oh-my-knowledge 0.34.0 → 0.36.0

package/dist/cli/commands/list.js

@@ -0,0 +1,243 @@
+import { existsSync, lstatSync, readdirSync } from 'node:fs';
+import { isAbsolute, join, resolve } from 'node:path';
+import { Flags } from '@oclif/core';
+import { LANG_FLAG, bilingual } from '../oclif/i18n.js';
+import { BaseCommand } from '../oclif/base-command.js';
+import { tCli } from '../lib/i18n.js';
+import { resolveInstallSource } from '../../inputs/source-resolver.js';
+import { buildManagedListRows, globalManagedDir, hashArtifactSource, isDistributablePath, loadAllManagedRecords, managedDir, resolveManagedDir, } from '../../managed/index.js';
+// 本地源读取成本上限。skill 是小体量 markdown(+少量 references 资产),远超这些边界的源必是手改 /
+// 投毒,拒读避免 `omk list`(只读命令,读盘上可能随仓库分发的 locator)被 /dev/zero / 超大文件 / 巨型
+// 目录递归拖垮(DoS)。
+const MAX_FILE_SOURCE_BYTES = 8 * 1024 * 1024; // 单文件-skill 上限
+const MAX_DIR_SOURCE_BYTES = 64 * 1024 * 1024; // 目录-skill 整树累计上限
+const MAX_DIR_SOURCE_FILES = 4000; // 目录-skill 文件数上限
+const MAX_DIR_SOURCE_DEPTH = 64; // 目录递归深度上限
+/**
+ * 目录-skill 源的**有边界**整树哈:先恢复 resolveFileSource 的形态校验(SKILL.md 存在、是常规文件、非
+ * 软链 —— 否则 locator 可指向任意可读目录让 list 递归读整棵树),再 stat-walk(只 stat 不读)按与
+ * hashArtifactSource 同一 `isDistributablePath` 过滤累计 文件数 / 字节 / 深度,超界即返回 null(unreachable),
+ * 把单文件 DoS 不再换成目录递归 DoS。通过后才真正 hashArtifactSource。返回 null = 拒读 / 非法 skill 目录。
+ */
+function boundedDirSkillHash(abs) {
+    const skillMd = join(abs, 'SKILL.md');
+    let md;
+    try {
+        md = lstatSync(skillMd);
+    }
+    catch {
+        return null; // 无 SKILL.md → 不是 skill 目录,拒
+    }
+    if (md.isSymbolicLink() || !md.isFile() || md.nlink !== 1)
+        return null; // SKILL.md 必须是常规、非软链、非硬链
+    let files = 0;
+    let bytes = 0;
+    const within = (dir, segs, depth) => {
+        if (depth > MAX_DIR_SOURCE_DEPTH)
+            return false;
+        let entries;
+        try {
+            entries = readdirSync(dir, { withFileTypes: true });
+        }
+        catch {
+            return false;
+        }
+        for (const e of entries) {
+            const ns = [...segs, e.name];
+            if (!isDistributablePath(ns))
+                continue; // 与 hashArtifactSource 读取范围一致
+            if (e.isDirectory()) {
+                if (!within(join(dir, e.name), ns, depth + 1))
+                    return false;
+            }
+            else if (e.isFile()) { // 软链 Dirent 既非 isFile 也非 isDirectory → 天然跳过
+                if (++files > MAX_DIR_SOURCE_FILES)
+                    return false;
+                try {
+                    const fst = lstatSync(join(dir, e.name));
+                    if (fst.nlink !== 1)
+                        return false; // 硬链(nlink>1)可在树内别名树外敏感 inode → 拒读整树
+                    bytes += fst.size;
+                }
+                catch {
+                    return false;
+                }
+                if (bytes > MAX_DIR_SOURCE_BYTES)
+                    return false;
+            }
+        }
+        return true;
+    };
+    if (!within(abs, [], 0))
+        return null;
+    return hashArtifactSource(abs, true);
+}
+/**
+ * 探测一条受管记录**当前源**的状态(三态,喂 buildManagedListRow 判 drift / 生命周期)。
+ *   - 远端 git(带 url):源身份钉不可变 SHA(install 时 pin),内容恒定 → 直接取 record.contentHash,
+ *     不联网(list 是快读命令,不为 drift 检查发网络请求)。reachable。
+ *   - 本地 git:locator `git:<ref>:<spec>` 复用 resolveInstallSource 在**仓库对象库**内重物化重哈
+ *     (读取受 git 边界约束,无任意文件读 DoS)。解析不到(常因 `omk list` 的 cwd 与 install 时不同、
+ *     spec 随 cwd 漂)→ 抛错 → **reachable:false(未核,不当 stale)**,避免对未改动的 skill 误报漂移。
+ *   - 本地 file:locator 是绝对路径,但受管 JSON **用户可手改 / 随仓库分发**(无 install、无 opt-in 即被
+ *     loadAllManagedRecords 读到)。只读命令绝不盲读任意路径:**拒软链、只读常规文件 / 真目录、单文件
+ *     设 size cap**(挡 `evil.md → /dev/zero` 这类 readFileSync 无界 DoS 与项目外任意读)。守卫不过 →
+ *     reachable:false。目录-skill 整树哈本就跳软链(hashArtifactSource 用 isFile() 过滤)。
+ */
+export function probeSourceState(record) {
+    const s = record.source;
+    if (s.sourceKind === 'git' && s.url)
+        return { reachable: true, hash: record.contentHash };
+    try {
+        if (s.sourceKind === 'git') {
+            const resolved = resolveInstallSource(s.locator);
+            try {
+                return { reachable: true, hash: hashArtifactSource(resolved.localRoot, resolved.isDirectorySkill) };
+            }
+            finally {
+                resolved.cleanup();
+            }
+        }
+        // 本地 file 源:守卫后再读。locator 必须是 install 实际写出的形态(绝对路径) —— 受管 JSON 随仓库
+        // 分发、无 opt-in 即被读到,相对 locator 不是 install 产物,拒,避免按 cwd 解析到项目外。
+        if (!isAbsolute(s.locator))
+            return { reachable: false };
+        const abs = resolve(s.locator);
+        if (!existsSync(abs))
+            return { reachable: false };
+        const st = lstatSync(abs); // lstat:不跟随软链 —— 软链直接拒(防 evil.md → /dev/zero)
+        if (st.isSymbolicLink())
+            return { reachable: false };
+        if (s.isDirectorySkill) {
+            if (!st.isDirectory())
+                return { reachable: false };
+            const hash = boundedDirSkillHash(abs); // 形态校验 + 成本边界(防任意目录递归读 / 目录 DoS)
+            return hash === null ? { reachable: false } : { reachable: true, hash };
+        }
+        // 单文件-skill:恢复 install(resolveFileSource)的形态约束 —— 必须是 `.md` 常规文件、非硬链、≤ size cap。
+        // 否则攻击者可写 locator:`/etc/passwd` / `~/.ssh/id_rsa`(非 .md 直接拒),或用 `.md` 命名的**硬链**别名
+        // 树外敏感文件绕过扩展名 / 软链守卫(lstat 分不出硬链)→ 诱 list 把任意本地文件读进进程参与 hash。install
+        // 写出的是 nlink=1 的全新副本,拒 nlink>1 不误伤合法源。非 install 形态一律 reachable:false。
+        if (!/\.md$/i.test(abs) || !st.isFile() || st.nlink !== 1 || st.size > MAX_FILE_SOURCE_BYTES)
+            return { reachable: false };
+        return { reachable: true, hash: hashArtifactSource(abs, false) };
+    }
+    catch {
+        return { reachable: false };
+    }
+}
+/** CJK 全角字符按 2 列计宽,使含中文表头的列也能对齐。 */
+export function dispWidth(s) {
+    let w = 0;
+    for (const ch of s)
+        w += /[ᄀ-ᅟ⺀-꓏가-힣豈-﫿︰-﹏＀-｠￠-￦]/.test(ch) ? 2 : 1;
+    return w;
+}
+function pad(s, width) {
+    return s + ' '.repeat(Math.max(0, width - dispWidth(s)));
+}
+/** 按**显示宽度**截断(不是 code unit):逐码点累加 dispWidth,绝不切断 surrogate 对、CJK 也不溢出列。 */
+export function truncate(s, max) {
+    if (dispWidth(s) <= max)
+        return s;
+    let w = 0;
+    let out = '';
+    for (const ch of s) {
+        const cw = dispWidth(ch);
+        if (w + cw > max - 1)
+            break; // 留 1 列给省略号
+        out += ch;
+        w += cw;
+    }
+    return `${out}…`;
+}
+/** 洗不可信显示字符:managed JSON 可随仓库分发,name / sourceLabel / verdict 等字段塞进表格前必须先洗,
+ *  否则会破坏表格甚至伪造终端输出。一律映射到可见 U+FFFD(--json 路径保留原值给脚本)。
+ *  用 Unicode **属性类**而非手列码点 —— 手列清单天然有缺口(BiDi、U+2028 / 2029、Tags 块都曾漏一轮补一轮),
+ *  属性类一次覆盖整类、新码点自动纳入:
+ *    - `\p{Cc}` 控制符(C0 / C1 / DEL,含 ESC / 换行 / 回车 / TAB)→ 杀 ANSI / OSC 转义与终端控制;
+ *    - `\p{Cf}` 格式符(BiDi 重排 / 隔离、零宽、joiners、BOM、Tags、interlinear)→ 防 Trojan-Source 视觉伪造与零宽隐藏 / 分割;
+ *    - `\p{Zl}` / `\p{Zp}` 行 / 段分隔(U+2028 / 2029)→ LF 的 Unicode 孪生,防换行伪造表格行;
+ *    - `\p{Mn}` / `\p{Me}` 非间距 / 封闭组合附加符 → 变可见,避免零前进宽度令 dispWidth 与终端列错位
+ *      (间距组合符 `\p{Mc}` 合法占 1 列,保留);
+ *    - Hangul filler(U+115F / U+1160 / U+3164,属 Lo 不在上述任何类)→ 零宽显示诡计,补列。 */
+export function sanitizeCell(s) {
+    return s.replace(/[\p{Cc}\p{Cf}\p{Zl}\p{Zp}\p{Mn}\p{Me}ᅟᅠㅤ]/gu, '�');
+}
+export function renderTable(rows, lang) {
+    const headers = [
+        tCli('cli.list.col_name', lang),
+        tCli('cli.list.col_kind', lang),
+        tCli('cli.list.col_state', lang),
+        tCli('cli.list.col_verdict', lang),
+        tCli('cli.list.col_evidence', lang),
+        tCli('cli.list.col_source', lang),
+    ];
+    const cells = rows.map((r) => [
+        truncate(sanitizeCell(r.name), 40), // name 与 source 同为用户可控、可超长 → 同样按显示宽度截断,防撑爆表宽
+        r.kind, // ArtifactKind 枚举(validator 已收窄),无需洗
+        // 不可达 → 标「?」(drift 未核),绝不冒充 stale;reachable 且漂移才 stale ⚠️。
+        !r.reachable ? `${r.state} ?` : r.state === 'stale' ? 'stale ⚠️' : r.state,
+        r.latestVerdict ? sanitizeCell(r.latestVerdict) : '—',
+        `${r.currentEvidenceCount}/${r.totalEvidenceCount}`,
+        truncate(sanitizeCell(r.sourceLabel), 48),
+    ]);
+    const widths = headers.map((h, i) => Math.max(dispWidth(h), ...cells.map((c) => dispWidth(c[i]))));
+    const line = (c) => c.map((v, i) => pad(v, widths[i])).join('  ').trimEnd();
+    return [line(headers), ...cells.map(line)].join('\n');
+}
+export default class List extends BaseCommand {
+    static description = bilingual({
+        zh: '列出受管 skill 及其证据状态：生命周期（installed / measurable / stale）、最新 verdict、证据数、源。',
+        en: 'List managed skills with evidence status: lifecycle (installed / measurable / stale), latest verdict, evidence count, source.',
+    });
+    static examples = [
+        { description: bilingual({ zh: '列出当前项目的受管 skill', en: 'List managed skills in the current project' }), command: '<%= config.bin %> list' },
+        { description: bilingual({ zh: '列出全局受管 skill', en: 'List globally managed skills' }), command: '<%= config.bin %> list --global' },
+        { description: bilingual({ zh: '机器可读 JSON 输出', en: 'Machine-readable JSON output' }), command: '<%= config.bin %> list --json' },
+    ];
+    static flags = {
+        lang: LANG_FLAG,
+        global: Flags.boolean({
+            description: bilingual({ zh: '看全局受管目录（~/.oh-my-knowledge/managed）而非项目 .omk/managed', en: 'Show the global managed dir (~/.oh-my-knowledge/managed) instead of project .omk/managed' }),
+        }),
+        json: Flags.boolean({
+            description: bilingual({ zh: '输出 JSON（含完整可比性 marker），供脚本消费', en: 'Output JSON (with full comparability markers) for scripts' }),
+        }),
+    };
+    async run() {
+        const { flags } = await this.parse(List);
+        const lang = this.lang;
+        await this.runWithCliExit(async () => {
+            const dir = flags.global ? globalManagedDir() : resolveManagedDir(managedDir());
+            const records = loadAllManagedRecords(dir);
+            const rows = buildManagedListRows(records, probeSourceState);
+            if (flags.json) {
+                // 版本化信封 —— 与 eval / doctor / diagnosis 等机读出口一致(都带 schemaVersion),让未来字段增删 /
+                // 改名是可检测的版本 bump,而非脚本静默 break。rows 的逐行形态见 ManagedListRow。
+                this.log(JSON.stringify({ schemaVersion: 1, rows }, null, 2));
+                return;
+            }
+            if (rows.length === 0) {
+                process.stderr.write(tCli('cli.list.empty', lang));
+                process.stderr.write(tCli('cli.list.empty_hint', lang));
+                return;
+            }
+            const scope = dir === globalManagedDir()
+                ? (lang === 'zh' ? '全局' : 'global')
+                : (lang === 'zh' ? '项目' : 'project');
+            process.stderr.write(tCli('cli.list.header', lang, { scope, count: rows.length }));
+            this.log(renderTable(rows, lang));
+            // 注脚块前留一行空白(无论先触发哪条 note);空行挂在块上而非 drift 分支,避免只 unreachable 时丢分隔。
+            const hasDrift = rows.some((r) => r.drifted);
+            const hasUnreachable = rows.some((r) => !r.reachable);
+            if (hasDrift || hasUnreachable)
+                process.stderr.write('\n');
+            if (hasDrift)
+                process.stderr.write(tCli('cli.list.drift_note', lang));
+            if (hasUnreachable)
+                process.stderr.write(tCli('cli.list.unreachable_note', lang));
+            process.stderr.write(tCli('cli.list.legend', lang));
+        });
+    }
+}

package/dist/cli/commands/sample.d.ts

@@ -6,7 +6,7 @@ export declare function collectSampleDesignFailureIds(report: Pick<Report, 'resu
 export declare function assertFixReportMatchesCurrentInputs(params: {
     report: Pick<Report, 'meta'>;
     treatmentName: string;
-    skillContent: string;
+    currentContentHash: string;
     samples: SampleType[];
     sampleIds: Set<string>;
     lang?: CliLang;

package/dist/cli/commands/sample.js

@@ -9,7 +9,8 @@ import { CliExit } from '../lib/cli-exit.js';
 import { tCli } from '../lib/i18n.js';
 import { DEFAULT_REPORTS_DIR } from '../lib/parse-run-config.js';
 import { loadSamples, parseYaml } from '../../inputs/load-samples.js';
-import { hashSample, hashString } from '../../eval-core/evaluation-reporting.js';
+import { hashSample } from '../../eval-core/evaluation-reporting.js';
+import { hashArtifactSource } from '../../inputs/content-hash.js';
 function isRecord(value) {
     return typeof value === 'object' && value !== null && !Array.isArray(value);
 }
@@ -48,20 +49,29 @@ export function collectSampleDesignFailureIds(report, treatmentName) {
     return ids;
 }
 export function assertFixReportMatchesCurrentInputs(params) {
-    const { report, treatmentName, skillContent, samples, sampleIds } = params;
+    const { report, treatmentName, currentContentHash, samples, sampleIds } = params;
     const lang = params.lang ?? 'zh';
     const issues = [];
-    const expectedSkillHash = report.meta.artifactHashes?.[treatmentName];
-    const currentSkillHash = hashString(skillContent);
-    if (!expectedSkillHash) {
+    // schemaVersion < 2 的报告:artifactHashes 是旧「仅 SKILL.md 正文文本」哈,与当前「整棵可分发树」哈
+    // 不同空间,直接比对会必然误报不一致。识别后给可见提示(归入 issues → 触发「请先重跑 eval」),
+    // 不拿旧文本哈与当前树哈错配比对。sample 指纹口径未变,下面照常校。
+    if ((report.meta.schemaVersion ?? 0) < 2) {
         issues.push(lang === 'zh'
-            ? `报告缺少 ${treatmentName} 的 skill 指纹，无法确认诊断对应当前 SKILL.md。`
-            : `Report is missing the skill hash for ${treatmentName}; cannot verify it matches the current SKILL.md.`);
+            ? `报告早于树哈纪元（skill 指纹口径已从「仅 SKILL.md 文本」改为「整棵可分发树」），无法与当前指纹比对。`
+            : `Report predates the tree-hash era (skill fingerprint changed from SKILL.md-body-text to whole-tree); cannot compare against the current fingerprint.`);
     }
-    else if (expectedSkillHash !== currentSkillHash) {
-        issues.push(lang === 'zh'
-            ? `skill 指纹不一致：报告 ${expectedSkillHash}，当前 ${currentSkillHash}。`
-            : `Skill hash mismatch: report ${expectedSkillHash}, current ${currentSkillHash}.`);
+    else {
+        const expectedSkillHash = report.meta.artifactHashes?.[treatmentName];
+        if (!expectedSkillHash) {
+            issues.push(lang === 'zh'
+                ? `报告缺少 ${treatmentName} 的 skill 指纹，无法确认诊断对应当前 SKILL.md。`
+                : `Report is missing the skill hash for ${treatmentName}; cannot verify it matches the current SKILL.md.`);
+        }
+        else if (expectedSkillHash !== currentContentHash) {
+            issues.push(lang === 'zh'
+                ? `skill 指纹不一致：报告 ${expectedSkillHash}，当前 ${currentContentHash}。`
+                : `Skill hash mismatch: report ${expectedSkillHash}, current ${currentContentHash}.`);
+        }
     }
     const reportSampleHashes = report.meta.sampleHashes;
     if (!reportSampleHashes) {
@@ -196,11 +206,14 @@ async function runSampleFix(args, flags, lang) {
         process.stderr.write(lang === 'zh' ? '✅ 没有 sample_design 类型的失败，无需修复\n' : '✅ No sample_design failures found, nothing to fix\n');
         return;
     }
+    // 当前内容指纹走整树哈,与 eval 报告口径一致:dir-skill(用户传 .../SKILL.md)哈整棵 skill 目录、
+    // 单文件 .md 哈单文件字节。
+    const currentContentHash = hashArtifactSource(isDir ? skillDir : resolvedSkillPath, isDir);
     try {
         assertFixReportMatchesCurrentInputs({
             report,
             treatmentName,
-            skillContent,
+            currentContentHash,
             samples,
             sampleIds: sampleDesignIds,
             lang,

package/dist/cli/lib/cmd-flags.d.ts

@@ -108,6 +108,7 @@ export interface EvalFlags {
     'trivial-diff'?: string;
     'report-only'?: boolean;
     'no-gate'?: boolean;
+    'no-evidence'?: boolean;
 }
 export interface EvolveArgs {
     skillPath: string;

package/dist/cli/lib/i18n-dict/install.d.ts

@@ -1,3 +1,3 @@
 import type { CliMessage } from './types.js';
-export type InstallMessageKey = 'cli.install.asset_missing' | 'cli.install.unknown_input' | 'cli.install.unknown_target' | 'cli.install.invalid_target_combo' | 'cli.install.no_detected_targets' | 'cli.install.target_exists' | 'cli.install.plan' | 'cli.install.plan_skill' | 'cli.install.installed' | 'cli.install.kind_unsupported' | 'cli.install.copied' | 'cli.install.adopted' | 'cli.install.registered' | 'cli.install.target_overlaps_source' | 'cli.install.path_not_found' | 'cli.install.skillmd_missing' | 'cli.install.skillmd_is_symlink' | 'cli.install.not_a_skill' | 'cli.install.not_a_git_repo' | 'cli.install.git_skill_not_found' | 'cli.install.git_unsafe_path' | 'cli.install.next_hint';
+export type InstallMessageKey = 'cli.install.asset_missing' | 'cli.install.unknown_input' | 'cli.install.unknown_target' | 'cli.install.invalid_target_combo' | 'cli.install.no_detected_targets' | 'cli.install.target_exists' | 'cli.install.plan' | 'cli.install.plan_skill' | 'cli.install.installed' | 'cli.install.kind_unsupported' | 'cli.install.copied' | 'cli.install.adopted' | 'cli.install.registered' | 'cli.install.target_overlaps_source' | 'cli.install.path_not_found' | 'cli.install.skillmd_missing' | 'cli.install.skillmd_is_symlink' | 'cli.install.not_a_skill' | 'cli.install.not_a_git_repo' | 'cli.install.git_skill_not_found' | 'cli.install.git_unsafe_path' | 'cli.install.invalid_remote_url' | 'cli.install.remote_fetch_failed' | 'cli.install.remote_ref_not_found' | 'cli.install.remote_skill_not_found' | 'cli.install.git_ref_needs_url' | 'cli.install.next_hint';
 export declare const installDict: Record<InstallMessageKey, CliMessage>;

package/dist/cli/lib/i18n-dict/install.js

@@ -83,6 +83,26 @@ export const installDict = {
         zh: 'git tree 含越界路径 {path}（.. / 绝对路径 / 空段），拒绝物化以防写出临时目录。该 skill 的 git tree 可能被手工构造，请核查来源。',
         en: 'git tree contains an out-of-bounds path {path} (.. / absolute / empty segment); refusing to materialize to avoid escaping the temp dir. The skill git tree may be hand-crafted; verify the source.',
     },
+    'cli.install.invalid_remote_url': {
+        zh: '不是合法的 git 远端 URL：{url}。支持 https:// / ssh:// / git:// / file:// 或 scp 形式 git@host:path。',
+        en: 'Not a valid git remote URL: {url}. Supported: https:// / ssh:// / git:// / file:// or scp-form git@host:path.',
+    },
+    'cli.install.remote_fetch_failed': {
+        zh: '从远端 {url} 拉取 ref {ref} 失败。请检查 URL、ref 是否存在、以及本机 git 凭证（SSH key / credential helper）。',
+        en: 'Failed to fetch ref {ref} from remote {url}. Check the URL, whether the ref exists, and your local git credentials (SSH key / credential helper).',
+    },
+    'cli.install.remote_ref_not_found': {
+        zh: '远端 {url} 上解析不到 ref {ref}。',
+        en: 'Could not resolve ref {ref} on remote {url}.',
+    },
+    'cli.install.remote_skill_not_found': {
+        zh: '在远端 {url} 的 ref {ref} 下找不到 skill {name}（既无 {name}/SKILL.md 也无 {name}.md）。',
+        en: 'Skill {name} not found at ref {ref} of remote {url} (neither {name}/SKILL.md nor {name}.md).',
+    },
+    'cli.install.git_ref_needs_url': {
+        zh: '--git-ref 需要配 --git-url 一起用（远端 git 源 = URL + ref + 仓库内路径）。',
+        en: '--git-ref requires --git-url (a remote git source = URL + ref + in-repo path).',
+    },
     'cli.install.next_hint': {
         zh: '现在可以在 coding agent 中说「用 omk 评测这个 skill」。',
         en: 'You can now ask your coding agent: "use omk to evaluate this skill".',

package/dist/cli/lib/i18n-dict/list.d.ts

@@ -0,0 +1,3 @@
+import type { CliMessage } from './types.js';
+export type ListMessageKey = 'cli.list.header' | 'cli.list.empty' | 'cli.list.empty_hint' | 'cli.list.col_name' | 'cli.list.col_kind' | 'cli.list.col_state' | 'cli.list.col_verdict' | 'cli.list.col_evidence' | 'cli.list.col_source' | 'cli.list.drift_note' | 'cli.list.unreachable_note' | 'cli.list.legend';
+export declare const listDict: Record<ListMessageKey, CliMessage>;

package/dist/cli/lib/i18n-dict/list.js

@@ -0,0 +1,32 @@
+export const listDict = {
+    'cli.list.header': {
+        zh: '受管 skill（{scope}，{count} 条）\n',
+        en: 'Managed skills ({scope}, {count})\n',
+    },
+    'cli.list.empty': {
+        zh: '没有受管记录。\n',
+        en: 'No managed records.\n',
+    },
+    'cli.list.empty_hint': {
+        zh: '用 omk install <skill> 登记并分发一个 skill 后，它会出现在这里。\n',
+        en: 'Run omk install <skill> to register and distribute a skill; it will show up here.\n',
+    },
+    'cli.list.col_name': { zh: '名称', en: 'NAME' },
+    'cli.list.col_kind': { zh: '类型', en: 'KIND' },
+    'cli.list.col_state': { zh: '状态', en: 'STATE' },
+    'cli.list.col_verdict': { zh: 'VERDICT', en: 'VERDICT' },
+    'cli.list.col_evidence': { zh: '证据', en: 'EVIDENCE' },
+    'cli.list.col_source': { zh: '源', en: 'SOURCE' },
+    'cli.list.drift_note': {
+        zh: '⚠️ = 源内容已漂移、脱离证据（stale）；重跑 omk eval 重新取证。\n',
+        en: '⚠️ = source content drifted off its evidence (stale); re-run omk eval to re-measure.\n',
+    },
+    'cli.list.unreachable_note': {
+        zh: '? = 源此处不可达 / 拒读，drift 未核（非 stale）；本地 git 源请在原仓库根目录跑 omk list。\n',
+        en: '? = source unreachable / refused here, drift unchecked (not stale); for a local git source run omk list from the original repo root.\n',
+    },
+    'cli.list.legend': {
+        zh: '证据列 = 当前有效 / 全部（历史含旧内容证据，供回滚）。\n',
+        en: 'EVIDENCE column = current / total (history keeps old-content evidence for rollback).\n',
+    },
+};

package/dist/cli/lib/i18n-dict/run.d.ts

@@ -1,3 +1,3 @@
 import type { CliMessage } from './types.js';
-export type RunMessageKey = 'cli.progress.preflight_starting' | 'cli.progress.sample_retry' | 'cli.progress.sample_error' | 'cli.progress.sample_executing' | 'cli.progress.sample_exec_done' | 'cli.progress.output_preview' | 'cli.progress.judging' | 'cli.progress.judged' | 'cli.progress.skipped' | 'cli.progress.sample_done' | 'cli.progress.sample_failed_done' | 'cli.run.invalid_repeat' | 'cli.run.invalid_judge_repeat' | 'cli.run.no_debias_length_active' | 'cli.run.invalid_bootstrap_samples' | 'cli.run.bootstrap_samples_too_large' | 'cli.run.dry_run_no_scores' | 'cli.run.skill_section' | 'cli.run.run_section' | 'cli.run.batch_complete' | 'cli.run.batch_verdict_header' | 'cli.run.batch_child_report_missing' | 'cli.run.eval_complete' | 'cli.run.tally' | 'cli.run.report_saved' | 'cli.run.report_only_gate_skipped' | 'cli.run.report_server_running' | 'cli.run.report_server_view' | 'cli.run.report_server_stop' | 'cli.run.no_serve_in_non_tty' | 'cli.run.no_serve_view_hint' | 'cli.run.gold_load_failed' | 'cli.run.gold_load_issue' | 'cli.run.contamination_warning' | 'cli.run.skip_connectivity_warning';
+export type RunMessageKey = 'cli.progress.preflight_starting' | 'cli.progress.sample_retry' | 'cli.progress.sample_error' | 'cli.progress.sample_executing' | 'cli.progress.sample_exec_done' | 'cli.progress.output_preview' | 'cli.progress.judging' | 'cli.progress.judged' | 'cli.progress.skipped' | 'cli.progress.sample_done' | 'cli.progress.sample_failed_done' | 'cli.run.invalid_repeat' | 'cli.run.invalid_judge_repeat' | 'cli.run.no_debias_length_active' | 'cli.run.invalid_bootstrap_samples' | 'cli.run.bootstrap_samples_too_large' | 'cli.run.dry_run_no_scores' | 'cli.run.skill_section' | 'cli.run.run_section' | 'cli.run.batch_complete' | 'cli.run.batch_verdict_header' | 'cli.run.batch_child_report_missing' | 'cli.run.eval_complete' | 'cli.run.tally' | 'cli.run.report_saved' | 'cli.run.evidence_recorded' | 'cli.run.evidence_recorded_unbound' | 'cli.run.report_only_gate_skipped' | 'cli.run.report_server_running' | 'cli.run.report_server_view' | 'cli.run.report_server_stop' | 'cli.run.no_serve_in_non_tty' | 'cli.run.no_serve_view_hint' | 'cli.run.gold_load_failed' | 'cli.run.gold_load_issue' | 'cli.run.contamination_warning' | 'cli.run.skip_connectivity_warning';
 export declare const runDict: Record<RunMessageKey, CliMessage>;

package/dist/cli/lib/i18n-dict/run.js

@@ -99,6 +99,14 @@ export const runDict = {
         zh: '📄 报告已保存到: {path}\n',
         en: '📄 Report saved to: {path}\n',
     },
+    'cli.run.evidence_recorded': {
+        zh: '🔖 已为受管 skill「{name}」记录评测证据 → measurable\n',
+        en: '🔖 Recorded eval evidence for managed skill "{name}" → measurable\n',
+    },
+    'cli.run.evidence_recorded_unbound': {
+        zh: '🔖 受管 skill「{name}」：评测内容与当前安装版本指纹不一致，证据已留存但不绑当前版本\n',
+        en: '🔖 Managed skill "{name}": eval content differs from the installed version; evidence kept but not bound to current\n',
+    },
     'cli.run.report_only_gate_skipped': {
         zh: 'ℹ 已启用 report-only 模式：保留 verdict 输出，但本次不使用 verdict 改写 exit code。\n',
         en: 'ℹ Report-only mode enabled: verdict is still printed, but it will not affect the exit code.\n',

package/dist/cli/lib/i18n-dict.d.ts

@@ -56,8 +56,9 @@ import { type GenMessageKey } from './i18n-dict/gen.js';
 import { type HelpMessageKey } from './i18n-dict/help.js';
 import { type InitMessageKey } from './i18n-dict/init.js';
 import { type InstallMessageKey } from './i18n-dict/install.js';
+import { type ListMessageKey } from './i18n-dict/list.js';
 import { type RunMessageKey } from './i18n-dict/run.js';
 import type { CliMessage } from './i18n-dict/types.js';
 export type { CliMessage } from './i18n-dict/types.js';
-export type CliMessageKey = CommonMessageKey | EvolveMessageKey | GenMessageKey | HelpMessageKey | InitMessageKey | InstallMessageKey | RunMessageKey;
+export type CliMessageKey = CommonMessageKey | EvolveMessageKey | GenMessageKey | HelpMessageKey | InitMessageKey | InstallMessageKey | ListMessageKey | RunMessageKey;
 export declare const CLI_DICT: Record<CliMessageKey, CliMessage>;

package/dist/cli/lib/i18n-dict.js

@@ -56,6 +56,7 @@ import { genDict } from './i18n-dict/gen.js';
 import { helpDict } from './i18n-dict/help.js';
 import { initDict } from './i18n-dict/init.js';
 import { installDict } from './i18n-dict/install.js';
+import { listDict } from './i18n-dict/list.js';
 import { runDict } from './i18n-dict/run.js';
 export const CLI_DICT = {
     ...commonDict,
@@ -64,5 +65,6 @@ export const CLI_DICT = {
     ...helpDict,
     ...initDict,
     ...installDict,
+    ...listDict,
     ...runDict,
 };

package/dist/cli/lib/parse-run-config/variant-resolution.js

@@ -24,6 +24,13 @@ import { configVariantsToSpecs } from '../../../inputs/eval-config.js';
  *  引导用户改用 --control-cwd / --treatment-cwd 或 eval.yaml 的 variant.cwd。git 修订语法 `@{...}`
  *  由 parseVariantCwd 保护、不误判。cwd 由调用方在边界注入(见 eval-runner)。 */
 function cliVariantSpec(rawExpr, role, cwd) {
+    // 远端 git 不走 CLI 字符串(URL 的 `:`/`@` 会被 parseGitInput / parseVariantCwd 误切)——
+    // 先于 @cwd guard 拦协议 URL 与 scp 形式 `git@host:path`,给明确的「走 eval.yaml」指引,
+    // 而非让 scp 形式落到下面 @cwd 的迁移报错(误导)。绝对本地路径 `/abs/skill.md` 不在此列。
+    if (/^(https?|ssh|git):\/\//i.test(rawExpr) || /^[\w.-]+@[\w.-]+:/.test(rawExpr)) {
+        throw new Error(`远端 git 源不支持经 --${role} 字符串传入: "${rawExpr}"。请在 eval.yaml 的 variant 上用结构化 `
+            + `git: { url, ref, spec } 字段(避开 URL 里的 : / @ 被误切),CLI 仅支持本地路径与 git:<ref>:<spec>。`);
+    }
     // 探测旧 name@cwd 形态报错。注:含合法 `@`(非 `@{`)的路径(如 /x/@dir/skill.md)会被一并
     // 误判 —— 属 pre-existing 限制(这类路径本就不被 @cwd 支持),报错文案仍指向迁移指引。
     if (parseVariantCwd(rawExpr).cwd !== undefined) {

package/dist/cli/lib/run-tally.js

@@ -19,7 +19,7 @@ export function computeRunTally(report) {
             failed += s.errorCount;
         }
     };
-    if (report.reportKind === 'batch-evaluation') {
+    if (report.kind === 'batch-evaluation') {
         for (const item of report.items)
             accumulate(item.summary);
     }

package/dist/cli/lib/shared.js

@@ -5,7 +5,7 @@ export function requireEvaluationReport(report, id, lang) {
         console.error(tCli('cli.common.report_not_found', lang, { id }));
         throw new CliExit(1);
     }
-    if (report.reportKind === 'batch-evaluation') {
+    if (report.kind === 'batch-evaluation') {
         console.error(lang === 'zh'
             ? `报告 ${id} 是 BatchEvaluationReport。该命令需要单次 EvaluationReport；请使用其中的 child reportId。`
             : `Report ${id} is a BatchEvaluationReport. This command requires an EvaluationReport; use a child reportId from the batch.`);

package/dist/doctor/index.js

@@ -26,10 +26,10 @@ export function resolveDoctorTargets(target, cwd) {
         const skillsDir = join(cwd, 'skills');
         if (existsSync(skillsDir) && statSync(skillsDir).isDirectory()) {
             const variants = discoverVariants(skillsDir).filter((v) => v !== 'baseline');
-            return variants.length > 0 ? resolveArtifacts(skillsDir, variants, { strictBaseline: false }) : [];
+            return variants.length > 0 ? resolveArtifacts(skillsDir, variants, { strictBaseline: false, materialize: false }) : [];
         }
         const variants = discoverVariants(cwd).filter((v) => v !== 'baseline');
-        return variants.length > 0 ? resolveArtifacts(cwd, variants, { strictBaseline: false }) : [];
+        return variants.length > 0 ? resolveArtifacts(cwd, variants, { strictBaseline: false, materialize: false }) : [];
     }
     const absTarget = resolve(target);
     if (!existsSync(absTarget)) {
@@ -38,7 +38,7 @@ export function resolveDoctorTargets(target, cwd) {
     const stat = statSync(absTarget);
     if (stat.isFile() && absTarget.endsWith('.md')) {
         // 单文件:用 file-path 模式(走 resolveArtifacts 的 "包含 /" 分支)
-        return resolveArtifacts(dirname(absTarget), [absTarget], { strictBaseline: false });
+        return resolveArtifacts(dirname(absTarget), [absTarget], { strictBaseline: false, materialize: false });
     }
     if (stat.isDirectory()) {
         // 目录自身就是 directory-skill (含 SKILL.md): 按单个 skill 解析,
@@ -48,10 +48,10 @@ export function resolveDoctorTargets(target, cwd) {
         // skillRoot 丢失,assets/foo.md 这类相对依赖会锚到 doctor 的 cwd 而不是
         // skill 目录, 误报缺文件。
         if (existsSync(join(absTarget, 'SKILL.md'))) {
-            return resolveArtifacts(dirname(absTarget), [basename(absTarget)], { strictBaseline: false });
+            return resolveArtifacts(dirname(absTarget), [basename(absTarget)], { strictBaseline: false, materialize: false });
         }
         const variants = discoverVariants(absTarget).filter((v) => v !== 'baseline');
-        return variants.length > 0 ? resolveArtifacts(absTarget, variants, { strictBaseline: false }) : [];
+        return variants.length > 0 ? resolveArtifacts(absTarget, variants, { strictBaseline: false, materialize: false }) : [];
     }
     throw new Error(`doctor target must be a .md file or directory: ${target}`);
 }
@@ -229,7 +229,7 @@ export async function runDoctor(opts) {
             ? 'warnings_only'
             : 'passed';
     return {
-        reportKind: 'doctor',
+        kind: 'doctor',
         schemaVersion: DOCTOR_REPORT_SCHEMA_VERSION,
         id: nextReportId(),
         timestamp: new Date().toISOString(),

package/dist/eval-core/cache.d.ts

@@ -2,8 +2,8 @@
  * Executor result cache.
  *
  * Caches successful executor results to disk to avoid redundant API calls.
- * Cache key v5 = sha256(model + system + prompt + cwd + allowedSkills + executor +
- *                       runtime + mocks + mocksStrict + effort).
+ * Cache key v6 = sha256(model + system + prompt + cwd + allowedSkills + executor +
+ *                       runtime + mocks + mocksStrict + effort + artifactContentHash).
  * Loaded into memory on init, flushed to disk on save().
  *
  * Prefix bumps intentionally invalidate old entries when construct-validity
@@ -15,6 +15,11 @@
  *       报告 meta 标的 effort 跟实际跑的 effort 不一致 — 测量可比性污染);
  *       同时 cache.set 不再砍 turns / toolCalls — 工具类断言 + diagnostic 要看 trace,
  *       砍掉的话 cached rerun 会让工具断言为空、diagnostic 没真实证据,跟 cold run 不一致
+ * - v6: artifact 内容指纹(contentHash)。`system` 只含 SKILL.md 正文,但本地 dir-skill 的
+ *       references/ 资产是真实运行时输入(cwd=skillRoot,agent 可读),改资产只动 contentHash、
+ *       不动 system → 旧 key 会命中旧输出、贴到新 artifactHashes 上,形成静默测量污染。把
+ *       contentHash 纳入 key,资产变即重跑。git skill 的 contentHash 只随 SKILL.md 变(其资产不
+ *       暴露给 executor、本就不该触发重跑),口径自洽
  */
 import type { ExecutorCache } from '../types/index.js';
 export declare function createCache(cacheDir: string): ExecutorCache;
@@ -27,4 +32,7 @@ mocksStrict?: boolean,
 /** Executor effort 也进 key:effort 'low'/'medium'/'high' 改变 LLM 思考预算,
  *  输出/工具调用/分数都可能不同,跨 effort 共享 cache 会让报告 meta 标的 effort
  *  跟实际生成的 effort 不一致,违反"两份报告比分数前先比 cliVersion / effort"语义。 */
-effort?: string): string;
+effort?: string, 
+/** artifact 内容指纹(整树 / 单文件哈)。本地 dir-skill 改 references/ 资产只动此值、不动 system,
+ *  不进 key 会让改资产后命中旧输出 → 静默污染。空(baseline / 无 skill)等价无指纹。 */
+artifactContentHash?: string): string;

package/dist/eval-core/cache.js

@@ -2,8 +2,8 @@
  * Executor result cache.
  *
  * Caches successful executor results to disk to avoid redundant API calls.
- * Cache key v5 = sha256(model + system + prompt + cwd + allowedSkills + executor +
- *                       runtime + mocks + mocksStrict + effort).
+ * Cache key v6 = sha256(model + system + prompt + cwd + allowedSkills + executor +
+ *                       runtime + mocks + mocksStrict + effort + artifactContentHash).
  * Loaded into memory on init, flushed to disk on save().
  *
  * Prefix bumps intentionally invalidate old entries when construct-validity
@@ -15,6 +15,11 @@
  *       报告 meta 标的 effort 跟实际跑的 effort 不一致 — 测量可比性污染);
  *       同时 cache.set 不再砍 turns / toolCalls — 工具类断言 + diagnostic 要看 trace,
  *       砍掉的话 cached rerun 会让工具断言为空、diagnostic 没真实证据,跟 cold run 不一致
+ * - v6: artifact 内容指纹(contentHash)。`system` 只含 SKILL.md 正文,但本地 dir-skill 的
+ *       references/ 资产是真实运行时输入(cwd=skillRoot,agent 可读),改资产只动 contentHash、
+ *       不动 system → 旧 key 会命中旧输出、贴到新 artifactHashes 上,形成静默测量污染。把
+ *       contentHash 纳入 key,资产变即重跑。git skill 的 contentHash 只随 SKILL.md 变(其资产不
+ *       暴露给 executor、本就不该触发重跑),口径自洽
  */
 import { readFileSync, writeFileSync, mkdirSync, existsSync } from 'node:fs';
 import { join } from 'node:path';
@@ -114,7 +119,10 @@ mocksStrict,
 /** Executor effort 也进 key:effort 'low'/'medium'/'high' 改变 LLM 思考预算,
  *  输出/工具调用/分数都可能不同,跨 effort 共享 cache 会让报告 meta 标的 effort
  *  跟实际生成的 effort 不一致,违反"两份报告比分数前先比 cliVersion / effort"语义。 */
-effort) {
+effort, 
+/** artifact 内容指纹(整树 / 单文件哈)。本地 dir-skill 改 references/ 资产只动此值、不动 system,
+ *  不进 key 会让改资产后命中旧输出 → 静默污染。空(baseline / 无 skill)等价无指纹。 */
+artifactContentHash) {
     // allowedSkills 序列化:undefined → "" / [] → "[]" / [...] → 排序后 JSON。
     // 排序保证 ["a","b"] 和 ["b","a"] 命中同一缓存(语义等价)。
     const isoStr = allowedSkills === undefined
@@ -130,8 +138,8 @@ effort) {
     // executor + runtime + effort 进 cache key:同 model 名走不同 executor 或同 executor
     // 换 binary/SDK 版本时输出可能不同,旧 cache 不可复用。
     const hash = createHash('sha256')
-        .update(`${model || ''}\n${system || ''}\n${prompt || ''}\n${cwd || ''}\n${isoStr}\n${executor || ''}\n${runtimeFingerprint || ''}\n${mockStr}\n${strictStr}\n${effortStr}`)
+        .update(`${model || ''}\n${system || ''}\n${prompt || ''}\n${cwd || ''}\n${isoStr}\n${executor || ''}\n${runtimeFingerprint || ''}\n${mockStr}\n${strictStr}\n${effortStr}\n${artifactContentHash || ''}`)
         .digest('hex')
         .slice(0, 16);
-    return `v5:${hash}`;
+    return `v6:${hash}`;
 }