svharness 0.14.2 → 0.14.7

package/dist/config/normalize.js

@@ -71,6 +71,7 @@ function pickBuildSection(raw) {
         'force',
         'yes',
         'verbose',
+        'repomix',
         'generateWiki',
         'wikiTasksOnly',
     ]) {
@@ -107,10 +108,13 @@ function pickConvertSection(raw) {
         if (raw[k] !== undefined)
             s[k] = Number(raw[k]);
     }
-    for (const k of ['force', 'yes', 'verbose']) {
+    for (const k of ['force', 'yes', 'verbose', 'splitSheets']) {
         if (raw[k] !== undefined)
             s[k] = Boolean(raw[k]);
     }
+    if (raw.splitSheetsSuffix !== undefined && raw.splitSheetsSuffix !== null) {
+        s.splitSheetsSuffix = String(raw.splitSheetsSuffix).trim();
+    }
     return s;
 }
 function pickDefaults(raw) {

package/dist/core/apply-project-entry.js

@@ -6,6 +6,7 @@ Object.defineProperty(exports, "__esModule", { value: true });
 exports.writeApplyProjectEntry = writeApplyProjectEntry;
 const fs_extra_1 = __importDefault(require("fs-extra"));
 const node_path_1 = __importDefault(require("node:path"));
+const repomix_apply_hint_1 = require("./repomix-apply-hint");
 const logger_1 = require("../utils/logger");
 function toPosix(p) {
     return p.replace(/\\/g, '/');
@@ -81,7 +82,13 @@ async function writeApplyProjectEntry(input) {
         : bridgeHint.length > 0
             ? `${raw.trimEnd()}\n\n${bridgeHint}`
             : raw;
-    const rewritten = rewriteEntryReferences(withBridgeHint, input.harnessDirName);
+    const repomixHint = await (0, repomix_apply_hint_1.buildRepomixApplyHintReplacement)({
+        harnessRoot: input.harnessRoot,
+        harnessDirName: input.harnessDirName,
+        blockquote: true,
+    });
+    const withRepomixHint = (0, repomix_apply_hint_1.applyRepomixHintPlaceholder)(withBridgeHint, repomixHint, repomix_apply_hint_1.REPOMIX_APPLY_HINT_PLACEHOLDER);
+    const rewritten = rewriteEntryReferences(withRepomixHint, input.harnessDirName);
     await fs_extra_1.default.outputFile(dest, rewritten, 'utf8');
     logger_1.logger.success(`已写入项目根 AI 入口：${rel}（由 AGENTS_APPLY.md 重命名）`);
     return rel;

package/dist/core/harness-yaml-baseline.js

@@ -0,0 +1,68 @@
+"use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.readHarnessYamlDoc = readHarnessYamlDoc;
+exports.getBaselineRepomixPackFromDoc = getBaselineRepomixPackFromDoc;
+exports.setBaselineRepomixPack = setBaselineRepomixPack;
+const fs_extra_1 = __importDefault(require("fs-extra"));
+const node_path_1 = __importDefault(require("node:path"));
+const js_yaml_1 = __importDefault(require("js-yaml"));
+const yaml_safe_path_1 = require("../utils/yaml-safe-path");
+const REPOMIX_PACK_KEY = 'repomix_pack';
+const REPOMIX_PACK_COMMENT = '  # repomix_pack: baseline/repomix/repomix-pack.xml  # 仅 --repomix 成功后由 CLI 写入';
+async function readHarnessYamlDoc(harnessRoot) {
+    const yamlPath = node_path_1.default.join(harnessRoot, 'harness.yaml');
+    if (!(await fs_extra_1.default.pathExists(yamlPath)))
+        return undefined;
+    try {
+        const raw = await fs_extra_1.default.readFile(yamlPath, 'utf8');
+        return js_yaml_1.default.load((0, yaml_safe_path_1.preprocessHarnessYamlText)(raw));
+    }
+    catch {
+        return undefined;
+    }
+}
+function getBaselineRepomixPackFromDoc(doc) {
+    if (!doc || typeof doc.baseline !== 'object' || doc.baseline === null)
+        return undefined;
+    const baseline = doc.baseline;
+    const v = baseline[REPOMIX_PACK_KEY];
+    if (typeof v !== 'string' || !v.trim())
+        return undefined;
+    return v.trim().replace(/\\/g, '/');
+}
+/**
+ * Set or clear `baseline.repomix_pack` in harness.yaml (line edit to preserve comments).
+ */
+async function setBaselineRepomixPack(harnessRoot, repomixPackRel) {
+    const yamlPath = node_path_1.default.join(harnessRoot, 'harness.yaml');
+    if (!(await fs_extra_1.default.pathExists(yamlPath))) {
+        throw new Error(`harness.yaml 不存在：${yamlPath}`);
+    }
+    let text = await fs_extra_1.default.readFile(yamlPath, 'utf8');
+    const rel = repomixPackRel?.trim().replace(/\\/g, '/') ?? null;
+    const activeLine = rel ? `  repomix_pack: ${rel}` : REPOMIX_PACK_COMMENT;
+    const activePattern = /^\s*repomix_pack:\s*.+$/m;
+    const commentPattern = /^\s*#\s*repomix_pack:.*$/m;
+    if (activePattern.test(text)) {
+        text = text.replace(activePattern, activeLine);
+    }
+    else if (commentPattern.test(text)) {
+        text = text.replace(commentPattern, activeLine);
+    }
+    else if (rel) {
+        const wikiLine = /(^\s*wiki:\s*baseline\/wiki\/.*$)/m;
+        if (wikiLine.test(text)) {
+            text = text.replace(wikiLine, `$1\n${activeLine}`);
+        }
+        else {
+            const baselineBlock = /(^baseline:\s*\n(?:^\s+.+\n)*)/m;
+            if (baselineBlock.test(text)) {
+                text = text.replace(baselineBlock, (block) => `${block}${activeLine}\n`);
+            }
+        }
+    }
+    await fs_extra_1.default.outputFile(yamlPath, text, 'utf8');
+}

package/dist/core/markdown-sheet-split.js

@@ -0,0 +1,109 @@
+"use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.XLSX_SPLIT_EXTS = void 0;
+exports.slugifySheetTitle = slugifySheetTitle;
+exports.splitSpreadsheetMarkdownBySheet = splitSpreadsheetMarkdownBySheet;
+exports.writeSheetSplitOutput = writeSheetSplitOutput;
+/**
+ * Split spreadsheet-derived Markdown by level-2 headings (`##`).
+ *
+ * MarkItDown emits one `## SheetName` block per Excel worksheet. This pass
+ * writes each block to its own `.md` file under `<basename><suffix>/`.
+ */
+const fs_extra_1 = __importDefault(require("fs-extra"));
+const node_path_1 = __importDefault(require("node:path"));
+/** Source extensions that trigger sheet split during `svharness convert`. */
+exports.XLSX_SPLIT_EXTS = new Set(['.xlsx', '.xls']);
+const INVALID_FILENAME_CHARS = /[<>:"/\\|?*\x00-\x1f]/g;
+/**
+ * Turn a sheet title into a safe filename: `{index}_{slug}.md`.
+ */
+function slugifySheetTitle(title, index) {
+    let name = title.trim();
+    name = name.replace(INVALID_FILENAME_CHARS, '_');
+    name = name.replace(/\s+/g, '_');
+    name = name.replace(/^[._]+|[._]+$/g, '');
+    if (!name) {
+        name = 'section';
+    }
+    return `${String(index).padStart(2, '0')}_${name}.md`;
+}
+/**
+ * Split markdown at `##` headings (one section per sheet).
+ */
+function splitSpreadsheetMarkdownBySheet(markdown) {
+    const charsBefore = Buffer.byteLength(markdown, 'utf8');
+    const lines = markdown.split(/\r?\n/);
+    const anchors = [];
+    for (let i = 0; i < lines.length; i++) {
+        const match = /^## (.+)$/.exec(lines[i]);
+        if (match) {
+            anchors.push({ title: match[1].trim(), startLine: i });
+        }
+    }
+    if (anchors.length === 0) {
+        return {
+            sections: [],
+            stats: { sectionsFound: 0, charsBefore, charsAfter: charsBefore },
+        };
+    }
+    const sections = [];
+    for (let i = 0; i < anchors.length; i++) {
+        const endLine = i + 1 < anchors.length ? anchors[i + 1].startLine : lines.length;
+        const body = lines.slice(anchors[i].startLine, endLine).join('\n').trimEnd() + '\n';
+        const filename = slugifySheetTitle(anchors[i].title, i + 1);
+        sections.push({
+            title: anchors[i].title,
+            body,
+            filename,
+        });
+    }
+    const charsAfter = sections.reduce((sum, s) => sum + Buffer.byteLength(s.body, 'utf8'), 0);
+    return {
+        sections,
+        stats: {
+            sectionsFound: sections.length,
+            charsBefore,
+            charsAfter,
+        },
+    };
+}
+function buildSplitIndex(sourceName, sections) {
+    const lines = [
+        `# Split index: ${sourceName}\n`,
+        `\nTotal sections: ${sections.length}\n\n`,
+    ];
+    for (const section of sections) {
+        lines.push(`- [${section.title}](${section.filename})\n`);
+    }
+    return lines.join('');
+}
+/**
+ * Persist split sections to `outputDir`. Returns absolute paths written.
+ */
+async function writeSheetSplitOutput(sections, outputDir, sourceName, opts) {
+    const writeIndex = opts?.writeIndex !== false;
+    const force = !!opts?.force;
+    await fs_extra_1.default.ensureDir(outputDir);
+    const written = [];
+    for (const section of sections) {
+        const filePath = node_path_1.default.join(outputDir, section.filename);
+        if (!force && (await fs_extra_1.default.pathExists(filePath))) {
+            throw new Error(`sheet split output exists (pass --force): ${filePath}`);
+        }
+        await fs_extra_1.default.writeFile(filePath, section.body, 'utf8');
+        written.push(filePath);
+    }
+    if (writeIndex) {
+        const indexPath = node_path_1.default.join(outputDir, 'README.md');
+        if (!force && (await fs_extra_1.default.pathExists(indexPath))) {
+            throw new Error(`sheet split index exists (pass --force): ${indexPath}`);
+        }
+        await fs_extra_1.default.writeFile(indexPath, buildSplitIndex(sourceName, sections), 'utf8');
+        written.push(indexPath);
+    }
+    return written;
+}

package/dist/core/markdown-table-cleanup.js

@@ -0,0 +1,151 @@
+"use strict";
+/**
+ * Post-process Markdown emitted from spreadsheet conversions (`.xlsx` / `.xls` / `.csv`).
+ *
+ * MarkItDown / pandas represent empty Excel cells as the literal "NaN" in pipe
+ * tables. This pass:
+ *   1. Replaces NaN cells with empty cells
+ *   2. Drops data rows that are entirely empty or only contain a numeric index
+ *   3. Drops columns whose data rows are all empty and whose header is blank or
+ *      "Unnamed: N" (pandas default for empty header cells)
+ */
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.XLSX_CONVERT_EXTS = void 0;
+exports.cleanupSpreadsheetMarkdown = cleanupSpreadsheetMarkdown;
+/** Source extensions that trigger table cleanup during `svharness convert`. */
+exports.XLSX_CONVERT_EXTS = new Set([
+    '.xlsx',
+    '.xls',
+    '.csv',
+]);
+const UNNAMED_HEADER = /^Unnamed: \d+$/;
+function isTableRow(line) {
+    const trimmed = line.trim();
+    return trimmed.startsWith('|') && trimmed.endsWith('|');
+}
+function parseTableRow(line) {
+    const inner = line.trim().replace(/^\|/, '').replace(/\|$/, '');
+    return inner.split('|').map((cell) => cell.trim());
+}
+function formatTableRow(cells) {
+    return `| ${cells.join(' | ')} |`;
+}
+function normalizeCell(cell) {
+    if (cell === 'NaN' || cell === 'nan') {
+        return '';
+    }
+    return cell;
+}
+function isSparseTemplateRow(row) {
+    const nonEmpty = row.filter((cell) => cell !== '');
+    if (nonEmpty.length === 0) {
+        return true;
+    }
+    // Excel 预留行常在首列保留序号（2、3、…），其余单元格为空。
+    if (nonEmpty.length === 1 && /^\d+\.?\d*$/.test(nonEmpty[0])) {
+        return true;
+    }
+    return false;
+}
+function isSeparatorRow(cells) {
+    return (cells.length > 0 &&
+        cells.every((cell) => {
+            const c = cell.trim();
+            return c === '' || /^:?-{3,}:?$/.test(c);
+        }));
+}
+function padRow(row, width) {
+    const out = row.slice();
+    while (out.length < width) {
+        out.push('');
+    }
+    return out;
+}
+function cleanupTableBlock(lines) {
+    if (lines.length === 0) {
+        return { lines, nanCellsReplaced: 0, rowsRemoved: 0, columnsRemoved: 0 };
+    }
+    let nanCellsReplaced = 0;
+    const rawRows = lines.map(parseTableRow);
+    const colCount = Math.max(...rawRows.map((row) => row.length), 0);
+    if (colCount === 0) {
+        return { lines, nanCellsReplaced: 0, rowsRemoved: 0, columnsRemoved: 0 };
+    }
+    const rows = rawRows.map((row) => padRow(row, colCount).map((cell) => {
+        const normalized = normalizeCell(cell);
+        if (normalized !== cell) {
+            nanCellsReplaced += 1;
+        }
+        return normalized;
+    }));
+    const hasSeparator = rows.length > 1 && isSeparatorRow(rows[1]);
+    const header = rows[0];
+    const dataStart = hasSeparator ? 2 : 1;
+    const dataRowsBefore = rows.slice(dataStart);
+    const dataRows = dataRowsBefore.filter((row) => !isSparseTemplateRow(row));
+    const rowsRemoved = dataRowsBefore.length - dataRows.length;
+    const keepCols = [];
+    for (let col = 0; col < colCount; col += 1) {
+        const headerCell = header[col] ?? '';
+        const dataEmpty = dataRows.every((row) => (row[col] ?? '') === '');
+        if (dataEmpty && (headerCell === '' || UNNAMED_HEADER.test(headerCell))) {
+            continue;
+        }
+        keepCols.push(col);
+    }
+    if (keepCols.length === 0) {
+        keepCols.push(0);
+    }
+    const columnsRemoved = colCount - keepCols.length;
+    const pickCols = (row) => keepCols.map((col) => padRow(row, colCount)[col] ?? '');
+    const out = [];
+    out.push(formatTableRow(pickCols(header)));
+    if (hasSeparator || dataRows.length > 0) {
+        out.push(formatTableRow(keepCols.map(() => '---')));
+    }
+    for (const row of dataRows) {
+        out.push(formatTableRow(pickCols(row)));
+    }
+    return { lines: out, nanCellsReplaced, rowsRemoved, columnsRemoved };
+}
+/**
+ * Clean spreadsheet-derived Markdown document-wide (table blocks only).
+ */
+function cleanupSpreadsheetMarkdown(markdown) {
+    const charsBefore = Buffer.byteLength(markdown, 'utf8');
+    const inputLines = markdown.split(/\r?\n/);
+    const outputLines = [];
+    let nanCellsReplaced = 0;
+    let rowsRemoved = 0;
+    let columnsRemoved = 0;
+    let index = 0;
+    while (index < inputLines.length) {
+        const line = inputLines[index];
+        if (!isTableRow(line)) {
+            outputLines.push(line);
+            index += 1;
+            continue;
+        }
+        const block = [];
+        while (index < inputLines.length && isTableRow(inputLines[index])) {
+            block.push(inputLines[index]);
+            index += 1;
+        }
+        const cleaned = cleanupTableBlock(block);
+        nanCellsReplaced += cleaned.nanCellsReplaced;
+        rowsRemoved += cleaned.rowsRemoved;
+        columnsRemoved += cleaned.columnsRemoved;
+        outputLines.push(...cleaned.lines);
+    }
+    const result = outputLines.join('\n');
+    return {
+        markdown: result,
+        stats: {
+            nanCellsReplaced,
+            rowsRemoved,
+            columnsRemoved,
+            charsBefore,
+            charsAfter: Buffer.byteLength(result, 'utf8'),
+        },
+    };
+}

package/dist/core/next-steps.js

@@ -60,11 +60,24 @@ function printNextSteps(input) {
     lines.push('4. 随时用下面的命令查看进度: ' +
         picocolors_1.default.cyan('cat .harness-build-state.yaml'));
     lines.push('');
-    if (input.hasSource) {
-        lines.push(picocolors_1.default.bold('Baseline Repomix（XML，默认）'));
+    if (input.repomixGenerated) {
+        lines.push(picocolors_1.default.bold('Baseline Repomix（XML）'));
         lines.push('   输出文件: ' + picocolors_1.default.cyan((0, repomix_pack_1.repomixPackRelFile)()));
         lines.push('');
     }
+    else if (input.hasSource) {
+        lines.push(picocolors_1.default.bold('Baseline Repomix（可选，默认关闭）'));
+        lines.push('   适用：大基线整库鸟瞰、只接受单文件上下文的工具、封存留档；' +
+            '日常 S40/S50 以 ' +
+            picocolors_1.default.cyan('baseline/code/') +
+            ' 为准即可');
+        lines.push('   启用：重新 build 并加 ' +
+            picocolors_1.default.cyan('--repomix') +
+            '（须保留 --baseline）→ ' +
+            picocolors_1.default.cyan((0, repomix_pack_1.repomixPackRelFile)()));
+        lines.push('   说明：svharnessbuild README「Repomix」');
+        lines.push('');
+    }
     if (wikiMode === 'tasks') {
         lines.push(picocolors_1.default.bold('Baseline wiki 任务清单已生成（默认 tasks-only 模式）'));
         lines.push('   清单位置: ' + picocolors_1.default.cyan('baseline/wiki/TASKS.md'));

package/dist/core/repomix-apply-hint.js

@@ -0,0 +1,68 @@
+"use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.REPOMIX_APPLY_HINT_PLACEHOLDER = void 0;
+exports.resolveRepomixPackRel = resolveRepomixPackRel;
+exports.renderRepomixApplyHintMarkdown = renderRepomixApplyHintMarkdown;
+exports.buildRepomixApplyHintReplacement = buildRepomixApplyHintReplacement;
+exports.applyRepomixHintPlaceholder = applyRepomixHintPlaceholder;
+const fs_extra_1 = __importDefault(require("fs-extra"));
+const node_path_1 = __importDefault(require("node:path"));
+const harness_yaml_baseline_1 = require("./harness-yaml-baseline");
+const repomix_pack_1 = require("./repomix-pack");
+exports.REPOMIX_APPLY_HINT_PLACEHOLDER = '__REPOMIX_APPLY_HINT__';
+/**
+ * Resolve Repomix pack path relative to harness root: harness.yaml field first, then file existence.
+ */
+async function resolveRepomixPackRel(harnessRoot) {
+    const doc = await (0, harness_yaml_baseline_1.readHarnessYamlDoc)(harnessRoot);
+    const fromYaml = (0, harness_yaml_baseline_1.getBaselineRepomixPackFromDoc)(doc);
+    if (fromYaml) {
+        const abs = node_path_1.default.join(harnessRoot, fromYaml);
+        if (await fs_extra_1.default.pathExists(abs))
+            return fromYaml;
+    }
+    const defaultRel = (0, repomix_pack_1.repomixPackRelFile)();
+    const defaultAbs = node_path_1.default.join(harnessRoot, defaultRel);
+    if (await fs_extra_1.default.pathExists(defaultAbs))
+        return defaultRel;
+    return undefined;
+}
+function renderRepomixApplyHintMarkdown(input) {
+    const harnessScoped = `./${input.harnessDirName}/${input.packRel.replace(/\\/g, '/')}`;
+    const codeScoped = `./${input.harnessDirName}/baseline/code/`;
+    const body = [
+        '**Baseline Repomix（可选快照）**',
+        '',
+        `- **路径**：\`${input.packRel}\`（项目根视角：\`${harnessScoped}\`）`,
+        '- **用途**：将 `baseline/code/` 打成单文件 XML，便于整库鸟瞰、单文件 attach；与 `baseline/wiki/` 互补。',
+        '- **优先级**：**权威参考实现仍为** `baseline/code/`（行级引用、specs 追溯、守则不变）；Repomix **不得**替代对具体文件的精读，也不得作为 specs 契约来源。',
+        `- **读取**：优先 Read 上述 XML；上下文过大时只读相关片段，或退回 \`${codeScoped}<repo-relative>\`。`,
+        '- **典型场景**：架构摸底、模块边界初扫；实现细节与交付校验仍以 specs + `baseline/code/` 为准。',
+    ];
+    if (input.blockquote) {
+        return ['> Repomix 快照（build 已启用 `--repomix`）', ...body.map((l) => (l ? `> ${l}` : '>'))].join('\n');
+    }
+    return ['## Baseline Repomix（可选快照）', '', ...body].join('\n');
+}
+async function buildRepomixApplyHintReplacement(input) {
+    const packRel = await resolveRepomixPackRel(input.harnessRoot);
+    if (!packRel)
+        return '';
+    const block = renderRepomixApplyHintMarkdown({
+        harnessDirName: input.harnessDirName,
+        packRel,
+        blockquote: input.blockquote,
+    });
+    return `${block}\n\n`;
+}
+function applyRepomixHintPlaceholder(content, hint, placeholder = exports.REPOMIX_APPLY_HINT_PLACEHOLDER) {
+    if (content.includes(placeholder)) {
+        return content.replace(new RegExp(placeholder, 'g'), hint.trimEnd() ? hint : '');
+    }
+    if (!hint.trim())
+        return content;
+    return `${content.trimEnd()}\n\n${hint}`;
+}

package/dist/core/repomix-pack.js

@@ -6,6 +6,11 @@ Object.defineProperty(exports, "__esModule", { value: true });
 exports.REPOMIX_PACK_FILENAME = exports.REPOMIX_BASELINE_REL_DIR = void 0;
 exports.repomixPackRelFile = repomixPackRelFile;
 exports.runRepomixPackBaseline = runRepomixPackBaseline;
+/**
+ * Optional baseline snapshot via Repomix (single XML under `baseline/repomix/`).
+ * Enabled only when `svharness build --repomix` is passed with `--baseline`.
+ * Complements `baseline/code/` (per-file references); see svharnessbuild README § Repomix.
+ */
 const fs_extra_1 = __importDefault(require("fs-extra"));
 const node_path_1 = __importDefault(require("node:path"));
 const repomix_1 = require("repomix");

package/dist/index.js

@@ -55,6 +55,7 @@ function buildSectionFromOpts(opts, harnessName) {
         force: opts.force,
         yes: opts.yes,
         verbose: opts.verbose,
+        repomix: opts.repomix,
         generateWiki: opts.generateWiki,
         wikiTasksOnly: opts.wikiTasksOnly,
         wikiLang: opts.wikiLang === 'en' ? 'en' : opts.wikiLang === 'zh' ? 'zh' : undefined,
@@ -87,6 +88,7 @@ async function runBuildAction(opts, cmd) {
             force: !!merged.force,
             yes: !!merged.yes,
             verbose: !!merged.verbose,
+            repomix: !!merged.repomix,
             generateWiki: !!merged.generateWiki,
             wikiTasksOnly: !!merged.wikiTasksOnly,
             wikiLang: merged.wikiLang === 'en' ? 'en' : merged.wikiLang === 'zh' ? 'zh' : undefined,
@@ -120,6 +122,7 @@ function attachBuildOptions(cmd) {
         .option('--arch <arch>', '架构模板：' + (0, validate_args_1.listSupportedArches)().join(' | '), DEFAULT_ARCH)
         .option('--agent <agent>', '目标 Agent：' + (0, validate_args_1.listSupportedAgents)().join(' | '), DEFAULT_AGENT)
         .option('--baseline <path|url>', '【可选】基线源码路径或 Git 仓库地址')
+        .option('--repomix', '【可选，需 --baseline】生成 baseline/repomix/repomix-pack.xml：大基线整库鸟瞰、单文件上下文工具、封存留档；日常 build 默认关闭，详见 README「Repomix」')
         .option('--requirements <path>', '【可选】需求文档输入路径（文件或目录）')
         .option('--references <path>', '【可选】参考资料输入路径（文件或目录）')
         .option('--extra-skills <path...>', '【可选】额外运行期资源（skills/rules 混放，先入 _incoming）')
@@ -231,6 +234,8 @@ function main() {
         .option('--timeout-sec <n>', '【默认 120】超时秒数', (v) => Number(v))
         .option('--type <type>', 'requirements | references')
         .option('--force', '覆盖已存在同名 .md')
+        .option('--split-sheets-suffix <suffix>', 'xlsx/xls 按 sheet（##）拆分时的子目录后缀', '_split')
+        .option('--no-split-sheets', '不将 xlsx/xls 合并 md 按 ## 拆分为多文件')
         .option('-y, --yes', '跳过交互确认')
         .option('--verbose', '显示详细日志')
         .action(async (opts, cmd) => {
@@ -246,6 +251,8 @@ function main() {
                 timeoutSec: opts.timeoutSec,
                 type: opts.type,
                 force: opts.force,
+                splitSheetsSuffix: opts.splitSheetsSuffix,
+                noSplitSheets: opts.noSplitSheets,
                 yes: opts.yes,
                 verbose: opts.verbose,
             }, loaded?.config.convert, loaded?.config.defaults, cmd);
@@ -259,6 +266,8 @@ function main() {
                 timeoutSec: merged.timeoutSec,
                 type: merged.type,
                 force: !!merged.force,
+                splitSheets: merged.noSplitSheets ? false : merged.splitSheets,
+                splitSheetsSuffix: merged.splitSheetsSuffix,
                 yes: !!merged.yes,
                 verbose: !!merged.verbose,
             });

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "svharness",
-  "version": "0.14.2",
+  "version": "0.14.7",
   "description": "CLI scaffolder for SDD-Driven Agent-Agnostic Coding Framework (harness)",
   "bin": {
     "svharness": "./bin/cli.js",

package/templates/_shared/apply-skills/harness-apply-skills-main.md

@@ -21,6 +21,8 @@ description: >
 4. 不修改 `__HARNESS_ROOT_REL__` 下的任何文件；harness 作为只读知识源。
 5. 入口链路以项目根 AI 入口文档为准：`AGENTS.md` 或 `CLAUDE.md`。
 
+__REPOMIX_APPLY_HINT__
+
 ## 典型触发
 
 - 应用 harness-apply-skills-main 完成 xxx 功能开发

package/templates/_shared/build-rules/harness-build-rule-chinese-only.md

@@ -6,7 +6,7 @@
 
 以下产出**必须**使用中文撰写：
 
-- `requirements/yaml/*.requirements.yaml` 中 `description`、`acceptance` 字段
+- `requirements/yaml/*.requirements.yaml` 中 `title`、`source_excerpt`、`description`、`acceptance` 字段
 - `specs/**/*.yaml` 中所有描述性字段（如 `description`、`note`、`summary`、`purpose`）
 - `agent-env/rules/**/*.md` 或 `*.mdc` 中正文段落、正反例注释、检测说明
 - `agent-env/skills/*/SKILL.md` 正文及 description
@@ -32,7 +32,7 @@
 ## 正反例
 
 正例：
-> `description: "根据 P_TMRAVA 信号显示或隐藏预约充电设置入口"`
+> `description: "当 P_TMRAVA=1 且车辆处于驻车状态时显示预约充电入口；当 P_TMRAVA=0 或车速>0 时隐藏入口。"`
 
 反例（严禁）：
 > `description: "Show or hide the scheduled charging settings entry based on P_TMRAVA signal"`

package/templates/_shared/build-rules/harness-build-rule-orchestrator-flow.md

@@ -14,12 +14,15 @@
 3. **S30_convert_docs** — 将 `requirements/raw/` 和 `references/raw/` 中的非 Markdown 原始文档统一转为 Markdown，产物落到对应 `md/` 目录。准入：S20_collect_inputs DONE；退出：每份源文档在对应 `md/` 目录中有同基名的 `.md` 文件。
 4. **S40_extract_requirements** — 由 `harness-build-skill-spec-builder` 将 raw 条目化到 `requirements/yaml/`。退出：
    - 已生成 `requirements/coverage-report.yaml`；
+   - `requirements/yaml/schema.json`（若存在）校验通过；
    - `unmapped` 为空，或已全部完成 waiver 与用户确认；
-   - 每条需求具备稳定 id 与可追溯锚点（允许有备案聚合，但不得无依据粗化）。
+   - 每条需求具备稳定 id 与可追溯锚点（允许有备案聚合，但不得无依据粗化）；
+   - 每条需求包含 `title`、`source_excerpt`、`description`，且不存在明显缩略风险（门禁策略可由 doctor/审查报告提供证据）。
 5. **S50_generate_specs** — 生成 `specs/{signals,ui,behavior,interfaces}/*.yaml`。退出：
    - 全部通过 `specs/*/schema.json` 校验；
    - 已产出 spec 覆盖率结果（建议 `specs/coverage-report.yaml`）；
-   - 每条 REQ 有 spec 映射或显式 N/A 理由。
+   - 每条 REQ 有 spec 映射或显式 N/A 理由；
+   - 深度启发式无 Critical（如 index-only signals、空 guard、断裂 bound_* 引用）。
 6. **S60_process_references**（阶段叙事：**references 处理**）— 对 S20 中的 references 执行处理与结构化：
    - 必须执行 `svharness convert`，不得跳过转换直接抽取；
    - 必须产出结构化索引（规制约束 / skills 候选 / signals / manuals，缺项需显式标注）；

package/templates/_shared/build-rules/harness-build-rule-pre-seal-review.md

@@ -21,10 +21,16 @@
 
 1. **需求可追溯**（若存在 requirements/yaml）：每条在已声明 spec 层有映射或 waiver。
 2. **覆盖率完整**：`requirements/coverage-report.yaml` 与（若存在）`specs/coverage-report.yaml` 可解析；`unmapped` 闭环。
-3. **描述完整性**：无 TBD/placeholder 占位语义。
+3. **描述完整性**：无 TBD/placeholder 占位语义，且 `description` 不得明显弱于 `source_excerpt`。
 4. **references / wiki / agent-env**（若目录存在）：与 S60、baseline 策略一致。
 5. **流程合规**、**中文与 agent-agnostic** 扫尾。
 
+补充抽检要求（至少随机 N=5 条或按项目规模调整）：
+
+- 抽检 `requirements/yaml`：确认 `source_excerpt` 保留原文约束（条件/数值/枚举），`description` 未删减关键语义。
+- 抽检 `specs/signals`：识别 index-only 信号（仅 id/name/type 且缺少协议/枚举语义）。
+- 抽检 `specs/behavior`：`transitions[].guard`/`action` 为空或占位语义应计入风险。
+
 ### Part B — 深度质量（按 specs.layers 启用）
 
 - 加载 `agent-env/review-profiles/<arch>.yaml` 或 `_default.yaml`。

package/templates/_shared/build-rules/harness-build-rule-requirements-extraction.md

@@ -23,7 +23,14 @@
      - `aggregation_reason`
      - 用户表单确认
 
-4. **覆盖率报告是 S40 必备产物**
+4. **原文优先，禁止缩略**
+   - `source_excerpt` 必须是可追溯锚点对应的原文摘录，禁止写成「见上文」「同前」「TBD」。
+   - `description` 必须覆盖 `source_excerpt` 里的条件、数值、枚举、时序，不得退化为标题短语。
+   - 推荐使用长度启发式审查：`description` 明显短于 `source_excerpt`（如 < 50%）时标记风险并复核。
+   - `title` 仅用于索引，禁止用 `title` 替代完整需求描述。
+   - `source_file` 必须指向 Agent 可读文本：优先 `requirements/md/<同名>.md`（convert 产物），或 `requirements/raw/` 下的 md/txt/代码文件；禁止引用 xlsx/pdf/docx 等难解析格式。
+
+5. **覆盖率报告是 S40 必备产物**
    - 必须生成 `requirements/coverage-report.yaml`。
    - 报告至少包含：
      - `extraction_strategy`
@@ -41,3 +48,5 @@
 - 禁止跳过源清点（inventory）直接写 `requirements/yaml`。
 - 禁止仅凭少量摘要条目宣称「提取完成」。
 - 禁止在未说明依据的情况下选择提取策略。
+- 禁止 `source_excerpt` 留空或使用占位语。
+- 禁止将多行表格仅提取第一列后声称完成条目化。