fix(tables): preserve numbered reference notes

Cargo.toml

@@ -62,6 +62,9 @@ sha2 = { version = "0.11", optional = true }
 image = { version = "0.25.6", default-features = false, optional = true }
 oar-ocr = { version = "0.9.1", default-features = false, features = ["simd"], optional = true }
 ort = { version = "=2.0.0-rc.13", default-features = false, features = ["load-dynamic"], optional = true }
+# HTTPS-only streaming downloader for pinned model artifacts. Kept separate
+# from model-cache so offline and package-managed deployments avoid HTTP/TLS.
+ureq = { version = "3.4", default-features = false, features = ["rustls", "platform-verifier"], optional = true }
 
 [target.'cfg(all(windows, not(target_arch = "wasm32")))'.dependencies]
 windows-sys = { version = "0.61", features = ["Win32_Storage_FileSystem"], optional = true }
@@ -80,8 +83,12 @@ default = []
 python = ["pyo3"]
 vision = []
 model-cache = ["vision", "dep:dirs", "dep:fs2", "dep:sha2", "dep:windows-sys"]
+model-download = ["model-cache", "dep:ureq"]
 ocr-oar = ["model-cache", "dep:image", "dep:oar-ocr", "dep:ort"]
 render-pdfium = ["vision", "dep:firecrawl-pdfium"]
+# Complete native OCR path. This remains opt-in so default library,
+# renderer-only, and browser consumers do not inherit inference or HTTP/TLS.
+ocr = ["render-pdfium", "ocr-oar", "model-download"]
 
 [[bin]]
 name = "pdf2md"

docs/rust-api.md

@@ -137,11 +137,12 @@ pdf-inspector = { version = "1", features = ["vision", "model-cache"] }
 
 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; a runtime integration can fetch a manifest's
-canonical URL only when allowed and pass the stream to `ModelStore::install`.
-Offline consumers set an explicit model directory and `ModelDownloadPolicy::Offline`.
-Renderer-only consumers do not enable `model-cache` and therefore do not compile
-its filesystem, locking, or hashing dependencies.
+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
+consumers do not enable `model-cache` or `model-download` and therefore do not
+compile their filesystem, hashing, or HTTP dependencies.
 
 ```rust
 use pdf_inspector::vision::{
@@ -244,8 +245,169 @@ The engine accepts renderer-neutral RGB, RGBA, and grayscale pages, preserves
 OAR's positioned quadrilaterals in bitmap coordinates, filters spans using
 `minimum_confidence`, and records the pinned model revision in every `OcrPage`.
 `OcrMode::Off` is rejected at the engine boundary so default options cannot run
-inference accidentally. Selective routing and OCR/native-text fusion are added
-by higher stack layers.
+inference accidentally.
+
+### Selective routing and lazy model acquisition
+
+`route_ocr_pages` applies the existing detector/text-quality recommendations to
+the configured mode. `Auto` processes only recommended pages, `Force` processes
+all pages (or an explicit page selection), and `Off` always returns an empty
+route. `run_ocr_pages` renders only that route, checks that both dependencies
+preserve its order, and retains each bitmap's PDF transform for fusion.
+
+```toml
+[dependencies]
+pdf-inspector = { version = "1", features = [
+  "render-pdfium",
+  "ocr-oar",
+  "model-download",
+] }
+```
+
+```rust
+use pdf_inspector::vision::{
+    route_ocr_pages, run_ocr_pages, HttpModelDownloader, ModelStore,
+    OarOcrEngine, OcrMode, OcrOptions, PdfiumRenderer, RenderOptions,
+    PP_OCR_V6_SMALL,
+};
+
+let bytes = std::fs::read("scan.pdf")?;
+let extraction = pdf_inspector::extract_pages_markdown_mem(&bytes, None)?;
+let options = OcrOptions::new().mode(OcrMode::Auto);
+let routed = route_ocr_pages(
+    options.mode,
+    extraction.pages.len() as u32,
+    &extraction.pages_needing_ocr,
+    None,
+)?;
+
+if !routed.is_empty() {
+    // No HTTP request or model initialization occurs before this point.
+    let store = ModelStore::from_options(&options)?;
+    let models = store.resolve_or_download(
+        &PP_OCR_V6_SMALL,
+        options.model_downloads,
+        &HttpModelDownloader::default(),
+    )?;
+    let run = run_ocr_pages(
+        &PdfiumRenderer::load()?,
+        &OarOcrEngine::from_models(&models)?,
+        &bytes,
+        &routed,
+        None,
+        &RenderOptions::new(),
+        &options,
+    )?;
+    println!("OCR processed {} pages", run.pages.len());
+}
+```
+
+The downloader accepts HTTPS only, checks a declared content length, caps the
+response stream to the pinned size plus one byte, and delegates final size and
+SHA-256 verification to `ModelStore`. The store serializes installation across
+processes and publishes completed artifacts atomically. Warm caches make no
+network calls; offline mode and explicit model directories never download.
+
+### OCR Markdown assembly and native fusion
+
+`fuse_ocr_pages` maps OCR polygons back into PDF coordinates and sends the
+result through pdf-inspector's existing deterministic reading-order, table,
+and Markdown pipeline. Pages whose native extraction was rejected use OCR
+output. When `Force` runs on a clean native page, normalized duplicate OCR
+blocks are removed and only additional image-backed text is retained.
+
+```rust
+use pdf_inspector::vision::{fuse_ocr_pages, OcrFusionOptions};
+
+let fused = fuse_ocr_pages(
+    &extraction.pages,
+    &run,
+    extraction.pages.len() as u32,
+    &OcrFusionOptions::new().render_dpi(150.0),
+)?;
+
+for page in &fused.pages {
+    println!("{}", page.markdown);
+    if page.provenance.hosted_recommended {
+        eprintln!("page {} needs the hosted document pipeline", page.page + 1);
+    }
+}
+```
+
+Each page carries `Native`, `Ocr`, or `Fused` provenance, the exact OCR model
+revision, accepted-page confidence, local stage timings, and non-fatal
+warnings. A page that required OCR recommends the hosted pipeline when local
+OCR is missing, empty, or below the configurable page-confidence threshold.
+This keeps the lightweight path explicit about cases it cannot finish well.
+
+### Complete OCR API
+
+The `ocr` convenience feature enables the renderer, OCR engine, verified
+model acquisition, routing, and fusion layers together. It is the intended
+downstream application integration boundary; lower-level features remain
+available for consumers that bring their own renderer, model package manager,
+or engine.
+
+```toml
+[dependencies]
+pdf-inspector = { version = "1", features = ["ocr"] }
+```
+
+```rust
+use pdf_inspector::vision::{
+    process_pdf_with_ocr, OcrMode, OcrPdfOptions,
+};
+
+let result = process_pdf_with_ocr(
+    "document.pdf",
+    OcrPdfOptions::new()
+        .mode(OcrMode::Auto)
+        .pages([1, 2, 3]),
+)?;
+
+println!("{}", result.markdown);
+println!("OCR pages: {:?}", result.pages_routed_to_ocr);
+println!(
+    "Hosted fallback pages: {:?}",
+    result.pages_recommending_hosted,
+);
+```
+
+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. Learned layout intentionally
+returns an explicit unsupported error in this lightweight pipeline.
+
+The one-call API keeps the most recently used verified OCR engine in process.
+Long-lived workers therefore verify the pinned artifacts and build the ONNX
+sessions once, then reuse those loaded sessions across documents. The cache is
+bounded to one model configuration and keyed by normalized model/runtime paths
+plus the pinned manifest revision and artifact digests; switching the model
+directory, runtime library, or compiled manifest replaces it. An active engine
+owns the model data it already verified, so mutating artifacts in place does
+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.
+
+Build the CLI with the same opt-in feature:
+
+```bash
+cargo build --release --features ocr --bin pdf2md
+pdf2md document.pdf --ocr auto --raw
+pdf2md document.pdf --ocr auto --json
+pdf2md document.pdf --ocr auto --ocr-offline --ocr-model-dir /opt/models/pp-ocrv6-small
+```
+
+CLI controls include `--ocr-dpi`, `--ocr-min-confidence`,
+`--ocr-hosted-threshold`, `--select-pages`, and the existing encrypted-PDF
+`--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::pages`.
 
 Extract per-page Markdown (one string per page, plus document-wide layout
 metadata):

src/bin/pdf2md.rs

@@ -1,6 +1,11 @@
 //! CLI tool for PDF to Markdown conversion
 
 use pdf_inspector::extractor::ItemType;
+#[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+use pdf_inspector::vision::{
+    process_pdf_with_ocr, ModelDownloadPolicy, OcrMode, OcrOptions, OcrPdfOptions, OcrPdfResult,
+    PageContentSource, RenderOptions,
+};
 use pdf_inspector::{
     extract_text_with_positions_pages_with_password, process_pdf_with_options, LayoutComplexity,
     PdfOptions, PdfType, ProcessMode, TextItem,
@@ -103,6 +108,134 @@ fn format_items_json(items: &[TextItem]) -> String {
     )
 }
 
+#[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+fn optional_json_number(value: Option<f32>) -> String {
+    value
+        .filter(|value| value.is_finite())
+        .map(|value| format!("{value:.4}"))
+        .unwrap_or_else(|| "null".to_string())
+}
+
+#[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+fn format_ocr_json(result: &OcrPdfResult) -> String {
+    let routed = result
+        .pages_routed_to_ocr
+        .iter()
+        .map(u32::to_string)
+        .collect::<Vec<_>>()
+        .join(",");
+    let recommended = result
+        .pages_recommended_for_ocr
+        .iter()
+        .map(u32::to_string)
+        .collect::<Vec<_>>()
+        .join(",");
+    let hosted = result
+        .pages_recommending_hosted
+        .iter()
+        .map(u32::to_string)
+        .collect::<Vec<_>>()
+        .join(",");
+    let pages = result
+        .pages
+        .iter()
+        .map(|page| {
+            let provenance = &page.provenance;
+            let source = match provenance.source {
+                PageContentSource::Native => "native",
+                PageContentSource::Ocr => "ocr",
+                PageContentSource::Fused => "fused",
+                _ => "unknown",
+            };
+            let model = provenance
+                .ocr_model
+                .as_ref()
+                .map(|model| {
+                    format!(
+                        r#"{{"name":"{}","revision":"{}"}}"#,
+                        json_escape(&model.name),
+                        json_escape(&model.revision)
+                    )
+                })
+                .unwrap_or_else(|| "null".to_string());
+            let warnings = provenance
+                .warnings
+                .iter()
+                .map(|warning| format!(r#""{}""#, json_escape(warning)))
+                .collect::<Vec<_>>()
+                .join(",");
+            format!(
+                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,
+                optional_json_number(provenance.render_dpi),
+                optional_json_number(provenance.ocr_confidence),
+                provenance.hosted_recommended,
+                provenance.timings.render_ms,
+                provenance.timings.ocr_ms,
+                provenance.timings.layout_ms,
+                provenance.timings.assembly_ms,
+                warnings,
+            )
+        })
+        .collect::<Vec<_>>()
+        .join(",");
+    let table_pages = result
+        .pages_with_tables
+        .iter()
+        .map(u32::to_string)
+        .collect::<Vec<_>>()
+        .join(",");
+    let column_pages = result
+        .pages_with_columns
+        .iter()
+        .map(u32::to_string)
+        .collect::<Vec<_>>()
+        .join(",");
+    let ocr_reasons = format_ocr_reasons_by_page(&result.ocr_reasons_by_page);
+    format!(
+        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,
+        result.ocr_time_ms,
+        recommended,
+        routed,
+        hosted,
+        ocr_reasons,
+        result.is_complex,
+        table_pages,
+        column_pages,
+        pages,
+        json_escape(&result.markdown),
+    )
+}
+
+fn argument_value<'a>(args: &'a [String], name: &str) -> Result<Option<&'a str>, String> {
+    args.iter()
+        .position(|argument| argument == name)
+        .map(|index| {
+            args.get(index + 1)
+                .map(String::as_str)
+                .ok_or_else(|| format!("{name} requires a value"))
+        })
+        .transpose()
+}
+
+#[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+fn float_argument(args: &[String], name: &str, default: f32) -> Result<f32, String> {
+    argument_value(args, name)?
+        .map(|value| {
+            value
+                .parse::<f32>()
+                .map_err(|_| format!("{name} requires a number, got {value:?}"))
+        })
+        .transpose()
+        .map(|value| value.unwrap_or(default))
+}
+
 fn extract_items_json(
     pdf_path: &str,
     page_filter: Option<&HashSet<u32>>,
@@ -242,6 +375,12 @@ fn main() {
         eprintln!("  --password PW       Password for an encrypted PDF");
         eprintln!("  --detect-only       Only detect PDF type (no extraction)");
         eprintln!("  --analyze           Detect + extract + layout analysis (no markdown)");
+        eprintln!("  --ocr MODE          OCR mode: off, auto, or force (requires feature `ocr`)");
+        eprintln!("  --ocr-dpi N         OCR render resolution (default: 150)");
+        eprintln!("  --ocr-min-confidence N  Drop OCR spans below N (default: 0)");
+        eprintln!("  --ocr-hosted-threshold N  Recommend hosted parsing below N (default: 0.5)");
+        eprintln!("  --ocr-model-dir DIR Use a package-managed local model directory");
+        eprintln!("  --ocr-offline       Never download missing OCR models");
         process::exit(1);
     }
 
@@ -253,6 +392,10 @@ fn main() {
     let page_numbers = args.iter().any(|a| a == "--pages");
     let detect_only = args.iter().any(|a| a == "--detect-only");
     let analyze = args.iter().any(|a| a == "--analyze");
+    let ocr_mode_argument = argument_value(&args, "--ocr").unwrap_or_else(|error| {
+        eprintln!("Error: {error}");
+        process::exit(1);
+    });
 
     // Parse --password value
     let password = args.iter().position(|a| a == "--password").map(|i| {
@@ -283,6 +426,141 @@ fn main() {
             })
         });
 
+    let output_file = args
+        .get(2)
+        .filter(|a| !a.starts_with("--"))
+        .map(|s| s.as_str());
+
+    let has_ocr_only_option = [
+        "--ocr-dpi",
+        "--ocr-min-confidence",
+        "--ocr-hosted-threshold",
+        "--ocr-model-dir",
+        "--ocr-offline",
+    ]
+    .iter()
+    .any(|option| args.iter().any(|argument| argument == option));
+    if ocr_mode_argument.is_none() && has_ocr_only_option {
+        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 {
+            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;
+            eprintln!("Error: this pdf2md build does not include OCR; rebuild with --features ocr");
+            process::exit(1);
+        }
+
+        #[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+        {
+            let mode = match mode {
+                "off" => OcrMode::Off,
+                "auto" => OcrMode::Auto,
+                "force" => OcrMode::Force,
+                value => {
+                    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| {
+                eprintln!("Error: {error}");
+                process::exit(1);
+            });
+            let minimum_confidence = float_argument(&args, "--ocr-min-confidence", 0.0)
+                .unwrap_or_else(|error| {
+                    eprintln!("Error: {error}");
+                    process::exit(1);
+                });
+            let hosted_threshold = float_argument(&args, "--ocr-hosted-threshold", 0.5)
+                .unwrap_or_else(|error| {
+                    eprintln!("Error: {error}");
+                    process::exit(1);
+                });
+            let model_directory =
+                argument_value(&args, "--ocr-model-dir").unwrap_or_else(|error| {
+                    eprintln!("Error: {error}");
+                    process::exit(1);
+                });
+
+            let mut ocr = OcrOptions::new()
+                .mode(mode)
+                .minimum_confidence(minimum_confidence);
+            if let Some(directory) = model_directory {
+                ocr = ocr.model_directory(directory);
+            }
+            if args.iter().any(|argument| argument == "--ocr-offline") {
+                ocr = ocr.model_downloads(ModelDownloadPolicy::Offline);
+            }
+            let mut markdown = pdf_inspector::MarkdownOptions::default();
+            if compact_output {
+                markdown.profile = pdf_inspector::MarkdownProfile::Compact;
+            }
+            markdown.include_page_numbers = page_numbers;
+            let mut pdf_options = OcrPdfOptions::new()
+                .render(RenderOptions::new().dpi(dpi))
+                .ocr(ocr)
+                .markdown(markdown)
+                .hosted_recommendation_confidence(hosted_threshold);
+            if let Some(pages) = page_filter.clone() {
+                pdf_options = pdf_options.pages(pages);
+            }
+            if let Some(password) = password.clone() {
+                pdf_options = pdf_options.password(password);
+            }
+
+            match process_pdf_with_ocr(pdf_path, pdf_options) {
+                Ok(result) => {
+                    if json_output {
+                        println!("{}", format_ocr_json(&result));
+                    } else if raw_output {
+                        print!("{}", result.markdown);
+                    } else {
+                        eprintln!("PDF to Markdown Conversion (OCR)");
+                        eprintln!("======================================");
+                        eprintln!("File: {pdf_path}");
+                        eprintln!("Pages: {}", result.page_count);
+                        eprintln!("Pages routed to OCR: {:?}", result.pages_routed_to_ocr);
+                        if !result.pages_recommending_hosted.is_empty() {
+                            eprintln!(
+                                "Hosted parsing recommended for pages: {:?}",
+                                result.pages_recommending_hosted
+                            );
+                        }
+                        eprintln!("Processing time: {}ms", result.processing_time_ms);
+                        if let Some(output) = output_file {
+                            fs::write(output, &result.markdown)
+                                .expect("Failed to write output file");
+                            eprintln!("Markdown written to: {output}");
+                        } else {
+                            eprintln!();
+                            eprintln!("--- Markdown Output ---");
+                            eprintln!();
+                            print!("{}", result.markdown);
+                        }
+                    }
+                }
+                Err(error) => {
+                    if json_output {
+                        println!(r#"{{"error":"{}"}}"#, json_escape(&error.to_string()));
+                    } else {
+                        eprintln!("Error: {error}");
+                    }
+                    process::exit(1);
+                }
+            }
+            return;
+        }
+    }
+
     if items_json_output {
         match extract_items_json(pdf_path, page_filter.as_ref(), password.as_deref()) {
             Ok(json) => println!("{}", json),
@@ -294,11 +572,6 @@ fn main() {
         return;
     }
 
-    let output_file = args
-        .get(2)
-        .filter(|a| !a.starts_with("--"))
-        .map(|s| s.as_str());
-
     let process_mode = if detect_only {
         ProcessMode::DetectOnly
     } else if analyze {

src/lib.rs

@@ -459,8 +459,35 @@ pub fn extract_pages_markdown_mem(
     buffer: &[u8],
     pages: Option<&[u32]>,
 ) -> Result<PagesExtractionResult, PdfError> {
+    extract_pages_markdown_mem_impl(buffer, pages, None, &MarkdownOptions::default(), false)
+        .map(|(result, _)| result)
+}
+
+#[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+pub(crate) fn extract_pages_markdown_mem_for_ocr(
+    buffer: &[u8],
+    pages: Option<&[u32]>,
+    password: Option<&str>,
+    markdown_options: &MarkdownOptions,
+) -> Result<(PagesExtractionResult, u32), PdfError> {
+    extract_pages_markdown_mem_impl(
+        buffer,
+        pages,
+        password,
+        markdown_options,
+        markdown_options.strip_headers_footers,
+    )
+}
+
+fn extract_pages_markdown_mem_impl(
+    buffer: &[u8],
+    pages: Option<&[u32]>,
+    password: Option<&str>,
+    markdown_options: &MarkdownOptions,
+    strip_repeated_headers_footers: bool,
+) -> Result<(PagesExtractionResult, u32), PdfError> {
     validate_pdf_bytes(buffer)?;
-    let (doc, page_count) = load_document_from_mem(buffer)?;
+    let (doc, page_count) = load_document_from_mem_with_password(buffer, password)?;
     let font_cmaps = FontCMaps::from_doc(&doc);
 
     // Extract ALL pages to get accurate, document-wide font stats. A malformed
@@ -503,6 +530,11 @@ pub fn extract_pages_markdown_mem(
 
     // Compute font stats from full document (cross-page consistency).
     let font_stats = markdown::analysis::calculate_font_stats_from_items(&filtered_items);
+    let repeated_header_footer_items = if strip_repeated_headers_footers {
+        repeated_header_footer_item_keys(&all_items, &page_thresholds, &chart_regions, page_count)
+    } else {
+        HashSet::new()
+    };
 
     // When caller doesn't specify pages, return every page in document order.
     let all_pages: Vec<u32>;
@@ -538,7 +570,10 @@ pub fn extract_pages_markdown_mem(
         let (page_items, page_number_removal_mask): (Vec<TextItem>, Vec<bool>) = all_items
             .iter()
             .zip(&page_number_removal_mask)
-            .filter(|(item, _)| item.page == page_1idx)
+            .filter(|(item, _)| {
+                item.page == page_1idx
+                    && !repeated_header_footer_items.contains(&HeaderFooterItemKey::from(*item))
+            })
             .map(|(item, remove)| (item.clone(), *remove))
             .unzip();
 
@@ -575,7 +610,7 @@ pub fn extract_pages_markdown_mem(
             base_font_size: Some(font_stats.most_common_size),
             include_page_numbers: false,
             strip_headers_footers: false,
-            ..MarkdownOptions::default()
+            ..markdown_options.clone()
         };
 
         let md = if has_text_quality_issue {
@@ -634,14 +669,129 @@ pub fn extract_pages_markdown_mem(
         });
     }
 
-    Ok(PagesExtractionResult {
-        pages: results,
-        pages_with_tables: complexity.pages_with_tables,
-        pages_with_columns: complexity.pages_with_columns,
-        pages_needing_ocr,
-        ocr_reasons_by_page: page_ocr_reasons_vec(ocr_reasons_by_page),
-        is_complex: complexity.is_complex,
-    })
+    Ok((
+        PagesExtractionResult {
+            pages: results,
+            pages_with_tables: complexity.pages_with_tables,
+            pages_with_columns: complexity.pages_with_columns,
+            pages_needing_ocr,
+            ocr_reasons_by_page: page_ocr_reasons_vec(ocr_reasons_by_page),
+            is_complex: complexity.is_complex,
+        },
+        page_count,
+    ))
+}
+
+#[derive(Debug, Clone, PartialEq, Eq, Hash)]
+struct HeaderFooterItemKey {
+    page: u32,
+    x: u32,
+    y: u32,
+    text: String,
+}
+
+impl From<&TextItem> for HeaderFooterItemKey {
+    fn from(item: &TextItem) -> Self {
+        Self {
+            page: item.page,
+            x: item.x.to_bits(),
+            y: item.y.to_bits(),
+            text: item.text.clone(),
+        }
+    }
+}
+
+fn repeated_header_footer_item_keys(
+    items: &[TextItem],
+    page_thresholds: &HashMap<u32, f32>,
+    chart_regions: &HashMap<u32, Vec<(f32, f32, f32, f32)>>,
+    page_count: u32,
+) -> HashSet<HeaderFooterItemKey> {
+    let candidates = items
+        .iter()
+        .filter(|item| {
+            matches!(
+                item.item_type,
+                types::ItemType::Text | types::ItemType::FormField
+            )
+        })
+        .cloned()
+        .collect();
+    let lines = extractor::group_prefiltered_items_into_lines_with_thresholds_and_charts(
+        candidates,
+        page_thresholds,
+        &HashSet::new(),
+        chart_regions,
+    );
+    let all_items: HashSet<_> = lines
+        .iter()
+        .flat_map(|line| line.items.iter().map(HeaderFooterItemKey::from))
+        .collect();
+    let kept = markdown::strip_repeated_header_footer_lines(lines, page_count);
+    let kept_items: HashSet<_> = kept
+        .iter()
+        .flat_map(|line| line.items.iter().map(HeaderFooterItemKey::from))
+        .collect();
+    all_items.difference(&kept_items).cloned().collect()
+}
+
+#[cfg(all(test, feature = "ocr", not(target_arch = "wasm32")))]
+mod ocr_header_footer_tests {
+    use super::*;
+
+    fn item(page: u32, text: &str, y: f32) -> TextItem {
+        TextItem {
+            text: text.to_string(),
+            x: 10.0,
+            y,
+            width: 120.0,
+            height: 10.0,
+            font: "Test".to_string(),
+            font_size: 10.0,
+            page,
+            is_bold: false,
+            is_italic: false,
+            is_underline: false,
+            is_strikeout: false,
+            item_type: types::ItemType::Text,
+            mcid: None,
+        }
+    }
+
+    #[test]
+    fn local_pipeline_prefilters_document_wide_repeated_headers() {
+        let mut items = Vec::new();
+        let mut thresholds = HashMap::new();
+        for page in 1..=3 {
+            items.push(item(page, "Repeated report header", 800.0));
+            for line in 0..12 {
+                items.push(item(
+                    page,
+                    &format!("Page {page} paragraph {line} unique content"),
+                    700.0 - line as f32 * 40.0,
+                ));
+            }
+            thresholds.insert(page, 0.1);
+        }
+
+        let removed = repeated_header_footer_item_keys(&items, &thresholds, &HashMap::new(), 3);
+        assert_eq!(removed.len(), 2);
+        for page in 1..=3 {
+            assert_eq!(
+                removed.contains(&HeaderFooterItemKey::from(&item(
+                    page,
+                    "Repeated report header",
+                    800.0,
+                ))),
+                page > 1,
+            );
+            assert!(!removed.contains(&HeaderFooterItemKey::from(&item(
+                page,
+                &format!("Page {page} paragraph 5 unique content"),
+                500.0,
+            ))));
+        }
+    }
 }
 
 /// Path-based wrapper for [`extract_pages_markdown_mem`].

src/markdown/mod.rs

@@ -1144,6 +1144,14 @@ pub fn to_markdown(text: &str, options: MarkdownOptions) -> String {
     output
 }
 
+/// Applies the document-wide repeated header/footer classifier to grouped lines.
+pub(crate) fn strip_repeated_header_footer_lines(
+    lines: Vec<crate::types::TextLine>,
+    page_count: u32,
+) -> Vec<crate::types::TextLine> {
+    preprocess::strip_repeated_lines(lines, page_count)
+}
+
 /// Convert positioned text items to markdown with structure detection
 pub fn to_markdown_from_items(items: Vec<TextItem>, options: MarkdownOptions) -> String {
     to_markdown_from_items_with_rects(items, options, &[])

src/tables/format.rs

@@ -442,6 +442,16 @@ fn clean_table_cells(cells: &[Vec<String>]) -> (Vec<Vec<String>>, Vec<String>) {
 fn is_footnote_row(text: &str) -> bool {
     let trimmed = text.trim();
 
+    // Japanese documents commonly use the reference mark followed by an
+    // ASCII or full-width number (for example `※1` / `※１`). These rows often
+    // sit immediately below a wide table and must not be merged into its last
+    // data row as wrapped first-column content.
+    if let Some(rest) = trimmed.strip_prefix('※') {
+        return rest.chars().next().is_some_and(|character| {
+            character.is_ascii_digit() || ('０'..='９').contains(&character)
+        });
+    }
+
     // Check for common footnote patterns
     // (1), (2), etc.
     if trimmed.starts_with('(') && trimmed.len() >= 2 {
@@ -503,6 +513,13 @@ mod tests {
         assert!(is_footnote_row("NOTES: uppercase"));
     }
 
+    #[test]
+    fn test_is_footnote_row_reference_mark_number() {
+        assert!(is_footnote_row("※1 explanation"));
+        assert!(is_footnote_row("※１ 説明"));
+        assert!(!is_footnote_row("※ general marker"));
+    }
+
     #[test]
     fn test_is_footnote_row_plain_text_false() {
         assert!(!is_footnote_row("Regular cell text"));

src/vision/download.rs

@@ -0,0 +1,84 @@
+//! HTTPS acquisition for pinned local model artifacts.
+
+use std::fmt;
+use std::io::Read;
+use std::time::Duration;
+
+use thiserror::Error;
+
+use super::{ModelArtifact, ModelDownloader};
+
+/// Default end-to-end timeout for one model artifact request.
+pub const DEFAULT_MODEL_DOWNLOAD_TIMEOUT: Duration = Duration::from_secs(5 * 60);
+
+/// Streaming HTTPS downloader used by lazy model resolution.
+#[derive(Clone)]
+pub struct HttpModelDownloader {
+    agent: ureq::Agent,
+}
+
+impl fmt::Debug for HttpModelDownloader {
+    fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
+        formatter
+            .debug_struct("HttpModelDownloader")
+            .finish_non_exhaustive()
+    }
+}
+
+impl Default for HttpModelDownloader {
+    fn default() -> Self {
+        Self::new(DEFAULT_MODEL_DOWNLOAD_TIMEOUT)
+    }
+}
+
+impl HttpModelDownloader {
+    /// Creates an HTTPS-only downloader with an end-to-end request timeout.
+    pub fn new(timeout: Duration) -> Self {
+        let config = ureq::Agent::config_builder()
+            .https_only(true)
+            .timeout_global(Some(timeout))
+            .user_agent(concat!("pdf-inspector/", env!("CARGO_PKG_VERSION")))
+            .build();
+        Self {
+            agent: ureq::Agent::new_with_config(config),
+        }
+    }
+}
+
+impl ModelDownloader for HttpModelDownloader {
+    type Error = HttpModelDownloadError;
+
+    fn open(&self, artifact: &ModelArtifact) -> Result<Box<dyn Read + Send>, Self::Error> {
+        let response = self.agent.get(artifact.url).call()?;
+        if let Some(actual) = response.body().content_length() {
+            if actual != artifact.size {
+                return Err(HttpModelDownloadError::ContentLength {
+                    expected: artifact.size,
+                    actual,
+                });
+            }
+        }
+
+        // One extra byte lets ModelStore report an exact size mismatch while
+        // preventing a malicious or broken server from filling the disk.
+        let limit = artifact.size.saturating_add(1);
+        Ok(Box::new(response.into_body().into_reader().take(limit)))
+    }
+}
+
+/// Failures before a response stream reaches [`super::ModelStore`].
+#[derive(Debug, Error)]
+#[non_exhaustive]
+pub enum HttpModelDownloadError {
+    /// DNS, TLS, redirect, HTTP status, or response-stream setup failed.
+    #[error(transparent)]
+    Request(#[from] ureq::Error),
+    /// The server declared a size that disagrees with the pinned manifest.
+    #[error("server declared {actual} bytes; manifest requires {expected}")]
+    ContentLength {
+        /// Pinned artifact size.
+        expected: u64,
+        /// Server-declared size.
+        actual: u64,
+    },
+}

src/vision/mod.rs

@@ -10,12 +10,20 @@
 
 #[cfg(all(feature = "vision", not(target_arch = "wasm32")))]
 mod contracts;
+#[cfg(all(feature = "model-download", not(target_arch = "wasm32")))]
+mod download;
+#[cfg(all(feature = "vision", not(target_arch = "wasm32")))]
+mod fusion;
 #[cfg(all(feature = "model-cache", not(target_arch = "wasm32")))]
 mod models;
 #[cfg(all(feature = "ocr-oar", not(target_arch = "wasm32")))]
 mod oar;
+#[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+mod pipeline;
 #[cfg(all(feature = "vision", not(target_arch = "wasm32")))]
 mod render;
+#[cfg(all(feature = "vision", not(target_arch = "wasm32")))]
+mod routing;
 
 #[cfg(all(feature = "render-pdfium", not(target_arch = "wasm32")))]
 mod pdfium;
@@ -26,16 +34,32 @@ pub use contracts::{
     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};
+#[cfg(all(feature = "vision", not(target_arch = "wasm32")))]
+pub use fusion::{
+    fuse_ocr_pages, ocr_page_to_markdown, FusedPageMarkdown, FusedPages, OcrFusionError,
+    OcrFusionOptions,
+};
 #[cfg(all(feature = "model-cache", not(target_arch = "wasm32")))]
 pub use models::{
-    ModelArtifact, ModelArtifactKind, ModelManifest, ModelPaths, ModelStore, ModelStoreError,
-    PP_OCR_V6_SMALL,
+    ModelAcquireError, ModelArtifact, ModelArtifactKind, ModelDownloader, ModelManifest,
+    ModelPaths, ModelStore, ModelStoreError, PP_OCR_V6_SMALL,
 };
 #[cfg(all(feature = "ocr-oar", not(target_arch = "wasm32")))]
 pub use oar::{OarOcrEngine, OarOcrError, ONNX_RUNTIME_LIBRARY_ENV};
+#[cfg(all(feature = "ocr", not(target_arch = "wasm32")))]
+pub use pipeline::{
+    process_pdf_with_ocr, process_pdf_with_ocr_mem, OcrPdfOptions, OcrPdfResult, OcrPipelineError,
+};
 #[cfg(all(feature = "vision", not(target_arch = "wasm32")))]
 pub use render::{
     PagePoint, PageTransform, RenderBufferError, RenderOptions, RenderPixelFormat, RenderedPage,
+    DEFAULT_RENDER_DPI,
+};
+#[cfg(all(feature = "vision", not(target_arch = "wasm32")))]
+pub use routing::{
+    route_ocr_pages, run_ocr_pages, OcrRoutingError, OcrRun, OcrRunError, RoutedOcrPage,
 };
 
 #[cfg(all(feature = "render-pdfium", not(target_arch = "wasm32")))]

src/vision/models.rs

@@ -12,7 +12,7 @@ use fs2::FileExt;
 use sha2::{Digest, Sha256};
 use thiserror::Error;
 
-use super::OcrOptions;
+use super::{ModelDownloadPolicy, OcrOptions};
 
 /// Environment variable overriding the default local model cache.
 pub const MODEL_CACHE_ENV: &str = "PDF_INSPECTOR_MODEL_CACHE";
@@ -138,6 +138,19 @@ pub struct ModelStore {
     override_root: Option<PathBuf>,
 }
 
+/// Streaming source for a pinned model artifact.
+///
+/// Implementations may use HTTP, an object store, or an application-owned
+/// package manager. [`ModelStore`] remains responsible for locking, atomic
+/// installation, exact size validation, and SHA-256 verification.
+pub trait ModelDownloader: Send + Sync {
+    /// Downloader-specific failure type.
+    type Error: std::error::Error + Send + Sync + 'static;
+
+    /// Opens a streaming reader for one manifest artifact.
+    fn open(&self, artifact: &ModelArtifact) -> Result<Box<dyn Read + Send>, Self::Error>;
+}
+
 impl ModelStore {
     /// Creates a model store rooted at an explicit cache directory.
     pub fn new(cache_root: impl Into<PathBuf>) -> Self {
@@ -177,16 +190,17 @@ impl ModelStore {
         &self.cache_root
     }
 
+    /// Effective directory containing one manifest's artifacts.
+    pub(crate) fn model_root(&self, manifest: &ModelManifest) -> PathBuf {
+        self.override_root
+            .clone()
+            .unwrap_or_else(|| self.manifest_cache_root(manifest))
+    }
+
     /// Validates and resolves every required artifact.
     pub fn resolve(&self, manifest: &ModelManifest) -> Result<ModelPaths, ModelStoreError> {
         validate_manifest(manifest)?;
-        let managed_root;
-        let root = if let Some(root) = self.override_root.as_deref() {
-            root
-        } else {
-            managed_root = self.manifest_cache_root(manifest);
-            managed_root.as_path()
-        };
+        let root = self.model_root(manifest);
 
         let mut artifacts = BTreeMap::new();
         for artifact in manifest.artifacts {
@@ -201,6 +215,54 @@ impl ModelStore {
         })
     }
 
+    /// Resolves a complete model set, fetching only missing or invalid managed
+    /// cache artifacts when policy permits.
+    ///
+    /// Explicit [`OcrOptions::model_directory`] overrides are never mutated or
+    /// supplemented from the network. This method also avoids all downloader
+    /// calls when the cache is already valid or downloads are offline.
+    pub fn resolve_or_download<D: ModelDownloader>(
+        &self,
+        manifest: &ModelManifest,
+        policy: ModelDownloadPolicy,
+        downloader: &D,
+    ) -> Result<ModelPaths, ModelAcquireError<D::Error>> {
+        validate_manifest(manifest).map_err(ModelAcquireError::Store)?;
+        match self.resolve(manifest) {
+            Ok(paths) => return Ok(paths),
+            Err(source) if self.override_root.is_some() => {
+                return Err(ModelAcquireError::ExplicitDirectoryIncomplete { source });
+            }
+            Err(source) if !source.permits_download_recovery() => {
+                return Err(ModelAcquireError::Store(source));
+            }
+            Err(source) if policy == ModelDownloadPolicy::Offline => {
+                return Err(ModelAcquireError::DownloadsDisabled { source });
+            }
+            Err(_) => {}
+        }
+
+        let root = self.manifest_cache_root(manifest);
+        for artifact in manifest.artifacts {
+            let _lock = lock_artifact(&root, artifact).map_err(ModelAcquireError::Store)?;
+            match verify_artifact(&root.join(artifact.filename), artifact) {
+                Ok(()) => continue,
+                Err(source) if source.permits_download_recovery() => {}
+                Err(source) => return Err(ModelAcquireError::Store(source)),
+            }
+            let reader =
+                downloader
+                    .open(artifact)
+                    .map_err(|source| ModelAcquireError::Download {
+                        kind: artifact.kind,
+                        url: artifact.url,
+                        source,
+                    })?;
+            install_locked(&root, artifact, reader).map_err(ModelAcquireError::Store)?;
+        }
+        self.resolve(manifest).map_err(ModelAcquireError::Store)
+    }
+
     /// Atomically installs one artifact from a reader after validating its
     /// exact size and SHA-256 digest.
     ///
@@ -219,58 +281,8 @@ impl ModelStore {
             .find(|artifact| artifact.kind == kind)
             .ok_or(ModelStoreError::ArtifactNotInManifest { kind })?;
         let root = self.manifest_cache_root(manifest);
-        fs::create_dir_all(&root).map_err(|source| ModelStoreError::Io {
-            path: root.clone(),
-            source,
-        })?;
-
-        let target = root.join(artifact.filename);
-        let lock_path = root.join(format!(".{}.lock", artifact.filename));
-        let lock = OpenOptions::new()
-            .create(true)
-            .read(true)
-            .write(true)
-            .truncate(false)
-            .open(&lock_path)
-            .map_err(|source| ModelStoreError::Io {
-                path: lock_path.clone(),
-                source,
-            })?;
-        FileExt::lock_exclusive(&lock).map_err(|source| ModelStoreError::Io {
-            path: lock_path,
-            source,
-        })?;
-
-        if verify_artifact(&target, artifact).is_ok() {
-            return Ok(target);
-        }
-
-        sweep_stale_install_files(&root, artifact.filename)?;
-        let (temporary, mut output) = create_temporary_file(&root, artifact.filename)?;
-        let result = (|| {
-            let mut limited = reader.by_ref().take(artifact.size.saturating_add(1));
-            let (size, digest) =
-                copy_and_hash(&mut limited, &mut output).map_err(|source| ModelStoreError::Io {
-                    path: temporary.clone(),
-                    source,
-                })?;
-            output.sync_all().map_err(|source| ModelStoreError::Io {
-                path: temporary.clone(),
-                source,
-            })?;
-            validate_size_and_hash(artifact, size, &digest, &temporary)?;
-
-            replace_file_atomic(&temporary, &target).map_err(|source| ModelStoreError::Io {
-                path: target.clone(),
-                source,
-            })?;
-            Ok(target.clone())
-        })();
-
-        if result.is_err() {
-            let _ = fs::remove_file(&temporary);
-        }
-        result
+        let _lock = lock_artifact(&root, artifact)?;
+        install_locked(&root, artifact, &mut reader)
     }
 
     fn manifest_cache_root(&self, manifest: &ModelManifest) -> PathBuf {
@@ -278,6 +290,43 @@ impl ModelStore {
     }
 }
 
+/// Failures while resolving or lazily acquiring a model set.
+#[derive(Debug, Error)]
+#[non_exhaustive]
+pub enum ModelAcquireError<E>
+where
+    E: std::error::Error + Send + Sync + 'static,
+{
+    /// Manifest validation, cache verification, or installation failed.
+    #[error(transparent)]
+    Store(#[from] ModelStoreError),
+    /// A managed-cache artifact could not be downloaded.
+    #[error("failed to download {kind:?} from {url}: {source}")]
+    Download {
+        /// Artifact role.
+        kind: ModelArtifactKind,
+        /// Pinned source URL.
+        url: &'static str,
+        /// Downloader failure.
+        #[source]
+        source: E,
+    },
+    /// Offline policy prevented acquisition of an unavailable artifact.
+    #[error("model artifacts are unavailable and downloads are disabled: {source}")]
+    DownloadsDisabled {
+        /// Original verification failure.
+        #[source]
+        source: ModelStoreError,
+    },
+    /// An explicit package-managed directory was incomplete or invalid.
+    #[error("explicit model directory is incomplete or invalid: {source}")]
+    ExplicitDirectoryIncomplete {
+        /// Original verification failure.
+        #[source]
+        source: ModelStoreError,
+    },
+}
+
 /// Failures while validating or installing model artifacts.
 #[derive(Debug, Error)]
 #[non_exhaustive]
@@ -333,6 +382,17 @@ pub enum ModelStoreError {
     },
 }
 
+impl ModelStoreError {
+    fn permits_download_recovery(&self) -> bool {
+        matches!(
+            self,
+            Self::MissingArtifact { .. }
+                | Self::SizeMismatch { .. }
+                | Self::ChecksumMismatch { .. }
+        )
+    }
+}
+
 fn validate_manifest(manifest: &ModelManifest) -> Result<(), ModelStoreError> {
     if manifest.schema_version != 1 {
         return Err(ModelStoreError::InvalidManifest(format!(
@@ -403,6 +463,67 @@ fn is_single_normal_path_component(value: &str) -> bool {
     matches!(components.next(), Some(Component::Normal(_))) && components.next().is_none()
 }
 
+fn lock_artifact(root: &Path, artifact: &ModelArtifact) -> Result<File, ModelStoreError> {
+    fs::create_dir_all(root).map_err(|source| ModelStoreError::Io {
+        path: root.to_path_buf(),
+        source,
+    })?;
+    let lock_path = root.join(format!(".{}.lock", artifact.filename));
+    let lock = OpenOptions::new()
+        .create(true)
+        .read(true)
+        .write(true)
+        .truncate(false)
+        .open(&lock_path)
+        .map_err(|source| ModelStoreError::Io {
+            path: lock_path.clone(),
+            source,
+        })?;
+    FileExt::lock_exclusive(&lock).map_err(|source| ModelStoreError::Io {
+        path: lock_path,
+        source,
+    })?;
+    Ok(lock)
+}
+
+fn install_locked(
+    root: &Path,
+    artifact: &ModelArtifact,
+    mut reader: impl Read,
+) -> Result<PathBuf, ModelStoreError> {
+    let target = root.join(artifact.filename);
+    if verify_artifact(&target, artifact).is_ok() {
+        return Ok(target);
+    }
+
+    sweep_stale_install_files(root, artifact.filename)?;
+    let (temporary, mut output) = create_temporary_file(root, artifact.filename)?;
+    let result = (|| {
+        let mut limited = reader.by_ref().take(artifact.size.saturating_add(1));
+        let (size, digest) =
+            copy_and_hash(&mut limited, &mut output).map_err(|source| ModelStoreError::Io {
+                path: temporary.clone(),
+                source,
+            })?;
+        output.sync_all().map_err(|source| ModelStoreError::Io {
+            path: temporary.clone(),
+            source,
+        })?;
+        validate_size_and_hash(artifact, size, &digest, &temporary)?;
+
+        replace_file_atomic(&temporary, &target).map_err(|source| ModelStoreError::Io {
+            path: target.clone(),
+            source,
+        })?;
+        Ok(target.clone())
+    })();
+
+    if result.is_err() {
+        let _ = fs::remove_file(&temporary);
+    }
+    result
+}
+
 fn sweep_stale_install_files(root: &Path, filename: &str) -> Result<(), ModelStoreError> {
     let prefix = format!(".{filename}.");
     for entry in fs::read_dir(root).map_err(|source| ModelStoreError::Io {
@@ -601,6 +722,34 @@ mod tests {
         artifacts: TEST_ARTIFACTS,
     };
 
+    #[derive(Debug)]
+    struct StaticDownloader {
+        bytes: &'static [u8],
+        requests: std::sync::Mutex<Vec<ModelArtifactKind>>,
+    }
+
+    impl StaticDownloader {
+        fn new(bytes: &'static [u8]) -> Self {
+            Self {
+                bytes,
+                requests: std::sync::Mutex::new(Vec::new()),
+            }
+        }
+
+        fn request_count(&self) -> usize {
+            self.requests.lock().unwrap().len()
+        }
+    }
+
+    impl ModelDownloader for StaticDownloader {
+        type Error = io::Error;
+
+        fn open(&self, artifact: &ModelArtifact) -> Result<Box<dyn Read + Send>, Self::Error> {
+            self.requests.lock().unwrap().push(artifact.kind);
+            Ok(Box::new(io::Cursor::new(self.bytes)))
+        }
+    }
+
     #[test]
     fn pinned_pp_ocr_manifest_is_well_formed() {
         validate_manifest(&PP_OCR_V6_SMALL).unwrap();
@@ -764,4 +913,93 @@ mod tests {
         assert_eq!(first, second);
         assert_eq!(fs::read(first).unwrap(), b"hello");
     }
+
+    #[test]
+    fn resolve_or_download_fetches_once_then_reuses_verified_cache() {
+        let temp = tempfile::tempdir().unwrap();
+        let store = ModelStore::new(temp.path());
+        let downloader = StaticDownloader::new(b"hello");
+
+        let first = store
+            .resolve_or_download(&TEST_MANIFEST, ModelDownloadPolicy::IfMissing, &downloader)
+            .unwrap();
+        let second = store
+            .resolve_or_download(&TEST_MANIFEST, ModelDownloadPolicy::IfMissing, &downloader)
+            .unwrap();
+        assert_eq!(first, second);
+        assert_eq!(downloader.request_count(), 1);
+    }
+
+    #[test]
+    fn concurrent_resolve_downloads_once_under_the_artifact_lock() {
+        let temp = tempfile::tempdir().unwrap();
+        let store = ModelStore::new(temp.path());
+        let downloader = std::sync::Arc::new(StaticDownloader::new(b"hello"));
+        let barrier = std::sync::Arc::new(std::sync::Barrier::new(3));
+
+        let handles: Vec<_> = (0..2)
+            .map(|_| {
+                let store = store.clone();
+                let downloader = std::sync::Arc::clone(&downloader);
+                let barrier = std::sync::Arc::clone(&barrier);
+                std::thread::spawn(move || {
+                    barrier.wait();
+                    store.resolve_or_download(
+                        &TEST_MANIFEST,
+                        ModelDownloadPolicy::IfMissing,
+                        downloader.as_ref(),
+                    )
+                })
+            })
+            .collect();
+        barrier.wait();
+        for handle in handles {
+            handle.join().unwrap().unwrap();
+        }
+        assert_eq!(downloader.request_count(), 1);
+    }
+
+    #[cfg(unix)]
+    #[test]
+    fn cache_io_failures_do_not_trigger_downloads() {
+        use std::os::unix::fs::symlink;
+
+        let temp = tempfile::tempdir().unwrap();
+        let store = ModelStore::new(temp.path());
+        let root = store.manifest_cache_root(&TEST_MANIFEST);
+        fs::create_dir_all(&root).unwrap();
+        symlink("hello.txt", root.join("hello.txt")).unwrap();
+        let downloader = StaticDownloader::new(b"hello");
+
+        assert!(matches!(
+            store.resolve_or_download(&TEST_MANIFEST, ModelDownloadPolicy::IfMissing, &downloader,),
+            Err(ModelAcquireError::Store(ModelStoreError::Io { .. }))
+        ));
+        assert_eq!(downloader.request_count(), 0);
+    }
+
+    #[test]
+    fn resolve_or_download_honors_offline_and_explicit_directory_boundaries() {
+        let cache = tempfile::tempdir().unwrap();
+        let override_dir = tempfile::tempdir().unwrap();
+        let downloader = StaticDownloader::new(b"hello");
+
+        let offline = ModelStore::new(cache.path())
+            .resolve_or_download(&TEST_MANIFEST, ModelDownloadPolicy::Offline, &downloader)
+            .unwrap_err();
+        assert!(matches!(
+            offline,
+            ModelAcquireError::DownloadsDisabled { .. }
+        ));
+
+        let explicit = ModelStore::new(cache.path())
+            .override_root(override_dir.path())
+            .resolve_or_download(&TEST_MANIFEST, ModelDownloadPolicy::IfMissing, &downloader)
+            .unwrap_err();
+        assert!(matches!(
+            explicit,
+            ModelAcquireError::ExplicitDirectoryIncomplete { .. }
+        ));
+        assert_eq!(downloader.request_count(), 0);
+    }
 }

src/vision/oar.rs

@@ -4,6 +4,7 @@ use std::path::PathBuf;
 use std::time::Instant;
 
 use image::RgbImage;
+use oar_ocr::core::config::onnx::OrtSessionConfig;
 use oar_ocr::oarocr::{OAROCRBuilder, OAROCR};
 use oar_ocr::processors::BoundingBox;
 use thiserror::Error;
@@ -86,7 +87,13 @@ impl OarOcrEngine {
         let recognition = required_model(models, ModelArtifactKind::TextRecognition)?;
         let dictionary = required_model(models, ModelArtifactKind::CharacterDictionary)?;
 
-        let pipeline = OAROCRBuilder::new(detection, recognition, dictionary).build()?;
+        let pipeline = OAROCRBuilder::new(detection, recognition, dictionary)
+            .ort_session(ocr_session_config())
+            // Document line crops often have very different widths. Keeping
+            // CPU recognition batches at one avoids padding every crop to the
+            // widest line, reducing both inference work and peak memory.
+            .region_batch_size(1)
+            .build()?;
         let model = ModelIdentity::new(models.manifest_id(), models.revision());
         Ok(Self { pipeline, model })
     }
@@ -169,11 +176,18 @@ impl OarOcrEngine {
     }
 }
 
+fn ocr_session_config() -> OrtSessionConfig {
+    let available = std::thread::available_parallelism()
+        .map(std::num::NonZeroUsize::get)
+        .unwrap_or(1);
+    OrtSessionConfig::new()
+        .with_intra_threads(available.min(4))
+        .with_inter_threads(1)
+        .with_parallel_execution(false)
+}
+
 fn load_onnx_runtime() -> Result<(), OarOcrError> {
-    let path = std::env::var_os(ONNX_RUNTIME_LIBRARY_ENV)
-        .filter(|path| !path.is_empty())
-        .map(PathBuf::from)
-        .unwrap_or_else(default_onnx_runtime_library);
+    let path = onnx_runtime_library_path();
     drop(
         ort::init_from(&path).map_err(|source| OarOcrError::OnnxRuntimeLoad {
             path: path.clone(),
@@ -183,6 +197,13 @@ fn load_onnx_runtime() -> Result<(), OarOcrError> {
     Ok(())
 }
 
+pub(crate) fn onnx_runtime_library_path() -> PathBuf {
+    std::env::var_os(ONNX_RUNTIME_LIBRARY_ENV)
+        .filter(|path| !path.is_empty())
+        .map(PathBuf::from)
+        .unwrap_or_else(default_onnx_runtime_library)
+}
+
 fn default_onnx_runtime_library() -> PathBuf {
     #[cfg(target_os = "windows")]
     const NAME: &str = "onnxruntime.dll";
@@ -355,6 +376,14 @@ mod tests {
     use super::*;
     use crate::vision::PageTransform;
 
+    #[test]
+    fn cpu_session_budget_is_bounded_for_small_ocr_models() {
+        let config = ocr_session_config();
+        assert!((1..=4).contains(&config.intra_threads.unwrap()));
+        assert_eq!(config.inter_threads, Some(1));
+        assert_eq!(config.parallel_execution, Some(false));
+    }
+
     fn page(format: RenderPixelFormat, stride: usize, pixels: Vec<u8>) -> RenderedPage {
         let transform =
             PageTransform::from_corners(2, 2, (0.0, 2.0), (2.0, 2.0), (0.0, 0.0)).unwrap();

src/vision/pipeline.rs

@@ -0,0 +1,533 @@
+//! One-call native extraction and OCR pipeline.
+
+use std::collections::BTreeSet;
+use std::path::{Path, PathBuf};
+use std::sync::{Arc, Mutex, OnceLock};
+use std::time::Instant;
+
+use thiserror::Error;
+
+use crate::{MarkdownOptions, PageOcrReasons, PdfError};
+
+use super::oar::onnx_runtime_library_path;
+use super::{
+    fuse_ocr_pages, 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,
+};
+
+#[derive(Debug, Clone, PartialEq, Eq)]
+struct OcrEngineCacheKey {
+    model_root: PathBuf,
+    runtime_library: PathBuf,
+    manifest_schema: u32,
+    manifest_id: &'static str,
+    manifest_revision: &'static str,
+    artifact_digests: Vec<&'static str>,
+}
+
+#[derive(Debug)]
+struct CachedOcrEngine {
+    key: OcrEngineCacheKey,
+    engine: Arc<OarOcrEngine>,
+}
+
+static OCR_ENGINE_CACHE: OnceLock<Mutex<Option<CachedOcrEngine>>> = OnceLock::new();
+
+/// Options for native extraction with optional OCR.
+#[derive(Clone)]
+pub struct OcrPdfOptions {
+    /// Page rasterization settings used when OCR is routed.
+    pub render: RenderOptions,
+    /// OCR routing, model, and recognition settings.
+    pub ocr: OcrOptions,
+    /// Markdown formatting shared by native and OCR assembly.
+    pub markdown: MarkdownOptions,
+    /// Optional 1-indexed page selection. `None` processes the full document.
+    pub page_filter: Option<BTreeSet<u32>>,
+    /// Password for an encrypted PDF.
+    pub password: Option<String>,
+    /// Weak OCR threshold for recommending the hosted pipeline.
+    pub hosted_recommendation_confidence: f32,
+}
+
+impl Default for OcrPdfOptions {
+    fn default() -> Self {
+        Self {
+            render: RenderOptions::default(),
+            ocr: OcrOptions::default(),
+            markdown: MarkdownOptions::default(),
+            page_filter: None,
+            password: None,
+            hosted_recommendation_confidence: 0.5,
+        }
+    }
+}
+
+impl std::fmt::Debug for OcrPdfOptions {
+    fn fmt(&self, formatter: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        formatter
+            .debug_struct("OcrPdfOptions")
+            .field("render", &self.render)
+            .field("ocr", &self.ocr)
+            .field("markdown", &self.markdown)
+            .field("page_filter", &self.page_filter)
+            .field("password", &self.password.as_ref().map(|_| "[REDACTED]"))
+            .field(
+                "hosted_recommendation_confidence",
+                &self.hosted_recommendation_confidence,
+            )
+            .finish()
+    }
+}
+
+impl OcrPdfOptions {
+    /// Creates options with OCR disabled, preserving the native-only path.
+    pub fn new() -> Self {
+        Self::default()
+    }
+
+    /// Replaces page rasterization settings.
+    pub fn render(mut self, render: RenderOptions) -> Self {
+        self.render = render;
+        self
+    }
+
+    /// Replaces OCR routing and recognition settings.
+    pub fn ocr(mut self, ocr: OcrOptions) -> Self {
+        self.ocr = ocr;
+        self
+    }
+
+    /// Sets OCR routing without changing the remaining OCR settings.
+    pub fn mode(mut self, mode: OcrMode) -> Self {
+        self.ocr.mode = mode;
+        self
+    }
+
+    /// Replaces Markdown formatting options.
+    pub fn markdown(mut self, markdown: MarkdownOptions) -> Self {
+        self.markdown = markdown;
+        self
+    }
+
+    /// Restricts processing to 1-indexed pages in ascending order.
+    pub fn pages(mut self, pages: impl IntoIterator<Item = u32>) -> Self {
+        self.page_filter = Some(pages.into_iter().collect());
+        self
+    }
+
+    /// Sets the password used to decrypt the PDF.
+    pub fn password(mut self, password: impl Into<String>) -> Self {
+        self.password = Some(password.into());
+        self
+    }
+
+    /// Sets the weak-OCR threshold for recommending hosted document parsing.
+    pub fn hosted_recommendation_confidence(mut self, confidence: f32) -> Self {
+        self.hosted_recommendation_confidence = confidence;
+        self
+    }
+}
+
+/// Complete native/OCR Markdown output for a PDF request.
+#[derive(Debug, Clone, PartialEq)]
+pub struct OcrPdfResult {
+    /// Final document Markdown in selected-page order.
+    pub markdown: String,
+    /// Final per-page Markdown and provenance, using 1-indexed page numbers.
+    pub pages: Vec<FusedPageMarkdown>,
+    /// Total pages in the PDF, independent of page selection.
+    pub page_count: u32,
+    /// 1-indexed selected pages recommended for OCR by native extraction.
+    pub pages_recommended_for_ocr: Vec<u32>,
+    /// 1-indexed pages actually rendered and recognized.
+    pub pages_routed_to_ocr: Vec<u32>,
+    /// 1-indexed pages whose OCR result recommends hosted document parsing.
+    pub pages_recommending_hosted: Vec<u32>,
+    /// Original machine-readable OCR reasons for selected pages.
+    pub ocr_reasons_by_page: Vec<PageOcrReasons>,
+    /// Selected pages where deterministic table detection found tables.
+    pub pages_with_tables: Vec<u32>,
+    /// Selected pages where deterministic layout found multiple columns.
+    pub pages_with_columns: Vec<u32>,
+    /// Whether deterministic extraction found tables or columns.
+    pub is_complex: bool,
+    /// End-to-end processing time.
+    pub processing_time_ms: u64,
+    /// Batch page-rendering time; zero when no OCR work was routed.
+    pub render_time_ms: u64,
+    /// Batch OCR time; zero when no OCR work was routed.
+    pub ocr_time_ms: u64,
+}
+
+/// Processes a PDF file through native extraction and selective OCR.
+pub fn process_pdf_with_ocr(
+    path: impl AsRef<Path>,
+    options: OcrPdfOptions,
+) -> Result<OcrPdfResult, OcrPipelineError> {
+    let bytes = std::fs::read(path).map_err(PdfError::from)?;
+    process_pdf_with_ocr_mem(&bytes, options)
+}
+
+/// Processes PDF bytes through native extraction and selective OCR.
+///
+/// Native extraction always runs first. `Auto` initializes PDFium, downloads
+/// models, and starts OAR only if the detector selected at least one page.
+/// `Off` therefore has no renderer, model-cache, network, or inference side
+/// effects even though the complete feature is compiled into the application.
+pub fn process_pdf_with_ocr_mem(
+    buffer: &[u8],
+    options: OcrPdfOptions,
+) -> Result<OcrPdfResult, OcrPipelineError> {
+    OcrFusionOptions::new()
+        .render_dpi(options.render.dpi)
+        .hosted_recommendation_confidence(options.hosted_recommendation_confidence)
+        .validate()?;
+    let minimum_confidence = options.ocr.minimum_confidence;
+    if !minimum_confidence.is_finite() || !(0.0..=1.0).contains(&minimum_confidence) {
+        return Err(OcrPipelineError::InvalidMinimumConfidence {
+            value: minimum_confidence,
+        });
+    }
+    if options
+        .page_filter
+        .as_ref()
+        .is_some_and(|pages| pages.contains(&0))
+    {
+        return Err(OcrPipelineError::InvalidSelectedPage { page: 0 });
+    }
+
+    let started = Instant::now();
+    let selected_pages: Option<Vec<u32>> = options
+        .page_filter
+        .as_ref()
+        .map(|pages| pages.iter().copied().collect());
+    let selected_pages_zero_indexed: Option<Vec<u32>> = selected_pages
+        .as_ref()
+        .map(|pages| pages.iter().map(|page| page - 1).collect());
+
+    let mut page_markdown_options = options.markdown.clone();
+    page_markdown_options.include_page_numbers = false;
+    let (native, page_count) = crate::extract_pages_markdown_mem_for_ocr(
+        buffer,
+        selected_pages_zero_indexed.as_deref(),
+        options.password.as_deref(),
+        &page_markdown_options,
+    )?;
+    if let Some(invalid) = selected_pages
+        .as_ref()
+        .and_then(|pages| pages.iter().copied().find(|page| *page > page_count))
+    {
+        return Err(OcrPipelineError::InvalidSelectedPage { page: invalid });
+    }
+
+    let routed = route_ocr_pages(
+        options.ocr.mode,
+        page_count,
+        &native.pages_needing_ocr,
+        selected_pages.as_deref(),
+    )?;
+
+    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.
+        let renderer = PdfiumRenderer::load()?;
+        let engine = cached_ocr_engine(&options.ocr)?;
+        run_ocr_pages(
+            &renderer,
+            engine.as_ref(),
+            buffer,
+            &routed,
+            options.password.as_deref(),
+            &options.render,
+            &options.ocr,
+        )?
+    };
+
+    let fusion_options = OcrFusionOptions::new()
+        .markdown(page_markdown_options)
+        .render_dpi(options.render.dpi)
+        .hosted_recommendation_confidence(options.hosted_recommendation_confidence);
+    let fused = fuse_ocr_pages(&native.pages, &ocr_run, page_count, &fusion_options)?;
+    let pages_recommending_hosted = fused
+        .pages
+        .iter()
+        .filter(|page| page.provenance.hosted_recommended)
+        .map(|page| page.provenance.page)
+        .collect();
+    let markdown = assemble_document_markdown(&fused.pages, options.markdown.include_page_numbers);
+
+    Ok(OcrPdfResult {
+        markdown,
+        pages: fused.pages,
+        page_count,
+        pages_recommended_for_ocr: native.pages_needing_ocr,
+        pages_routed_to_ocr: routed,
+        pages_recommending_hosted,
+        ocr_reasons_by_page: native.ocr_reasons_by_page,
+        pages_with_tables: native.pages_with_tables,
+        pages_with_columns: native.pages_with_columns,
+        is_complex: native.is_complex,
+        processing_time_ms: elapsed_ms(started),
+        render_time_ms: fused.render_time_ms,
+        ocr_time_ms: fused.ocr_time_ms,
+    })
+}
+
+fn cached_ocr_engine(options: &OcrOptions) -> Result<Arc<OarOcrEngine>, OcrPipelineError> {
+    let store = ModelStore::from_options(options)?;
+    let key = OcrEngineCacheKey {
+        model_root: normalized_cache_path(store.model_root(&PP_OCR_V6_SMALL)),
+        runtime_library: normalized_cache_path(onnx_runtime_library_path()),
+        manifest_schema: PP_OCR_V6_SMALL.schema_version,
+        manifest_id: PP_OCR_V6_SMALL.id,
+        manifest_revision: PP_OCR_V6_SMALL.revision,
+        artifact_digests: PP_OCR_V6_SMALL
+            .artifacts
+            .iter()
+            .map(|artifact| artifact.sha256)
+            .collect(),
+    };
+    let cache = OCR_ENGINE_CACHE.get_or_init(|| Mutex::new(None));
+    {
+        let cached = cache.lock().unwrap_or_else(|error| error.into_inner());
+        if let Some(cached) = cached.as_ref().filter(|cached| cached.key == key) {
+            return Ok(Arc::clone(&cached.engine));
+        }
+    }
+
+    // The loaded sessions own the verified model data, so a cache hit never
+    // needs to trust or reopen mutable files on disk. Do the expensive download
+    // and session construction outside the process-wide cache lock so unrelated
+    // OCR requests can continue using a warm engine. Concurrent cold misses may
+    // build redundantly; the second cache check keeps only one shared session.
+    let models = store.resolve_or_download(
+        &PP_OCR_V6_SMALL,
+        options.model_downloads,
+        &HttpModelDownloader::default(),
+    )?;
+    let engine = Arc::new(OarOcrEngine::from_models(&models)?);
+
+    let mut cached = cache.lock().unwrap_or_else(|error| error.into_inner());
+    if let Some(cached) = cached.as_ref().filter(|cached| cached.key == key) {
+        return Ok(Arc::clone(&cached.engine));
+    }
+    *cached = Some(CachedOcrEngine {
+        key,
+        engine: Arc::clone(&engine),
+    });
+    Ok(engine)
+}
+
+fn normalized_cache_path(path: PathBuf) -> PathBuf {
+    let absolute = if path.is_absolute() {
+        path
+    } else {
+        std::env::current_dir()
+            .map(|directory| directory.join(&path))
+            .unwrap_or(path)
+    };
+    if let Ok(canonical) = std::fs::canonicalize(&absolute) {
+        return canonical;
+    }
+
+    // A managed cache often does not exist on the first request. Resolve the
+    // nearest existing ancestor so a relative path has the same key before
+    // and after model acquisition creates its final directories.
+    let mut ancestor = absolute.as_path();
+    let mut suffix = Vec::new();
+    while let Some(name) = ancestor.file_name() {
+        suffix.push(name.to_os_string());
+        let Some(parent) = ancestor.parent() else {
+            break;
+        };
+        ancestor = parent;
+        if let Ok(mut canonical) = std::fs::canonicalize(ancestor) {
+            for component in suffix.iter().rev() {
+                canonical.push(component);
+            }
+            return canonical;
+        }
+    }
+    absolute
+}
+
+fn assemble_document_markdown(pages: &[FusedPageMarkdown], include_page_numbers: bool) -> String {
+    let mut document = String::new();
+    for (index, page) in pages.iter().enumerate() {
+        if index > 0 {
+            document.push_str("\n\n");
+        }
+        if include_page_numbers {
+            document.push_str(&format!("<!-- Page {} -->\n\n", page.page));
+        }
+        document.push_str(page.markdown.trim());
+    }
+    if !document.is_empty() {
+        document.push('\n');
+    }
+    document
+}
+
+fn elapsed_ms(started: Instant) -> u64 {
+    u64::try_from(started.elapsed().as_millis()).unwrap_or(u64::MAX)
+}
+
+/// Failures from the complete OCR pipeline.
+#[derive(Debug, Error)]
+#[non_exhaustive]
+pub enum OcrPipelineError {
+    /// PDF loading or native extraction failed.
+    #[error(transparent)]
+    Pdf(#[from] PdfError),
+    /// Page routing rejected an invalid request.
+    #[error(transparent)]
+    Routing(#[from] OcrRoutingError),
+    /// The model cache could not be located or initialized.
+    #[error(transparent)]
+    ModelStore(#[from] ModelStoreError),
+    /// A pinned model set could not be resolved or acquired.
+    #[error(transparent)]
+    ModelAcquire(#[from] ModelAcquireError<HttpModelDownloadError>),
+    /// PDFium could not load or rasterize the request.
+    #[error(transparent)]
+    Render(#[from] RenderError),
+    /// The OAR engine could not initialize.
+    #[error(transparent)]
+    Oar(#[from] OarOcrError),
+    /// Selective rendering or OCR execution failed.
+    #[error(transparent)]
+    Run(#[from] OcrRunError),
+    /// OCR/native Markdown fusion failed.
+    #[error(transparent)]
+    Fusion(#[from] OcrFusionError),
+    /// Page zero is invalid because public page selections are 1-indexed.
+    #[error("selected page {page} is invalid; page numbers are 1-indexed")]
+    InvalidSelectedPage {
+        /// Invalid page number.
+        page: u32,
+    },
+    /// OCR span confidence is outside the inclusive 0–1 range.
+    #[error("minimum OCR confidence must be between 0 and 1, got {value}")]
+    InvalidMinimumConfidence {
+        /// Invalid value.
+        value: f32,
+    },
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn cache_path_is_stable_when_a_relative_directory_is_created() {
+        let current = std::fs::canonicalize(std::env::current_dir().unwrap()).unwrap();
+        let temporary = tempfile::tempdir_in(&current).unwrap();
+        let relative_root = temporary.path().strip_prefix(&current).unwrap();
+        let relative = relative_root.join("models").join("revision");
+
+        let before = normalized_cache_path(relative.clone());
+        std::fs::create_dir_all(&relative).unwrap();
+        let after = normalized_cache_path(relative);
+
+        assert!(before.is_absolute());
+        assert_eq!(before, after);
+    }
+
+    #[test]
+    fn off_mode_extracts_native_text_without_runtime_side_effects() {
+        let bytes = std::fs::read("tests/fixtures/thermo-freon12.pdf").unwrap();
+        let result = process_pdf_with_ocr_mem(&bytes, OcrPdfOptions::new()).unwrap();
+
+        assert_eq!(result.page_count, 3);
+        assert_eq!(result.pages.len(), 3);
+        assert!(result.markdown.contains("Thermodynamic Properties"));
+        assert!(result.pages_recommended_for_ocr.is_empty());
+        assert!(result.pages_routed_to_ocr.is_empty());
+        assert!(result.pages_recommending_hosted.is_empty());
+        assert_eq!(result.render_time_ms, 0);
+        assert_eq!(result.ocr_time_ms, 0);
+    }
+
+    #[test]
+    fn auto_mode_does_not_load_pdfium_or_models_for_clean_pdf() {
+        let bytes = std::fs::read("tests/fixtures/thermo-freon12.pdf").unwrap();
+        let result =
+            process_pdf_with_ocr_mem(&bytes, OcrPdfOptions::new().mode(OcrMode::Auto)).unwrap();
+
+        assert!(result.pages_routed_to_ocr.is_empty());
+        assert!(result.markdown.contains("Freon 12"));
+    }
+
+    #[test]
+    fn selection_and_page_markers_use_public_one_indexed_pages() {
+        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().pages([2]).markdown(markdown))
+                .unwrap();
+
+        assert_eq!(result.pages.len(), 1);
+        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 -->"));
+    }
+
+    #[test]
+    fn off_mode_marks_unprocessed_scan_for_hosted_fallback() {
+        let bytes = std::fs::read("tests/fixtures/scan_with_native_header_text.pdf").unwrap();
+        let result = process_pdf_with_ocr_mem(&bytes, OcrPdfOptions::new()).unwrap();
+
+        assert!(result.pages_routed_to_ocr.is_empty());
+        assert_eq!(result.pages_recommending_hosted, vec![1]);
+    }
+
+    #[test]
+    fn password_is_redacted_and_used_for_native_extraction() {
+        let options = OcrPdfOptions::new().password("secret123");
+        assert!(!format!("{options:?}").contains("secret123"));
+
+        let bytes = std::fs::read("tests/fixtures/encrypted-secret123.pdf").unwrap();
+        let result = process_pdf_with_ocr_mem(&bytes, options).unwrap();
+        assert!(result.markdown.contains("Procurement"));
+    }
+
+    #[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().pages([4])).unwrap_err();
+        assert!(matches!(
+            error,
+            OcrPipelineError::InvalidSelectedPage { page: 4 }
+        ));
+    }
+
+    #[test]
+    fn invalid_expensive_options_fail_before_pdf_or_runtime_access() {
+        let mut invalid_dpi = OcrPdfOptions::new();
+        invalid_dpi.render.dpi = f32::NAN;
+        assert!(matches!(
+            process_pdf_with_ocr_mem(b"not a PDF", invalid_dpi),
+            Err(OcrPipelineError::Fusion(
+                OcrFusionError::InvalidRenderDpi { .. }
+            ))
+        ));
+
+        let invalid_hosted = OcrPdfOptions::new().hosted_recommendation_confidence(1.1);
+        assert!(matches!(
+            process_pdf_with_ocr_mem(b"not a PDF", invalid_hosted),
+            Err(OcrPipelineError::Fusion(
+                OcrFusionError::InvalidHostedConfidence { .. }
+            ))
+        ));
+    }
+}

src/vision/routing.rs

@@ -0,0 +1,380 @@
+//! Page routing and renderer/OCR orchestration without Markdown fusion.
+
+use std::collections::BTreeSet;
+use std::error::Error;
+use std::time::Instant;
+
+use thiserror::Error;
+
+use super::{OcrEngine, OcrMode, OcrOptions, OcrPage, PageRenderer, RenderOptions, RenderedPage};
+
+/// A rendered page paired with OCR output in the same bitmap coordinate space.
+#[derive(Debug)]
+pub struct RoutedOcrPage {
+    /// Renderer-owned bitmap and pixel↔PDF transform.
+    pub rendered: RenderedPage,
+    /// Positioned OCR spans for the bitmap.
+    pub ocr: OcrPage,
+}
+
+/// Output of one selective OCR invocation.
+#[derive(Debug)]
+pub struct OcrRun {
+    /// Pages processed in ascending document order.
+    pub pages: Vec<RoutedOcrPage>,
+    /// Total page-rendering wall time.
+    pub render_time_ms: u64,
+    /// Total engine wall time.
+    pub ocr_time_ms: u64,
+}
+
+/// Selects 1-indexed pages for OCR.
+///
+/// `recommended_pages` comes from pdf-inspector's existing detector/text
+/// quality signals. `selected_pages` is an optional user page filter. Results
+/// are validated, deduplicated, and returned in document order.
+pub fn route_ocr_pages(
+    mode: OcrMode,
+    page_count: u32,
+    recommended_pages: &[u32],
+    selected_pages: Option<&[u32]>,
+) -> Result<Vec<u32>, OcrRoutingError> {
+    match mode {
+        OcrMode::Off => Ok(Vec::new()),
+        OcrMode::Auto => {
+            let mut routed = validated_page_set("recommended", recommended_pages, page_count)?;
+            if let Some(selected) = selected_pages {
+                let selected = validated_page_set("selected", selected, page_count)?;
+                routed.retain(|page| selected.contains(page));
+            }
+            Ok(routed.into_iter().collect())
+        }
+        OcrMode::Force => {
+            let routed = selected_pages
+                .map(|pages| validated_page_set("selected", pages, page_count))
+                .transpose()?
+                .unwrap_or_else(|| (1..=page_count).collect());
+            Ok(routed.into_iter().collect())
+        }
+    }
+}
+
+/// Renders and recognizes already-routed pages while retaining transforms for
+/// the following fusion layer.
+///
+/// An empty page list returns without calling either dependency, which keeps
+/// model resolution and inference lazy when Auto routing finds no OCR work.
+#[allow(clippy::too_many_arguments)]
+pub fn run_ocr_pages<R, O>(
+    renderer: &R,
+    engine: &O,
+    pdf_bytes: &[u8],
+    pages: &[u32],
+    password: Option<&str>,
+    render_options: &RenderOptions,
+    ocr_options: &OcrOptions,
+) -> Result<OcrRun, OcrRunError>
+where
+    R: PageRenderer,
+    O: OcrEngine,
+{
+    if pages.is_empty() {
+        return Ok(OcrRun {
+            pages: Vec::new(),
+            render_time_ms: 0,
+            ocr_time_ms: 0,
+        });
+    }
+    if ocr_options.mode == OcrMode::Off {
+        return Err(OcrRunError::OcrDisabled);
+    }
+
+    let render_started = Instant::now();
+    let rendered = renderer
+        .render_pages(pdf_bytes, pages, password, render_options)
+        .map_err(|source| OcrRunError::Render {
+            source: Box::new(source),
+        })?;
+    let render_time_ms = elapsed_ms(render_started);
+    validate_page_order("renderer", pages, rendered.iter().map(RenderedPage::page))?;
+
+    let ocr_started = Instant::now();
+    let recognized =
+        engine
+            .recognize(&rendered, ocr_options)
+            .map_err(|source| OcrRunError::Ocr {
+                source: Box::new(source),
+            })?;
+    let ocr_time_ms = elapsed_ms(ocr_started);
+    validate_page_order("OCR engine", pages, recognized.iter().map(|page| page.page))?;
+
+    Ok(OcrRun {
+        pages: rendered
+            .into_iter()
+            .zip(recognized)
+            .map(|(rendered, ocr)| RoutedOcrPage { rendered, ocr })
+            .collect(),
+        render_time_ms,
+        ocr_time_ms,
+    })
+}
+
+/// Invalid page routing or renderer/engine contract output.
+#[derive(Debug, Error)]
+#[non_exhaustive]
+pub enum OcrRoutingError {
+    /// A page list contained zero or a page beyond the document.
+    #[error("{source_name} OCR page {page} is outside the valid range 1..={page_count}")]
+    InvalidPage {
+        /// Page-list source.
+        source_name: &'static str,
+        /// Invalid 1-indexed page.
+        page: u32,
+        /// Document page count.
+        page_count: u32,
+    },
+}
+
+/// Failures while rendering and recognizing a routed page set.
+#[derive(Debug, Error)]
+#[non_exhaustive]
+pub enum OcrRunError {
+    /// A non-empty route cannot execute with OCR disabled.
+    #[error("cannot process routed pages while OCR mode is Off")]
+    OcrDisabled,
+    /// Page rasterization failed.
+    #[error("page rendering failed: {source}")]
+    Render {
+        /// Renderer-specific failure.
+        #[source]
+        source: Box<dyn Error + Send + Sync>,
+    },
+    /// OCR inference failed.
+    #[error("OCR inference failed: {source}")]
+    Ocr {
+        /// Engine-specific failure.
+        #[source]
+        source: Box<dyn Error + Send + Sync>,
+    },
+    /// A dependency returned the wrong count or order.
+    #[error("{stage} returned pages {actual:?}; expected {expected:?}")]
+    PageOrderMismatch {
+        /// Dependency boundary that violated the contract.
+        stage: &'static str,
+        /// Requested 1-indexed pages.
+        expected: Vec<u32>,
+        /// Returned 1-indexed pages.
+        actual: Vec<u32>,
+    },
+}
+
+fn validated_page_set(
+    source_name: &'static str,
+    pages: &[u32],
+    page_count: u32,
+) -> Result<BTreeSet<u32>, OcrRoutingError> {
+    let mut result = BTreeSet::new();
+    for &page in pages {
+        if page == 0 || page > page_count {
+            return Err(OcrRoutingError::InvalidPage {
+                source_name,
+                page,
+                page_count,
+            });
+        }
+        result.insert(page);
+    }
+    Ok(result)
+}
+
+fn validate_page_order(
+    stage: &'static str,
+    expected: &[u32],
+    actual: impl IntoIterator<Item = u32>,
+) -> Result<(), OcrRunError> {
+    let actual: Vec<u32> = actual.into_iter().collect();
+    if actual == expected {
+        Ok(())
+    } else {
+        Err(OcrRunError::PageOrderMismatch {
+            stage,
+            expected: expected.to_vec(),
+            actual,
+        })
+    }
+}
+
+fn elapsed_ms(started: Instant) -> u64 {
+    u64::try_from(started.elapsed().as_millis()).unwrap_or(u64::MAX)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::vision::{
+        ImagePoint, ImageQuad, ModelIdentity, OcrSpan, PageTransform, RenderBufferError,
+        RenderPixelFormat,
+    };
+
+    #[derive(Debug, Error)]
+    #[error("fake failure")]
+    struct FakeError;
+
+    struct FakeRenderer;
+
+    impl PageRenderer for FakeRenderer {
+        type Error = FakeError;
+
+        fn render_pages(
+            &self,
+            _pdf_bytes: &[u8],
+            pages: &[u32],
+            _password: Option<&str>,
+            _options: &RenderOptions,
+        ) -> Result<Vec<RenderedPage>, Self::Error> {
+            pages
+                .iter()
+                .copied()
+                .map(rendered_page)
+                .collect::<Result<_, _>>()
+                .map_err(|_| FakeError)
+        }
+    }
+
+    struct FakeEngine {
+        model: ModelIdentity,
+    }
+
+    impl FakeEngine {
+        fn new() -> Self {
+            Self {
+                model: ModelIdentity::new("fake", "v1"),
+            }
+        }
+    }
+
+    impl OcrEngine for FakeEngine {
+        type Error = FakeError;
+
+        fn model(&self) -> &ModelIdentity {
+            &self.model
+        }
+
+        fn recognize(
+            &self,
+            pages: &[RenderedPage],
+            _options: &OcrOptions,
+        ) -> Result<Vec<OcrPage>, Self::Error> {
+            Ok(pages
+                .iter()
+                .map(|page| OcrPage {
+                    page: page.page(),
+                    spans: vec![OcrSpan {
+                        text: format!("page {}", page.page()),
+                        polygon: ImageQuad::new([
+                            ImagePoint::new(0.0, 0.0),
+                            ImagePoint::new(1.0, 0.0),
+                            ImagePoint::new(1.0, 1.0),
+                            ImagePoint::new(0.0, 1.0),
+                        ]),
+                        confidence: 0.9,
+                        orientation_degrees: None,
+                    }],
+                    mean_confidence: Some(0.9),
+                    model: self.model.clone(),
+                    processing_time_ms: 1,
+                    warnings: Vec::new(),
+                })
+                .collect())
+        }
+    }
+
+    fn rendered_page(page: u32) -> Result<RenderedPage, RenderBufferError> {
+        let transform =
+            PageTransform::from_corners(1, 1, (0.0, 1.0), (1.0, 1.0), (0.0, 0.0)).unwrap();
+        RenderedPage::new(
+            page,
+            1.0,
+            1.0,
+            1,
+            1,
+            3,
+            RenderPixelFormat::Rgb8,
+            vec![255; 3],
+            transform,
+        )
+    }
+
+    #[test]
+    fn off_auto_and_force_route_expected_pages() {
+        assert_eq!(
+            route_ocr_pages(OcrMode::Off, 0, &[99], Some(&[0])).unwrap(),
+            Vec::<u32>::new()
+        );
+        assert_eq!(
+            route_ocr_pages(OcrMode::Auto, 5, &[5, 3, 3, 1], Some(&[2, 3, 5])).unwrap(),
+            vec![3, 5]
+        );
+        assert_eq!(
+            route_ocr_pages(OcrMode::Force, 4, &[], None).unwrap(),
+            vec![1, 2, 3, 4]
+        );
+        assert_eq!(
+            route_ocr_pages(OcrMode::Force, 4, &[], Some(&[4, 2, 2])).unwrap(),
+            vec![2, 4]
+        );
+    }
+
+    #[test]
+    fn routing_rejects_invalid_page_numbers() {
+        assert!(matches!(
+            route_ocr_pages(OcrMode::Auto, 2, &[0], None),
+            Err(OcrRoutingError::InvalidPage { page: 0, .. })
+        ));
+        assert!(matches!(
+            route_ocr_pages(OcrMode::Force, 2, &[], Some(&[3])),
+            Err(OcrRoutingError::InvalidPage { page: 3, .. })
+        ));
+    }
+
+    #[test]
+    fn run_retains_render_transforms_and_input_order() {
+        let options = OcrOptions::new().mode(OcrMode::Auto);
+        let run = run_ocr_pages(
+            &FakeRenderer,
+            &FakeEngine::new(),
+            b"pdf",
+            &[2, 4],
+            None,
+            &RenderOptions::new(),
+            &options,
+        )
+        .unwrap();
+        assert_eq!(
+            run.pages
+                .iter()
+                .map(|page| page.rendered.page())
+                .collect::<Vec<_>>(),
+            vec![2, 4]
+        );
+        assert_eq!(run.pages[1].ocr.spans[0].text, "page 4");
+        assert_eq!(run.pages[1].rendered.pixel_to_page(0.0, 0.0).y, 1.0);
+    }
+
+    #[test]
+    fn empty_route_is_a_noop_even_when_ocr_is_off() {
+        let run = run_ocr_pages(
+            &FakeRenderer,
+            &FakeEngine::new(),
+            b"pdf",
+            &[],
+            None,
+            &RenderOptions::new(),
+            &OcrOptions::new(),
+        )
+        .unwrap();
+        assert!(run.pages.is_empty());
+        assert_eq!(run.render_time_ms, 0);
+        assert_eq!(run.ocr_time_ms, 0);
+    }
+}

tests/ocr_tests.rs

@@ -1,5 +1,9 @@
 #![cfg(all(feature = "ocr-oar", not(target_arch = "wasm32")))]
 
+#[cfg(feature = "ocr")]
+use pdf_inspector::vision::{
+    process_pdf_with_ocr_mem, ModelDownloadPolicy, OcrPdfOptions, PageContentSource,
+};
 use pdf_inspector::vision::{
     ModelStore, OarOcrEngine, OcrEngine, OcrMode, OcrOptions, PageTransform, RenderPixelFormat,
     RenderedPage, PP_OCR_V6_SMALL,
@@ -100,6 +104,37 @@ fn recognizes_a_pdfium_rendered_fixture_with_verified_models() {
     assert_usable_result(&results);
 }
 
+#[cfg(all(feature = "ocr", feature = "render-pdfium"))]
+#[test]
+fn complete_ocr_pipeline_routes_and_assembles_a_scanned_fixture() {
+    let Some(model_directory) = std::env::var_os(MODEL_DIRECTORY_ENV) else {
+        eprintln!("skipping OCR runtime test because {MODEL_DIRECTORY_ENV} is not set");
+        return;
+    };
+    let Some(_renderer) = load_renderer() else {
+        return;
+    };
+
+    let bytes = std::fs::read("tests/fixtures/scan_with_native_header_text.pdf").unwrap();
+    let ocr = OcrOptions::new()
+        .mode(OcrMode::Auto)
+        .minimum_confidence(0.3)
+        .model_directory(model_directory)
+        .model_downloads(ModelDownloadPolicy::Offline);
+    let options = OcrPdfOptions::new().ocr(ocr);
+    let result = process_pdf_with_ocr_mem(&bytes, options.clone()).unwrap();
+    let repeated = process_pdf_with_ocr_mem(&bytes, options).unwrap();
+
+    assert_eq!(result.pages_routed_to_ocr, vec![1]);
+    assert!(!result.markdown.trim().is_empty());
+    assert_eq!(result.pages[0].provenance.source, PageContentSource::Ocr);
+    assert_eq!(
+        result.pages[0].provenance.ocr_model.as_ref().unwrap().name,
+        PP_OCR_V6_SMALL.id
+    );
+    assert_eq!(repeated.markdown, result.markdown);
+}
+
 fn recognize(
     model_directory: &std::ffi::OsStr,
     pages: &[RenderedPage],