOptions {
            render: RenderOptions::default(),
            ocr: OcrOptions::default(),
            markdown: MarkdownOptions::default(),
-            page_numbers: None,
+            page_filter: None,
            password: None,
            hosted_recommendation_confidence: 0.5,
        }
@@ -89,7 +83,7 @@ impl std::fmt::Debug for OcrPdfOptions {
            .field("render", &self.render)
            .field("ocr", &self.ocr)
            .field("markdown", &self.markdown)
-            .field("page_numbers", &self.page_numbers)
+            .field("page_filter", &self.page_filter)
            .field("password", &self.password.as_ref().map(|_| "[REDACTED]"))
            .field(
                "hosted_recommendation_confidence",
@@ -105,11 +99,6 @@ impl OcrPdfOptions {
        Self::default()
    }

-    /// Creates options with selective OCR enabled for recommended pages.
-    pub fn auto() -> Self {
-        Self::default().mode(OcrMode::Auto)
-    }
-
    /// Replaces page rasterization settings.
    pub fn render(mut self, render: RenderOptions) -> Self {
        self.render = render;
@@ -135,8 +124,8 @@ impl OcrPdfOptions {
    }

    /// Restricts processing to 1-indexed pages in ascending order.
-    pub fn page_numbers(mut self, pages: impl IntoIterator<Item = u32>) -> Self {
-        self.page_numbers = Some(pages.into_iter().collect());
+    pub fn pages(mut self, pages: impl IntoIterator<Item = u32>) -> Self {
+        self.page_filter = Some(pages.into_iter().collect());
        self
    }

@@ -214,7 +203,7 @@ pub fn process_pdf_with_ocr_mem(
        });
    }
    if options
-        .page_numbers
+        .page_filter
        .as_ref()
        .is_some_and(|pages| pages.contains(&0))
    {
@@ -223,7 +212,7 @@ pub fn process_pdf_with_ocr_mem(

    let started = Instant::now();
    let selected_pages: Option<Vec<u32>> = options
-        .page_numbers
+        .page_filter
        .as_ref()
        .map(|pages| pages.iter().copied().collect());
    let selected_pages_zero_indexed: Option<Vec<u32>> = selected_pages
@@ -338,22 +327,12 @@ pub fn process_pdf_with_ocr_mem(
        }
    }

-    let fusion_options = OcrFusionOptions::new()
-        .markdown(page_markdown_options)
-        .render_dpi(options.render.dpi)
-        .hosted_recommendation_confidence(options.hosted_recommendation_confidence);
-    let mut fused = if routed.is_empty() {
-        fuse_ocr_pages_adaptive(
-            &native.pages,
-            &OcrRun {
-                pages: Vec::new(),
-                render_time_ms: 0,
-                ocr_time_ms: 0,
-            },
-            page_count,
-            &fusion_options,
-            &native_candidates,
-        )?
+    let ocr_run = if routed.is_empty() {
+        OcrRun {
+            pages: Vec::new(),
+            render_time_ms: 0,
+            ocr_time_ms: 0,
+        }
    } else {
        // Resolve the native renderer before any network request so a missing
        // PDFium installation cannot trigger a model download it cannot use.
@@ -362,7 +341,7 @@ pub fn process_pdf_with_ocr_mem(
            None => PdfiumRenderer::load()?,
        };
        let engine = cached_ocr_engine(&options.ocr)?;
-        run_and_fuse_ocr_chunks(
+        run_ocr_pages(
            &renderer,
            engine.as_ref(),
            buffer,
@@ -370,14 +349,22 @@ pub fn process_pdf_with_ocr_mem(
            options.password.as_deref(),
            &options.render,
            &options.ocr,
-            &native.pages,
-            page_count,
-            &fusion_options,
-            &native_candidates,
        )?
    };
+
+    let fusion_options = OcrFusionOptions::new()
+        .markdown(page_markdown_options)
+        .render_dpi(options.render.dpi)
+        .hosted_recommendation_confidence(options.hosted_recommendation_confidence);
+    let mut fused = fuse_ocr_pages_adaptive(
+        &native.pages,
+        &ocr_run,
+        page_count,
+        &fusion_options,
+        &native_candidates,
+    )?;
    for page in &mut fused.pages {
-        if recovered_natively.contains(&page.page_number) {
+        if recovered_natively.contains(&page.page) {
            page.provenance
                .warnings
                .push("recovered a credible positioned native text layer before OCR".to_string());
@@ -387,14 +374,14 @@ pub fn process_pdf_with_ocr_mem(
        .pages
        .iter()
        .filter(|page| page.provenance.hosted_recommended)
-        .map(|page| page.provenance.page_number)
+        .map(|page| page.provenance.page)
        .collect();
    let markdown = assemble_document_markdown(&fused.pages, options.markdown.include_page_numbers);

    let mut pages_with_tables = native.pages_with_tables;
    for page in &fused.pages {
-        if markdown_has_table(&page.markdown) && !pages_with_tables.contains(&page.page_number) {
-            pages_with_tables.push(page.page_number);
+        if markdown_has_table(&page.markdown) && !pages_with_tables.contains(&page.page) {
+            pages_with_tables.push(page.page);
        }
    }
    pages_with_tables.sort_unstable();
@@ -416,122 +403,6 @@ pub fn process_pdf_with_ocr_mem(
    })
 }

-#[allow(clippy::too_many_arguments)]
-fn run_and_fuse_ocr_chunks<R, O>(
-    renderer: &R,
-    engine: &O,
-    pdf_bytes: &[u8],
-    routed_pages: &[u32],
-    password: Option<&str>,
-    render_options: &RenderOptions,
-    ocr_options: &OcrOptions,
-    native_pages: &[PageMarkdown],
-    document_page_count: u32,
-    fusion_options: &OcrFusionOptions,
-    native_candidates: &BTreeMap<u32, NativeFallbackCandidate>,
-) -> Result<FusedPages, OcrPipelineError>
-where
-    R: PageRenderer,
-    O: OcrEngine,
-{
-    let routed: BTreeSet<u32> = routed_pages.iter().copied().collect();
-    let native_by_number: BTreeMap<u32, &PageMarkdown> = native_pages
-        .iter()
-        .map(|page| (page.page + 1, page))
-        .collect();
-    let mut pages_by_number = BTreeMap::new();
-    let mut render_time_ms = 0u64;
-    let mut ocr_time_ms = 0u64;
-
-    for chunk in routed_pages.chunks(OCR_PAGE_CHUNK_SIZE) {
-        let native_chunk = chunk
-            .iter()
-            .map(|page_number| {
-                clone_native_page(
-                    native_by_number
-                        .get(page_number)
-                        .copied()
-                        .expect("every routed page has a native page"),
-                )
-            })
-            .collect::<Vec<_>>();
-        let run = run_ocr_pages(
-            renderer,
-            engine,
-            pdf_bytes,
-            chunk,
-            password,
-            render_options,
-            ocr_options,
-        )?;
-        let fused = fuse_ocr_pages_adaptive(
-            &native_chunk,
-            &run,
-            document_page_count,
-            fusion_options,
-            native_candidates,
-        )?;
-        render_time_ms = render_time_ms.saturating_add(fused.render_time_ms);
-        ocr_time_ms = ocr_time_ms.saturating_add(fused.ocr_time_ms);
-        for page in fused.pages {
-            pages_by_number.insert(page.page_number, page);
-        }
-        // `run` and its rendered bitmaps are released before the next chunk.
-    }
-
-    let native_only = select_native_pages(native_pages, |page| !routed.contains(&page));
-    if !native_only.is_empty() {
-        let fused = fuse_ocr_pages_adaptive(
-            &native_only,
-            &OcrRun {
-                pages: Vec::new(),
-                render_time_ms: 0,
-                ocr_time_ms: 0,
-            },
-            document_page_count,
-            fusion_options,
-            native_candidates,
-        )?;
-        for page in fused.pages {
-            pages_by_number.insert(page.page_number, page);
-        }
-    }
-
-    let pages = native_pages
-        .iter()
-        .map(|native| {
-            pages_by_number
-                .remove(&(native.page + 1))
-                .expect("every native page is fused exactly once")
-        })
-        .collect();
-    Ok(FusedPages {
-        pages,
-        render_time_ms,
-        ocr_time_ms,
-    })
-}
-
-fn select_native_pages(
-    native_pages: &[PageMarkdown],
-    include: impl Fn(u32) -> bool,
-) -> Vec<PageMarkdown> {
-    native_pages
-        .iter()
-        .filter(|page| include(page.page + 1))
-        .map(clone_native_page)
-        .collect()
-}
-
-fn clone_native_page(page: &PageMarkdown) -> PageMarkdown {
-    PageMarkdown {
-        page: page.page,
-        markdown: page.markdown.clone(),
-        needs_ocr: page.needs_ocr,
-        ocr_reason: page.ocr_reason.clone(),
-    }
-}
-
 fn cached_ocr_engine(options: &OcrOptions) -> Result<Arc<OarOcrEngine>, OcrPipelineError> {
    let store = ModelStore::from_options(options)?;
    let key = OcrEngineCacheKey {
@@ -806,7 +677,6 @@ fn markdown_has_table(markdown: &str) -> bool {
 fn remove_duplicate_table_lines(markdown: &str) -> String {
    let mut output = String::new();
    let mut adjacent_table_row = None;
-    let mut wide_table_rows = BTreeSet::new();
    for line in markdown.lines() {
        let trimmed = line.trim();
        let is_table_line = trimmed.starts_with('|') && trimmed.ends_with('|');
@@ -814,28 +684,19 @@ fn remove_duplicate_table_lines(markdown: &str) -> String {
            if !trimmed.contains("|---") && trimmed.matches('|').count() >= 4 {
                let canonical = canonical_table_text(trimmed);
                if !canonical.is_empty() {
-                    if table_cell_count(trimmed) >= 8 {
-                        wide_table_rows.insert(canonical.clone());
-                    }
                    adjacent_table_row = Some(canonical);
                }
            }
        } else if trimmed.is_empty() {
            // Keep adjacency across the blank line emitted after a table.
        } else {
-            let canonical = canonical_table_text(trimmed);
-            let duplicate = wide_table_rows.contains(&canonical)
-                || adjacent_table_row
-                    .as_ref()
-                    .is_some_and(|table_row| *table_row == canonical);
+            let duplicate = adjacent_table_row
+                .as_ref()
+                .is_some_and(|table_row| *table_row == canonical_table_text(trimmed));
            adjacent_table_row = None;
            if duplicate {
                continue;
            }
-            // Wide rows are only candidates inside the duplicate block that
-            // immediately follows a table. Once unrelated prose begins, the
-            // same text may be a legitimate later reference.
-            wide_table_rows.clear();
        }
        output.push_str(line);
        output.push('\n');
@@ -846,13 +707,6 @@ fn remove_duplicate_table_lines(markdown: &str) -> String {
    output
 }

-fn table_cell_count(row: &str) -> usize {
-    row.trim_matches('|')
-        .split('|')
-        .filter(|cell| !cell.trim().is_empty())
-        .count()
-}
-
 fn canonical_table_text(text: &str) -> String {
    text.replace('|', " ")
        .split_whitespace()
@@ -867,7 +721,7 @@ fn assemble_document_markdown(pages: &[FusedPageMarkdown], include_page_numbers:
            document.push_str("\n\n");
        }
        if include_page_numbers {
-            document.push_str(&format!("<!-- Page {} -->\n\n", page.page_number));
+            document.push_str(&format!("<!-- Page {} -->\n\n", page.page));
        }
        document.push_str(page.markdown.trim());
    }
@@ -927,84 +781,6 @@ pub enum OcrPipelineError {
 mod tests {
    use super::*;

-    struct TrackingRenderer {
-        batches: Mutex<Vec<Vec<u32>>>,
-    }
-
-    impl PageRenderer for TrackingRenderer {
-        type Error = std::convert::Infallible;
-
-        fn render_pages(
-            &self,
-            _pdf_bytes: &[u8],
-            pages: &[u32],
-            _password: Option<&str>,
-            _options: &RenderOptions,
-        ) -> Result<Vec<super::super::RenderedPage>, Self::Error> {
-            self.batches.lock().unwrap().push(pages.to_vec());
-            Ok(pages
-                .iter()
-                .map(|page| {
-                    let transform = super::super::PageTransform::from_corners(
-                        1,
-                        1,
-                        (0.0, 1.0),
-                        (1.0, 1.0),
-                        (0.0, 0.0),
-                    )
-                    .unwrap();
-                    super::super::RenderedPage::new(
-                        *page,
-                        1.0,
-                        1.0,
-                        1,
-                        1,
-                        3,
-                        super::super::RenderPixelFormat::Rgb8,
-                        vec![255; 3],
-                        transform,
-                    )
-                    .unwrap()
-                })
-                .collect())
-        }
-    }
-
-    struct TrackingEngine {
-        batches: Mutex<Vec<Vec<u32>>>,
-        model: super::super::ModelIdentity,
-    }
-
-    impl OcrEngine for TrackingEngine {
-        type Error = std::convert::Infallible;
-
-        fn model(&self) -> &super::super::ModelIdentity {
-            &self.model
-        }
-
-        fn recognize(
-            &self,
-            pages: &[super::super::RenderedPage],
-            _options: &OcrOptions,
-        ) -> Result<Vec<super::super::OcrPage>, Self::Error> {
-            self.batches
-                .lock()
-                .unwrap()
-                .push(pages.iter().map(super::super::RenderedPage::page).collect());
-            Ok(pages
-                .iter()
-                .map(|page| super::super::OcrPage {
-                    page_number: page.page(),
-                    spans: Vec::new(),
-                    mean_confidence: None,
-                    model: self.model.clone(),
-                    processing_time_ms: 0,
-                    warnings: Vec::new(),
-                })
-                .collect())
-        }
-    }
-
    fn recovery_item(text: &str, x: f32, y: f32, width: f32, height: f32) -> crate::TextItem {
        crate::TextItem {
            text: text.to_string(),
@@ -1039,51 +815,6 @@ mod tests {
        assert_eq!(before, after);
    }

-    #[test]
-    fn high_level_ocr_bounds_rendering_and_inference_batches() {
-        let renderer = TrackingRenderer {
-            batches: Mutex::new(Vec::new()),
-        };
-        let engine = TrackingEngine {
-            batches: Mutex::new(Vec::new()),
-            model: super::super::ModelIdentity::new("test-ocr", "v1"),
-        };
-        let native_pages = (0..10)
-            .map(|page| PageMarkdown {
-                page,
-                markdown: String::new(),
-                needs_ocr: true,
-                ocr_reason: Some(crate::OCR_REASON_SCANNED.to_string()),
-            })
-            .collect::<Vec<_>>();
-        let routed_pages = (1..=10).collect::<Vec<_>>();
-        let ocr_options = OcrOptions::new().mode(OcrMode::Force);
-
-        let fused = run_and_fuse_ocr_chunks(
-            &renderer,
-            &engine,
-            b"test",
-            &routed_pages,
-            None,
-            &RenderOptions::new(),
-            &ocr_options,
-            &native_pages,
-            10,
-            &OcrFusionOptions::new(),
-            &BTreeMap::new(),
-        )
-        .unwrap();
-
-        let expected = vec![vec![1, 2, 3, 4], vec![5, 6, 7, 8], vec![9, 10]];
-        assert_eq!(*renderer.batches.lock().unwrap(), expected);
-        assert_eq!(*engine.batches.lock().unwrap(), expected);
-        assert_eq!(fused.pages.len(), 10);
-        assert!(fused
-            .pages
-            .iter()
-            .all(|page| page.provenance.hosted_recommended));
-    }
-
    #[test]
    fn native_recovery_is_limited_to_recoverable_routing_reasons() {
        let routed = [1, 2, 3, 4];
@@ -1177,23 +908,6 @@ mod tests {
        assert_eq!(remove_duplicate_table_lines(markdown), markdown);
    }

-    #[test]
-    fn recovered_markdown_keeps_wide_table_text_after_unrelated_prose() {
-        let markdown = "|Date|A|B|C|D|E|F|G|\n|---|---|---|---|---|---|---|---|\n|April 1|1|2|3|4|5|6|7|\n\nSummary follows.\n\nApril 1 1 2 3 4 5 6 7\n";
-
-        assert_eq!(remove_duplicate_table_lines(markdown), markdown);
-    }
-
-    #[test]
-    fn recovered_markdown_drops_contiguous_duplicate_block_of_wide_table_rows() {
-        let markdown = "|Date|A|B|C|D|E|F|G|\n|---|---|---|---|---|---|---|---|\n|April 1|1|2|3|4|5|6|7|\n|April 2|8|9|10|11|12|13|14|\n\nApril 1 1 2 3 4 5 6 7\nApril 2 8 9 10 11 12 13 14\n\nSummary follows.\n";
-
-        assert_eq!(
-            remove_duplicate_table_lines(markdown),
-            "|Date|A|B|C|D|E|F|G|\n|---|---|---|---|---|---|---|---|\n|April 1|1|2|3|4|5|6|7|\n|April 2|8|9|10|11|12|13|14|\n\n\nSummary follows.\n"
-        );
-    }
-
    #[test]
    fn extractor_candidates_require_clean_partial_content_reasons() {
        let reasons = [
@@ -1255,18 +969,13 @@ mod tests {
        let bytes = std::fs::read("tests/fixtures/thermo-freon12.pdf").unwrap();
        let mut markdown = MarkdownOptions::default();
        markdown.include_page_numbers = true;
-        let result = process_pdf_with_ocr_mem(
-            &bytes,
-            OcrPdfOptions::new().page_numbers([2]).markdown(markdown),
-        )
-        .unwrap();
+        let result =
+            process_pdf_with_ocr_mem(&bytes, OcrPdfOptions::new().pages([2]).markdown(markdown))
+                .unwrap();

        assert_eq!(result.pages.len(), 1);
-        assert_eq!(result.pages[0].page_number, 2);
-        assert_eq!(
-            result.pages[0].page_number,
-            result.pages[0].provenance.page_number
-        );
+        assert_eq!(result.pages[0].page, 2);
+        assert_eq!(result.pages[0].page, result.pages[0].provenance.page);
        assert!(result.markdown.starts_with("<!-- Page 2 -->"));
    }

@@ -1313,8 +1022,7 @@ mod tests {
    #[test]
    fn rejects_out_of_range_selection_even_with_ocr_off() {
        let bytes = std::fs::read("tests/fixtures/thermo-freon12.pdf").unwrap();
-        let error =
-            process_pdf_with_ocr_mem(&bytes, OcrPdfOptions::new().page_numbers([4])).unwrap_err();
+        let error = process_pdf_with_ocr_mem(&bytes, OcrPdfOptions::new().pages([4])).unwrap_err();
        assert!(matches!(
            error,
            OcrPipelineError::InvalidSelectedPage { page: 4 }
@@ -106,11 +106,7 @@ where
                source: Box::new(source),
            })?;
    let ocr_time_ms = elapsed_ms(ocr_started);
-    validate_page_order(
-        "OCR engine",
-        pages,
-        recognized.iter().map(|page| page.page_number),
-    )?;
+    validate_page_order("OCR engine", pages, recognized.iter().map(|page| page.page))?;

    Ok(OcrRun {
        pages: rendered
@@ -272,7 +268,7 @@ mod tests {
            Ok(pages
                .iter()
                .map(|page| OcrPage {
-                    page_number: page.page(),
+                    page: page.page(),
                    spans: vec![OcrSpan {
                        text: format!("page {}", page.page()),
                        polygon: ImageQuad::new([
@@ -5,7 +5,9 @@ use pdf_inspector::vision::{PdfiumRenderer, RenderError, RenderOptions, RenderPi
 fn load_renderer() -> Option<PdfiumRenderer> {
    match PdfiumRenderer::load() {
        Ok(renderer) => Some(renderer),
-        Err(RenderError::PdfiumLoad { .. }) => {
+        Err(RenderError::Pdfium(firecrawl_pdfium::Error::Load(
+            firecrawl_pdfium::LoadError::LibraryNotFound { .. },
+        ))) => {
            eprintln!("skipping PDFium runtime test because no native library is installed");
            None
        }
@@ -20,7 +20,9 @@ const EXPECTED_TEXT_ENV: &str = "PDF_INSPECTOR_OCR_TEST_EXPECTED";
 fn load_renderer() -> Option<PdfiumRenderer> {
    match PdfiumRenderer::load() {
        Ok(renderer) => Some(renderer),
-        Err(RenderError::PdfiumLoad { .. }) => {
+        Err(RenderError::Pdfium(firecrawl_pdfium::Error::Load(
+            firecrawl_pdfium::LoadError::LibraryNotFound { .. },
+        ))) => {
            eprintln!("skipping OCR runtime test because no native PDFium library is installed");
            None
        }
@@ -206,7 +208,7 @@ fn recognize(

 fn assert_usable_result(results: &[pdf_inspector::vision::OcrPage]) {
    assert_eq!(results.len(), 1);
-    assert_eq!(results[0].page_number, 1);
+    assert_eq!(results[0].page, 1);
    assert_eq!(results[0].model.name, PP_OCR_V6_SMALL.id);
    assert_eq!(results[0].model.revision, PP_OCR_V6_SMALL.revision);
    assert!(!results[0].spans.is_empty());
@@ -77,50 +77,6 @@ class TestProcessPdfBytes:
        assert result.markdown is not None


-# ---------------------------------------------------------------------------
-# process_pdf_with_ocr / process_pdf_with_ocr_bytes
-# ---------------------------------------------------------------------------
-
-
-class TestProcessPdfWithOcr:
-    def test_off_mode_has_full_provenance_without_external_runtimes(self):
-        result = pdf_inspector.process_pdf_with_ocr(
-            fixture_path("thermo-freon12.pdf"), mode="off"
-        )
-        assert result.page_count == 3
-        assert len(result.pages) == 3
-        assert result.pages_routed_to_ocr == []
-        assert all(page.provenance.source == "native" for page in result.pages)
-        assert all(page.provenance.ocr_model is None for page in result.pages)
-        assert result.markdown
-        assert "OcrPdfResult" in repr(result)
-
-    def test_auto_mode_skips_external_runtimes_for_clean_text(self):
-        result = pdf_inspector.process_pdf_with_ocr_bytes(
-            fixture_bytes("thermo-freon12.pdf")
-        )
-        assert result.pages_routed_to_ocr == []
-        assert result.render_time_ms == 0
-        assert result.ocr_time_ms == 0
-
-    def test_selected_pages_are_one_indexed(self):
-        result = pdf_inspector.process_pdf_with_ocr(
-            fixture_path("thermo-freon12.pdf"), mode="off", page_numbers=[2]
-        )
-        assert [page.page_number for page in result.pages] == [2]
-
-    def test_rejects_invalid_options(self):
-        with pytest.raises(ValueError, match="mode must be"):
-            pdf_inspector.process_pdf_with_ocr(
-                fixture_path("thermo-freon12.pdf"), mode="sometimes"
-            )
-        with pytest.raises(ValueError, match="page 0"):
-            pdf_inspector.process_pdf_with_ocr(
-                fixture_path("thermo-freon12.pdf"),
-                mode="off",
-                page_numbers=[0],
-            )
-
 # ---------------------------------------------------------------------------
 # detect_pdf / detect_pdf_bytes
 # ---------------------------------------------------------------------------
@@ -724,7 +724,7 @@ checksum = "d6790f58c7ff633d8771f42965289203411a5e5c68388703c06e14f24770b41e"

 [[package]]
 name = "pdf-inspector"
-version = "1.15.0"
+version = "1.14.2"
 dependencies = [
 "env_logger",
 "include_dir",
@@ -740,7 +740,7 @@ dependencies = [

 [[package]]
 name = "pdf-inspector-wasm"
-version = "1.15.0"
+version = "1.14.2"
 dependencies = [
 "console_error_panic_hook",
 "js-sys",
@@ -1,6 +1,6 @@
 [package]
 name = "pdf-inspector-wasm"
-version = "1.15.0"
+version = "1.14.2"
 edition = "2021"
 authors = ["Firecrawl Team"]
 description = "Browser WebAssembly bindings for pdf-inspector"
Author	SHA1	Message	Date
Abimael Martell	6d4f044d67	fix(vision): preserve adaptive OCR fallbacks	2026-08-16 21:42:45 -07:00
Abimael Martell	7e7c85801f	feat(vision): adaptively fuse native and OCR text	2026-08-16 21:42:45 -07:00
Abimael Martell	c6df46e328	fix(vision): validate native recovery coverage	2026-08-16 21:42:45 -07:00
Abimael Martell	852a790aa5	feat(vision): recover credible PDFium text layers	2026-08-16 21:42:45 -07:00
Abimael Martell	634a29f04d	fix(tables): preserve numbered reference notes	2026-08-16 21:42:45 -07:00
Abimael Martell	0e2e287c04	fix(vision): harden OCR engine caching	2026-08-16 21:42:45 -07:00
Abimael Martell	616f9b59fb	perf(vision): reuse OCR runtime sessions	2026-08-16 21:42:45 -07:00
Abimael Martell	21a436ac1b	fix(vision): normalize white bullet rows	2026-08-16 21:40:55 -07:00
Abimael Martell	d2d8e35a7b	fix(vision): harden OCR line recovery	2026-08-16 21:30:07 -07:00
Abimael Martell	30c9dbbc72	fix(vision): preserve OCR row boundaries	2026-08-16 21:30:07 -07:00
Abimael Martell	162c5cbf10	refactor(vision): expose OCR API	2026-08-16 21:30:07 -07:00
Abimael Martell	4e4cfdc74c	fix(vision): harden OCR API	2026-08-16 21:30:07 -07:00
Abimael Martell	24e66245cb	feat(vision): expose OCR pipeline	2026-08-16 21:30:07 -07:00
Abimael Martell	cee7b6c381	refactor(vision): use OCR fusion terminology	2026-08-16 21:30:07 -07:00
Abimael Martell	b5a63d7036	fix(vision): make OCR fusion conservative	2026-08-16 21:30:07 -07:00
Abimael Martell	6829397bce	feat(vision): fuse OCR output	2026-08-16 21:30:07 -07:00
Abimael Martell	fc16133a58	refactor(vision): name routed OCR results	2026-08-16 21:30:06 -07:00
Abimael Martell	41a6a67c03	fix(vision): serialize model acquisition	2026-08-16 21:30:06 -07:00
Abimael Martell	58fe5a0224	feat(vision): add OCR routing	2026-08-16 21:30:06 -07:00
Abimael Martell	c4c969a562	refactor(vision): use OCR engine terminology	2026-08-16 21:30:06 -07:00
Abimael Martell	bf0cd8decb	fix(vision): harden OAR runtime loading	2026-08-16 21:30:06 -07:00
Abimael Martell	232b4cdef5	feat(vision): add OAR OCR engine	2026-08-16 21:30:06 -07:00
Abimael Martell	e3f5429638	refactor(vision): use OCR terminology	2026-08-16 21:30:06 -07:00
Abimael Martell	f6cbe979f6	fix(vision): harden OCR contracts	2026-08-16 21:30:06 -07:00
Abimael Martell	3f43745313	feat(vision): add OCR contracts	2026-08-16 21:30:06 -07:00
Abimael Martell	a012cb65a6	docs(render): use OCR terminology	2026-08-16 21:30:06 -07:00
Abimael Martell	6567e1ab2d	fix(render): honor PDFium row stride	2026-08-16 21:30:06 -07:00
Abimael Martell	3af409d27f	feat(render): add optional PDFium page rendering	2026-08-16 21:30:06 -07:00