dsh-file-convert 0.4.0

package/lib/tools/optimize-file.js

@@ -0,0 +1,91 @@
+import fs from 'node:fs/promises';
+import path from 'node:path';
+import { defineTool } from '@deepseek-ai/dsh-tools';
+import { DetectError, optimizeFile, resolveBinary } from '../core/index.js';
+import { canonicalExtension } from '../core/index.js';
+import { formatBytes, formatDuration, formatFailure } from '../format.js';
+export function createOptimizeFileTool(router, config, logger) {
+    return defineTool({
+        name: 'optimize_file',
+        description: 'Shrink a file toward a target size, fully local: MP4/MOV video via two-pass x264 (bitrate computed from the target, output is MP4), JPG/WEBP/PNG images via encoder quality search, and PDF via Ghostscript presets (printer/ebook/screen). Not for GIF yet. Video needs ffmpeg+ffprobe and PDF needs Ghostscript installed; images work without any external tool.',
+        parameters: {
+            input: { type: 'string', required: true, description: 'Absolute path of the file to shrink.' },
+            target_size_mb: { type: 'number', required: true, description: 'Desired maximum output size in megabytes.' },
+            output: {
+                type: 'string',
+                description: 'Optional absolute output path. Defaults to next to the input with a "-min" suffix. If the plugin config sets outputRoots, the path must be inside one of them.',
+            },
+            overwrite: { type: 'boolean', description: 'Replace the output file if it exists. Default false.' },
+        },
+        output: {
+            schema: { type: 'string' },
+            render: (_args, value) => [{ type: 'text', text: value }],
+        },
+        timeoutMs: Math.max(config.timeoutMs, 600_000), // two-pass video needs room
+        isConcurrencySafe: () => true,
+        async execute(args, exec) {
+            const targetBytes = Math.max(1, Math.round(args.target_size_mb * 1024 * 1024));
+            let detection;
+            try {
+                detection = (await router.detect(args.input)).detection;
+            }
+            catch (err) {
+                if (err instanceof DetectError)
+                    throw new Error(formatFailure(err.error));
+                throw err;
+            }
+            const format = detection.format;
+            // Default output: next to the input, same base + "-min", proper extension.
+            const outExt = format === 'mov' ? '.mp4' : canonicalExtension(format);
+            const output = args.output ??
+                path.join(path.dirname(args.input), `${path.basename(args.input, path.extname(args.input))}-min${outExt}`);
+            if (path.resolve(output) === path.resolve(args.input)) {
+                throw new Error('Output path equals the input path; optimizing would destroy the source. Use the default -min output name or pick another path.');
+            }
+            if (args.output !== undefined && config.outputRoots.length > 0 && !isInsideRoots(args.output, config.outputRoots)) {
+                throw new Error(`Output path is outside every configured outputRoot (${config.outputRoots.join(', ')}).`);
+            }
+            if (args.overwrite !== true && (await exists(output))) {
+                throw new Error(`Output file already exists: ${output}. Pass overwrite: true to replace it.`);
+            }
+            const overrides = {};
+            if (config.ffmpegPath)
+                overrides.ffmpegPath = config.ffmpegPath;
+            if (config.ffprobePath)
+                overrides.ffprobePath = config.ffprobePath;
+            const resolve = (dep) => resolveBinary(dep, overrides, logger);
+            const result = await optimizeFile(args.input, targetBytes, output, format, resolve, { logger, signal: exec.signal, timeoutMs: Math.max(config.timeoutMs, 600_000) });
+            if (!result.ok)
+                throw new Error(formatFailure(result.error));
+            const lines = [
+                `Optimized: ${result.input} (${format}) -> ${result.output}`,
+                `${formatBytes(result.bytesIn)} -> ${formatBytes(result.bytesOut)} (target ${args.target_size_mb} MB) in ${formatDuration(result.durationMs)}`,
+                `Applied: ${result.detail}`,
+            ];
+            if (result.bytesOut > targetBytes) {
+                lines.push(`Warning: result is still above the target; try a higher target_size_mb.`);
+            }
+            for (const warning of result.warnings)
+                lines.push(`Warning: ${warning}`);
+            return lines.join('\n');
+        },
+    });
+}
+function isInsideRoots(output, roots) {
+    const resolved = path.resolve(output);
+    const candidate = process.platform === 'win32' ? resolved.replace(/\\/g, '/').toLowerCase() : resolved;
+    return roots.some((root) => {
+        const rr = path.resolve(root);
+        const prefix = process.platform === 'win32' ? rr.replace(/\\/g, '/').toLowerCase() : rr;
+        return candidate === prefix || candidate.startsWith(prefix.endsWith('/') ? prefix : prefix + '/');
+    });
+}
+async function exists(p) {
+    try {
+        await fs.access(p);
+        return true;
+    }
+    catch {
+        return false;
+    }
+}

package/package.json

@@ -0,0 +1,66 @@
+{
+  "name": "dsh-file-convert",
+  "version": "0.4.0",
+  "description": "Local-first file conversion for DeepSeek Harness - images, PDF, data, audio/video and office documents. No API keys, no uploads, no token cost.",
+  "license": "MIT",
+  "type": "module",
+  "main": "./lib/index.js",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/zzy-12345678/dsh-file-convert.git"
+  },
+  "bugs": {
+    "url": "https://github.com/zzy-12345678/dsh-file-convert/issues"
+  },
+  "homepage": "https://github.com/zzy-12345678/dsh-file-convert#readme",
+  "engines": {
+    "node": ">=20"
+  },
+  "files": [
+    "lib",
+    "cordis.patch.yml",
+    "README.md",
+    "README.zh-CN.md",
+    "LICENSE"
+  ],
+  "dsh": {
+    "bundle": {
+      "patch": "./cordis.patch.yml"
+    }
+  },
+  "scripts": {
+    "build": "tsc",
+    "prepare": "npm run build",
+    "test": "vitest run",
+    "smoke": "node scripts/smoke-test.mjs"
+  },
+  "keywords": [
+    "dsh-plugin",
+    "deepseek-harness",
+    "convert",
+    "file-conversion",
+    "local-first"
+  ],
+  "dependencies": {
+    "@deepseek-ai/cordis": "^4.0.1",
+    "@deepseek-ai/dsh-tools": "0.0.1-rc.1",
+    "@deepseek-ai/schemastery": "^3.18.1",
+    "@napi-rs/canvas": "^1.0.8",
+    "csv-parse": "^7.0.2",
+    "csv-stringify": "^6.8.3",
+    "file-type": "^22.0.2",
+    "js-yaml": "^4.1.0",
+    "pdfjs-dist": "^6.2.108",
+    "sharp": "^0.35.4",
+    "tesseract.js": "^7.0.0"
+  },
+  "devDependencies": {
+    "@types/js-yaml": "^4.0.9",
+    "@types/node": "^22.0.0",
+    "docx": "^9.7.1",
+    "fflate": "^0.8.3",
+    "pdf-lib": "^1.17.1",
+    "typescript": "^5.9.0",
+    "vitest": "^4.1.11"
+  }
+}