feat(analysis): add ocrs OCR backend and OCR-driven page text search

Adds an in-process ocrs OCR backend as the active analysis engine
(vision left dormant), enables OCR text search on the page-tag
aggregation endpoints, and reshapes the admin analysis/settings UI to
present the OCR-only surface. Bumps version 0.89.0 -> 0.90.0.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

backend/src/analysis/mod.rs

@@ -9,5 +9,6 @@
 
 pub mod daemon;
 pub mod events;
+pub mod ocr;
 pub mod prompt;
 pub mod vision;

backend/src/analysis/ocr.rs

@@ -0,0 +1,201 @@
+//! The in-process OCR analysis backend (the `ocrs` engine).
+//!
+//! A lightweight alternative to [`crate::analysis::vision`]: instead of a slow
+//! local LLM, each page is run through `ocrs` — a pure-Rust detect→recognize
+//! OCR pipeline on the `rten` runtime. It extracts **text only** (no tags,
+//! scene description or NSFW flags — those stay the vision backend's job), then
+//! reuses [`repo::page_analysis::persist_analysis`] so the OCR lines land in
+//! `page_ocr_text` and the weighted `search_doc` tsvector exactly as the vision
+//! path produces them. That makes the existing text-search surfaces
+//! (`/v1/me/page-search` and the tag aggregations) work with no further wiring.
+//!
+//! The engine is split behind the [`OcrEngine`] trait so the dispatcher is
+//! unit-testable without shipping the (multi-MB) `.rten` model files: tests use
+//! [`test_support::StubOcrEngine`], production uses [`OcrsEngine`].
+
+use std::sync::Arc;
+
+use async_trait::async_trait;
+use sqlx::PgPool;
+use uuid::Uuid;
+
+use crate::analysis::daemon::AnalyzeDispatcher;
+use crate::domain::page_analysis::{OcrResult, SafetyFlag, VisionAnalysis};
+use crate::repo;
+use crate::storage::Storage;
+
+/// The `model` label stamped onto `page_analysis` rows written by this backend.
+pub const OCR_MODEL_LABEL: &str = "ocrs";
+
+/// Extracts text lines from a decoded-or-encoded page image. The production
+/// impl ([`OcrsEngine`]) decodes the bytes itself; the trait takes the raw
+/// stored image bytes so the dispatcher stays engine-agnostic.
+pub trait OcrEngine: Send + Sync {
+    /// Run OCR over one page image (the bytes as stored, e.g. PNG/JPEG/WebP).
+    /// Returns the recognized text lines in reading order (top→bottom).
+    fn recognize(&self, image: &[u8]) -> anyhow::Result<Vec<String>>;
+}
+
+/// Turn the OCR engine's ordered text lines into the [`VisionAnalysis`] shape
+/// that [`repo::page_analysis::persist_analysis`] consumes. OCR-only: the tag,
+/// scene and safety fields are left empty/default. The line `kind` is left
+/// blank — `persist_analysis` maps an empty kind to the neutral mid-weight
+/// `OcrKind::Narration` bucket (classifying speech/sfx/… is the deferred
+/// vision backend's job).
+pub fn lines_to_analysis(lines: Vec<String>) -> VisionAnalysis {
+    let ocr_results = lines
+        .into_iter()
+        .map(|text| OcrResult { text, kind: String::new(), y: None })
+        .collect();
+    VisionAnalysis {
+        ocr_results,
+        tagging_results: Vec::new(),
+        scene_description: String::new(),
+        safety_flag: SafetyFlag::default(),
+    }
+}
+
+/// Production OCR engine: an `ocrs` detect+recognize pipeline with the two
+/// `.rten` models loaded once at startup. Cheap to share across workers — the
+/// recognize path borrows `&self`.
+pub struct OcrsEngine {
+    engine: ocrs::OcrEngine,
+}
+
+impl OcrsEngine {
+    /// Load the detection + recognition models from disk and build the engine.
+    /// Fails (at startup) if either model file is missing or unreadable, so a
+    /// misconfigured path is a loud boot error rather than a per-page failure.
+    pub fn from_model_paths(detection: &str, recognition: &str) -> anyhow::Result<Self> {
+        use anyhow::Context;
+        let detection_model = rten::Model::load_file(detection)
+            .with_context(|| format!("load ocrs detection model {detection}"))?;
+        let recognition_model = rten::Model::load_file(recognition)
+            .with_context(|| format!("load ocrs recognition model {recognition}"))?;
+        let engine = ocrs::OcrEngine::new(ocrs::OcrEngineParams {
+            detection_model: Some(detection_model),
+            recognition_model: Some(recognition_model),
+            ..Default::default()
+        })
+        .context("construct ocrs engine")?;
+        Ok(Self { engine })
+    }
+}
+
+impl OcrEngine for OcrsEngine {
+    fn recognize(&self, image: &[u8]) -> anyhow::Result<Vec<String>> {
+        use anyhow::Context;
+        // Decode to RGB8 so `ImageSource` gets a known channel layout.
+        let rgb = image::load_from_memory(image)
+            .context("decode page image for OCR")?
+            .into_rgb8();
+        let source = ocrs::ImageSource::from_bytes(rgb.as_raw(), rgb.dimensions())
+            .map_err(|e| anyhow::anyhow!("build OCR image source: {e}"))?;
+        let input = self.engine.prepare_input(source)?;
+        // detect words → group into lines → recognize each line. Mirrors
+        // `OcrEngine::get_text`, but keeps the lines as a Vec instead of
+        // joining them, so each becomes its own `page_ocr_text` row.
+        let words = self.engine.detect_words(&input)?;
+        let line_rects = self.engine.find_text_lines(&input, &words);
+        let lines = self
+            .engine
+            .recognize_text(&input, &line_rects)?
+            .into_iter()
+            .filter_map(|line| line.map(|l| l.to_string()))
+            .map(|s| s.trim().to_string())
+            .filter(|s| !s.is_empty())
+            .collect();
+        Ok(lines)
+    }
+}
+
+/// Production dispatcher for the OCR backend: load the page, read its image
+/// from storage, run OCR on the blocking pool, and persist the lines. Mirrors
+/// [`crate::analysis::daemon::RealAnalyzeDispatcher`] but with no network I/O.
+pub struct OcrAnalyzeDispatcher {
+    pub db: PgPool,
+    pub storage: Arc<dyn Storage>,
+    pub engine: Arc<dyn OcrEngine>,
+    pub max_image_bytes: usize,
+}
+
+#[async_trait]
+impl AnalyzeDispatcher for OcrAnalyzeDispatcher {
+    async fn dispatch(&self, page_id: Uuid) -> anyhow::Result<()> {
+        let Some(page) = repo::page::find_by_id(&self.db, page_id).await? else {
+            // Page was deleted between enqueue and dispatch — nothing to do.
+            return Ok(());
+        };
+        let bytes = self
+            .storage
+            .get(&page.storage_key)
+            .await
+            .map_err(|e| anyhow::anyhow!("read page image {}: {e}", page.storage_key))?;
+        if bytes.len() > self.max_image_bytes {
+            anyhow::bail!(
+                "page image {} is {} bytes, over the {} cap",
+                page.storage_key,
+                bytes.len(),
+                self.max_image_bytes
+            );
+        }
+        // OCR inference is CPU-bound and synchronous — keep it off the async
+        // worker's runtime thread.
+        let engine = Arc::clone(&self.engine);
+        let lines = tokio::task::spawn_blocking(move || engine.recognize(&bytes))
+            .await
+            .map_err(|e| anyhow::anyhow!("OCR task join error: {e}"))??;
+        let analysis = lines_to_analysis(lines);
+        repo::page_analysis::persist_analysis(&self.db, page_id, &analysis, OCR_MODEL_LABEL).await?;
+        Ok(())
+    }
+}
+
+/// Stubs for the OCR dispatcher's integration tests. Public because the tests
+/// live in the `tests/` dir (a separate crate).
+pub mod test_support {
+    use super::*;
+
+    /// An [`OcrEngine`] that returns a fixed set of lines regardless of input,
+    /// so the dispatcher's storage→persist path can be tested without models.
+    pub struct StubOcrEngine {
+        pub lines: Vec<String>,
+    }
+
+    impl StubOcrEngine {
+        pub fn new(lines: &[&str]) -> Arc<Self> {
+            Arc::new(Self { lines: lines.iter().map(|s| s.to_string()).collect() })
+        }
+    }
+
+    impl OcrEngine for StubOcrEngine {
+        fn recognize(&self, _image: &[u8]) -> anyhow::Result<Vec<String>> {
+            Ok(self.lines.clone())
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn lines_to_analysis_maps_lines_in_order_and_leaves_rest_empty() {
+        let v = lines_to_analysis(vec!["Hello".to_string(), "world!".to_string()]);
+        assert_eq!(v.ocr_results.len(), 2);
+        assert_eq!(v.ocr_results[0].text, "Hello");
+        assert_eq!(v.ocr_results[1].text, "world!");
+        // OCR-only: kind blank (→ Narration at persist), no tags/scene/safety.
+        assert!(v.ocr_results.iter().all(|r| r.kind.is_empty()));
+        assert!(v.tagging_results.is_empty());
+        assert_eq!(v.scene_description, "");
+        assert!(!v.safety_flag.is_nsfw);
+        assert!(v.safety_flag.content_type.is_empty());
+    }
+
+    #[test]
+    fn lines_to_analysis_handles_no_text() {
+        let v = lines_to_analysis(Vec::new());
+        assert!(v.ocr_results.is_empty());
+    }
+}