@intentic/claude-plugin 1.322.0 → 1.323.0

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
     "name": "intentic",
     "displayName": "Intentic",
-    "version": "1.322.0",
+    "version": "1.323.0",
     "description": "Cheaper, sharper Claude Code sessions: Bash output trimmed before Claude reads it, a project map and this project's field notes at session start, iq code search and fileq document reading taught, and /intentic:stats to show what each one saved. Every mechanism is a switch in /config.",
     "author": {
         "name": "intentic"

package/dist/fileq.mjs

@@ -87118,8 +87118,8 @@ var require_body_reader = __commonJS({
         if (checkboxResult) {
           var checkboxElement = fldChar.firstOrEmpty("w:ffData").firstOrEmpty("w:checkBox");
           var checkedElement = checkboxElement.first("w:checked");
-          var checked = checkedElement == null ? readBooleanElement(checkboxElement.first("w:default")) : readBooleanElement(checkedElement);
-          return { type: "checkbox", checked };
+          var checked2 = checkedElement == null ? readBooleanElement(checkboxElement.first("w:default")) : readBooleanElement(checkedElement);
+          return { type: "checkbox", checked: checked2 };
         }
         return { type: "unknown" };
       }
@@ -105433,12 +105433,12 @@ var init_pdf_furniture = __esm({
 });
 
 // ../fileq/src/lib/derivers/pdf.ts
-import { execFile as execFile2 } from "node:child_process";
+import { execFile as execFile2, spawnSync } from "node:child_process";
 import { mkdtemp, readdir, readFile as readFile10, rm } from "node:fs/promises";
 import { tmpdir } from "node:os";
 import { join as join3 } from "node:path";
 import { promisify as promisify2 } from "node:util";
-var SCAN_THRESHOLD_CHARS_PER_PAGE, MAX_OCR_PAGES, OCR_DPI, run3, ocrAvailable, recognisePages, pagesToMarkdown, furnitureNotes, withoutFurniture, pdfDeriver;
+var SCAN_THRESHOLD_CHARS_PER_PAGE, MAX_OCR_PAGES, OCR_DPI, OCR_TIMEOUT_MS, run3, checked, ocrAvailable, readPages, recognisePages, pagesToMarkdown, furnitureNotes, withoutFurniture, pdfDeriver;
 var init_pdf = __esm({
   "../fileq/src/lib/derivers/pdf.ts"() {
     "use strict";
@@ -105448,8 +105448,27 @@ var init_pdf = __esm({
     SCAN_THRESHOLD_CHARS_PER_PAGE = 24;
     MAX_OCR_PAGES = 20;
     OCR_DPI = "200";
+    OCR_TIMEOUT_MS = 6e4 + MAX_OCR_PAGES * 15e3;
     run3 = promisify2(execFile2);
-    ocrAvailable = () => onPath("tesseract") && onPath("pdftoppm");
+    checked = /* @__PURE__ */ new Map();
+    ocrAvailable = () => {
+      const path = process.env["PATH"] ?? "";
+      let available = checked.get(path);
+      if (available === void 0) {
+        available = onPath("pdftoppm") && onPath("ocr") && spawnSync("ocr", ["--check"], { stdio: "ignore", timeout: 1e4 }).status === 0;
+        checked.set(path, available);
+      }
+      return available;
+    };
+    readPages = (images) => new Promise((resolve6, reject) => {
+      execFile2("ocr", [...images], { timeout: OCR_TIMEOUT_MS, maxBuffer: 16 * 1024 * 1024 }, (error2, stdout) => {
+        if (error2 === null || error2.code === 1) {
+          resolve6(stdout);
+        } else {
+          reject(error2);
+        }
+      });
+    });
     recognisePages = async (absPath, totalPages) => {
       const dir = await mkdtemp(join3(tmpdir(), "fileq-ocr-"));
       try {
@@ -105457,12 +105476,11 @@ var init_pdf = __esm({
           timeout: 12e4
         });
         const images = (await readdir(dir)).filter((name) => name.endsWith(".png")).toSorted();
-        const pages = [];
-        for (const image of images) {
-          const { stdout } = await run3("tesseract", [join3(dir, image), "stdout", "-l", "eng"], { timeout: 12e4, maxBuffer: 16 * 1024 * 1024 });
-          pages.push(stdout.replaceAll(/[ \t]+/g, " ").trim());
+        if (images.length === 0) {
+          return [];
         }
-        return pages;
+        const pages = (await readPages(images.map((image) => join3(dir, image)))).split("\f");
+        return images.map((_3, index) => (pages[index] ?? "").replaceAll(/[ \t]+/g, " ").trim());
       } finally {
         await rm(dir, { recursive: true, force: true });
       }
@@ -105478,11 +105496,11 @@ ${page === "" ? "(no text on this page)" : page}`).join("\n\n");
       return { markdown: pagesToMarkdown(kept), notes: furnitureNotes(removed, example) };
     };
     pdfDeriver = {
-      // The stamp names OCR capability, since a sidecar written before tesseract was available must read as stale now
-      // that it's here.
-      // A static name would leave a pre-OCR sidecar looking current forever.
+      // The stamp names OCR capability, since a sidecar written before the reader was available must read as stale now
+      // that it's here. A static name would leave a pre-OCR sidecar looking current forever. It names the reader too:
+      // `pdf+ocr` was tesseract's, whose pages PaddleOCR reads again.
       get name() {
-        return ocrAvailable() ? "pdf+ocr" : "pdf";
+        return ocrAvailable() ? "pdf+ppocr" : "pdf";
       },
       version: 2,
       derive: async (absPath) => {
@@ -105504,10 +105522,10 @@ ${page === "" ? "(no text on this page)" : page}`).join("\n\n");
           }
           const recognised = await recognisePages(absPath, totalPages);
           const notes = [
-            `scanned: text recognised by OCR (tesseract) on ${recognised.length} of ${totalPages} page${plural3} \u2014 recognised, not exact; check figures against the page image`
+            `scanned: text recognised by OCR (PaddleOCR) on ${recognised.length} of ${totalPages} page${plural3} \u2014 recognised, not exact; check figures against the page image`
           ];
           if (totalPages > MAX_OCR_PAGES) {
-            notes.push(`OCR stops at ${MAX_OCR_PAGES} pages: run tesseract over the rest yourself if they matter`);
+            notes.push(`OCR stops at ${MAX_OCR_PAGES} pages: draw the rest with pdftoppm and read them with \`ocr <page.png>...\` if they matter`);
           }
           const { markdown, notes: stripped } = withoutFurniture(recognised);
           return { markdown, title, notes: [...notes, ...stripped] };

package/generated/skills/fileq/SKILL.md

@@ -13,7 +13,7 @@ cached by content, so a repeat read of unchanged content is instant.
 - Prints a capsule (format, token cost), the content up to the budget, and `saved:` — the markdown file
   carrying the whole thing. Over budget, the cut is announced with that exact path to Read.
 - Formats: docx and odt (headings, lists, tables), xlsx (capped tables), pptx (slides + speaker notes),
-  pdf (text layer; a scan is OCR'd when `tesseract` is on PATH, and the note says the words are
+  pdf (text layer; a scan is OCR'd when an `ocr` command is on PATH, and the note says the words are
   recognised, not exact), epub (chapters in reading order), ipynb (cells, fenced code, capped outputs),
   png/jpg/gif/webp (dimensions + EXIF), mp3/wav/flac/mp4/… (duration + tags), html, and V8 profiles
   (`.cpuprofile` from `node --cpu-prof`, `.heapprofile` from `--heap-prof`) as functions ranked by self and total cost.
@@ -29,9 +29,10 @@ without parsing it again. Run it again rather than opening a sidecar under `.int
 checks the hash for you.
 
 ## What it refuses, and why
-- A scanned PDF with no `tesseract` on PATH answers "no usable text layer … OCR is not part of this tier"
+- A scanned PDF with no `ocr` on PATH answers "no usable text layer … OCR is not part of this tier"
   rather than an empty page; images say "no visual description". Treat those notes as "not generated",
-  never as "nothing there". Installing tesseract turns the first into OCR.
+  never as "nothing there". An `ocr` command that prints each image's text, a form feed between images (the
+  Intentic sandbox's PaddleOCR reader), turns the first into OCR.
 - Plain text (md, csv, txt, code) is not fileq's business: Read it directly — but see below for the big ones.
 - Web pages belong to `webq`; images for a vision model belong to the Read tool, which shows the pixels.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@intentic/claude-plugin",
-  "version": "1.322.0",
+  "version": "1.323.0",
   "description": "The intentic Claude Code plugin: trimmed Bash output, a project map and field notes at session start, iq search and fileq teaching, and a /intentic:stats report of what each saved",
   "license": "MIT",
   "type": "module",
@@ -40,8 +40,8 @@
   },
   "devDependencies": {
     "@intentic/agent-context": "0.0.0",
-    "@intentic/fileq": "1.322.0",
-    "@intentic/iq": "1.322.0",
+    "@intentic/fileq": "1.323.0",
+    "@intentic/iq": "1.323.0",
     "@intentic/output-cleaners": "0.0.0",
     "@intentic/testing": "0.0.0",
     "@intentic/tsconfig": "0.0.0",