sorokin.oleg.edu/learnharness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

wave E stage 1: pdf_render goes native - pdfjs paints, Skia hosts

Browse Source 
The browser was never the PDF engine - pdfjs always painted the pages;
Chrome only hosted the canvas tab. Now pdfjs-dist v6's own Node
integration (@napi-rs/canvas, its optionalDependency) hosts in-process:
same paint code, Skia canvas, zero browsers, zero temp files, no base64
hop. The whole pdf-reader runs browser-free - the Chrome gate on
pdf_render is gone.

The Skia binary (27MB per platform, exactly one per build - npm installs
only the building machine's) rides the standalone via the same
outputFileTracingIncludes pattern as pdfjs-dist. Verified: builds green
(1515), native render pinned against the real fixture (canonical
single-IDAT PNGs, dpi/72 arithmetic, page-range skipping), and the
canvas loads + paints from inside .next/standalone.

Stages 2-3 (resvg for SVG, the --browser-service demo helper) follow.
This commit is contained in:
amosblomqvist
2026-10-11 06:49:13 +03:00
parent 0af005d343
commit 951c7704b9
4 changed files with 150 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/agent/subagents/headless.ts
+47 -75
View File
@@ -290,92 +290,64 @@ async function renderSvg(svg: string, opts: RenderSvgOptions = {}): Promise<Buff
}
}
// ─── PDF page rasterization (pdfjs paints, Chrome hosts) ───────────────
// ─── PDF page rasterization (pdfjs paints, Skia hosts) ─────────────────
/** Render PDF pages to PNGs — the sources-v0 pdf-reader's eyes.
*
* The engine (user-chosen hybrid, live-verified 2026-09-19): pdfjs paints
* each page into a <canvas> (scale = dpi/72, the skill's zoom arithmetic)
* inside a headless Chrome tab, and the canvas pixels come back via
* toDataURL. Chrome's OWN PDF viewer plugin does not paint in headless
* mode (verified: identical blank screenshots regardless of page), so the
* canvas shim is the pixel path — Chrome still hosts and encodes, no
* native node-canvas anywhere. PDF bytes pass in as base64 (fetch() is
* blocked on file://); pdfjs runs via its real worker module under
* --allow-file-access-from-files. */
* History: pdfjs ALWAYS painted the pages (scale = dpi/72, the skill's
* zoom arithmetic) — first inside a headless Chrome tab (canvas shim,
* toDataURL, 2026-09-19), now into @napi-rs/canvas in this process (Wave
* E, 2026-10-10). The paint engine never changed; only the canvas host:
* Skia in-process via pdfjs-dist v6's own Node integration. No browser,
* no temp files, no base64 hop. */
async function renderPdfPages(
pdfPath: string,
pages: number[],
opts: RenderPdfOptions = {},
): Promise<RenderedPdfPage[]> {
const dpi = opts.dpi ?? 150;
const pdfAbs = path.resolve(pdfPath);
const pdfjsUrl = pathToFileURL(
path.join(PATHS_nodeModules(), "pdfjs-dist/legacy/build/pdf.mjs"),
).href;
const b64 = fs.readFileSync(pdfAbs).toString("base64");
const dir = tempDir("lh-pdf-");
const file = path.join(dir, "shim.html");
fs.writeFileSync(
file,
"<!doctype html><html><head><meta charset='utf-8'><style>html,body{margin:0;padding:0;background:#fff}canvas{display:block}</style></head><body></body></html>",
"utf-8",
);
const browser = await launchBrowser(["--allow-file-access-from-files"]);
// NATIVE CANVAS (Wave E, owner 2026-10-10): pdfjs paints into
// @napi-rs/canvas in this process — no browser involved. pdfjs-dist v6's
// own Node integration IS @napi-rs/canvas (its optionalDependency: the
// NodeCanvasFactory requires it), so the paint engine is the exact code
// that used to run in the Chrome shim tab; only the canvas host changed
// (Skia in-process instead of a DOM canvas). Text-side pdf tools never
// needed a browser; now renders don't either.
const pdfjs = await import("pdfjs-dist/legacy/build/pdf.mjs");
const { createCanvas } = await import("@napi-rs/canvas");
const data = new Uint8Array(fs.readFileSync(path.resolve(pdfPath)));
// Standard-font data as a directory path (live-smoke finding 2026-09-19:
// without it pdfjs renders non-embedded standard fonts via fallback);
// verbosity 0 = errors only (JBIG2 noise on scanned PDFs).
const standardFontDataUrl =
path.join(PATHS_nodeModules(), "pdfjs-dist", "standard_fonts") + path.sep;
const loadingTask = pdfjs.getDocument({ data, standardFontDataUrl, verbosity: 0 });
const doc = await loadingTask.promise;
try {
const page = await browser.newPage();
await page.setViewport({ width: 1200, height: 1600, deviceScaleFactor: 1 });
await page.goto(pathToFileURL(file).href, { waitUntil: "load", timeout: 30_000 });
// Standard-font data as a file URL (live-smoke finding 2026-09-19:
// without it pdfjs renders non-embedded standard fonts via fallback);
// verbosity 0 = errors only (JBIG2 noise on scanned PDFs).
const fontsUrl = pathToFileURL(path.join(PATHS_nodeModules(), "pdfjs-dist", "standard_fonts") + path.sep).href;
const results = await page.evaluate(
async (b64pdf, workerUrl, pageNos, dpi, fontsUrl) => {
// window-scope dynamic import (Chrome evaluates this string in the
// shim page, not under Node)
const pdfjs = (await import(workerUrl)) as typeof import("pdfjs-dist");
pdfjs.GlobalWorkerOptions.workerSrc = workerUrl.replace("pdf.mjs", "pdf.worker.mjs");
const bin = atob(b64pdf);
const bytes = new Uint8Array(bin.length);
for (let i = 0; i < bin.length; i++) bytes[i] = bin.charCodeAt(i);
const doc = await pdfjs.getDocument({ data: bytes, standardFontDataUrl: fontsUrl, verbosity: 0 }).promise;
const out: Array<{ page: number; dataUrl: string; w: number; h: number }> = [];
for (const pageNo of pageNos) {
if (pageNo < 1 || pageNo > doc.numPages) continue;
const pg = await doc.getPage(pageNo);
const vp = pg.getViewport({ scale: dpi / 72 });
const canvas = document.createElement("canvas");
canvas.width = Math.ceil(vp.width);
canvas.height = Math.ceil(vp.height);
const ctx = canvas.getContext("2d");
if (!ctx) throw new Error("canvas 2d context unavailable");
await pg.render({ canvasContext: ctx, canvas, viewport: vp }).promise;
out.push({ page: pageNo, dataUrl: canvas.toDataURL("image/png"), w: canvas.width, h: canvas.height });
}
return out;
},
b64,
pdfjsUrl,
pages,
dpi,
fontsUrl,
);
return results.map((r) => ({
page: r.page,
// canvas-encoded PNG → providerSafePng for the same single-IDAT
// canonical form every other vision-model image gets.
png: providerSafePng(Buffer.from(r.dataUrl.slice(r.dataUrl.indexOf(",") + 1), "base64")),
}));
} finally {
await browser.close().catch(() => {});
try {
fs.rmSync(dir, { recursive: true, force: true });
} catch {
/* best-effort cleanup */
const out: RenderedPdfPage[] = [];
for (const pageNo of pages) {
if (pageNo < 1 || pageNo > doc.numPages) continue;
const pg = await doc.getPage(pageNo);
const vp = pg.getViewport({ scale: dpi / 72 });
const canvas = createCanvas(Math.ceil(vp.width), Math.ceil(vp.height));
const ctx = canvas.getContext("2d");
// pdfjs's render types speak the DOM context; @napi-rs/canvas's
// context is the same 2D API implemented over Skia.
await pg.render({
canvasContext: ctx as unknown as CanvasRenderingContext2D,
canvas: canvas as unknown as HTMLCanvasElement,
viewport: vp,
}).promise;
out.push({
page: pageNo,
// Skia-encoded PNG → providerSafePng for the same single-IDAT
// canonical form every other vision-model image gets.
png: providerSafePng(canvas.toBuffer("image/png")),
});
}
return out;
} finally {
await loadingTask.destroy().catch(() => {});
}
}
src/agent/subagents/pdf-reader.ts
+20 -26
View File
@@ -173,9 +173,9 @@ export async function runPdfReaderAgent(
if (openError) {
return { path: pdfPath, question: input.question, brief: `PDF failed: ${openError}`, pagesRead: [], pagesConsulted: [] };
}
const chromeReason = headless.unavailableReason();
// Chrome missing does NOT fail the run: text-side tools still work; the
// doctrine degrades to extract+search (render calls return an error note).
// No Chrome gate (Wave E, 2026-10-10): pdf_render is native now
// (pdfjs paints into @napi-rs/canvas in-process) — the whole pdf-reader
// runs browser-free; text tools always worked without one.
const tools = createPdfTools(pdfPath);
const toolDeclarations = Object.values(tools);
@@ -280,30 +280,24 @@ export async function runPdfReaderAgent(
} else if (call.name === "pdf_render") {
const spec = String(args.pages ?? "1");
const dpi = numOr(args.dpi, 150);
if (chromeReason) {
toolResults.push(
toolText(call.id, call.name, `ERROR: rendering unavailable — ${chromeReason} Read via pdf_extract instead.`),
);
const wanted = specNumbers(spec, RENDER_BATCH_CAP);
opts.onActivity?.(`pdf_render: ${spec} @${dpi}dpi`);
const pages = await headless.renderPdfPages(pdfPath, wanted, { dpi });
for (const p of pages) {
consulted.add(p.page);
read.add(p.page);
}
if (pages.length === 0) {
toolResults.push(toolText(call.id, call.name, "ERROR: no pages rendered (spec matched nothing?)"));
} else {
const wanted = specNumbers(spec, RENDER_BATCH_CAP);
opts.onActivity?.(`pdf_render: ${spec} @${dpi}dpi`);
const pages = await headless.renderPdfPages(pdfPath, wanted, { dpi });
for (const p of pages) {
consulted.add(p.page);
read.add(p.page);
}
if (pages.length === 0) {
toolResults.push(toolText(call.id, call.name, "ERROR: no pages rendered (spec matched nothing?)"));
} else {
renderedImages = pages;
toolResults.push(
toolText(
call.id,
call.name,
`Rendered ${pages.length} page(s) at ${dpi} DPI — the images follow below. Read them carefully (equations, diagrams, layout).`,
),
);
}
renderedImages = pages;
toolResults.push(
toolText(
call.id,
call.name,
`Rendered ${pages.length} page(s) at ${dpi} DPI — the images follow below. Read them carefully (equations, diagrams, layout).`,
),
);
}
} else {
toolResults.push(toolText(call.id, call.name, `ERROR: unknown tool "${call.name}"`));