@lumoai/cli 1.25.1 → 1.27.0

package/assets/skill/references/tasks.md

@@ -199,7 +199,7 @@ Top 3 recommended tasks (of 12 open):
 Next: lumo session attach LUM-42 && lumo task context LUM-42
 ```
 
-When to suggest: the user asks "what should I work on", "what's next", "推荐下一个任务", "pick my next task", or starts a session without a task in mind. After they choose, run `session attach` + `task context` for the picked task.
+When to suggest: the user asks "what should I work on", "what's next", "recommend my next task" (in any language), "pick my next task", or starts a session without a task in mind. After they choose, run `session attach` + `task context` for the picked task.
 
 ### `lumo task show <identifier>` — print one task's detail
 
@@ -227,7 +227,7 @@ The CLI does not support @-mention chip syntax. If the user wants to ping someon
 
 ### `lumo task deps list <LUM-N>` — show all dependency edges
 
-Prints the task's dependency edges grouped into three sections: **CONFIRMED**, **SUGGESTED(待确认)**, and **DISMISSED**. Each row includes a short 8-character edge id in square brackets, the direction (`blocked by` / `blocks`), the other task's identifier and title, the other task's current status, the source (`MANUAL` or `DETECTED`), and inline evidence for detected edges.
+Prints the task's dependency edges grouped into three sections: **CONFIRMED**, **SUGGESTED (pending confirmation)**, and **DISMISSED**. Each row includes a short 8-character edge id in square brackets, the direction (`blocked by` / `blocks`), the other task's identifier and title, the other task's current status, the source (`MANUAL` or `DETECTED`), and inline evidence for detected edges.
 
 ```bash
 lumo task deps list LUM-42
@@ -239,29 +239,29 @@ Example output:
 Dependencies for LUM-42 (3)
 
 CONFIRMED
-  [a1b2c3d4] blocked by LUM-9「Fix auth token expiry」 IN_PROGRESS · MANUAL
+  [a1b2c3d4] blocked by LUM-9 "Fix auth token expiry" IN_PROGRESS · MANUAL
 
-SUGGESTED(待确认)
-  [e5f6a7b8] blocks LUM-55「Migrate DB schema」 TODO · shared_files(4 个共享文件: src/db/schema.ts, src/db/migrate.ts, ...)
-      确认: lumo task deps confirm LUM-42 e5f6a7b8(方向反了加 --reverse;误报: dismiss)
-  [c9d0e1f2] blocked by LUM-38「Add OAuth scopes」 IN_REVIEW · task_mention(description)
-      确认: lumo task deps confirm LUM-42 c9d0e1f2(方向反了加 --reverse;误报: dismiss)
+SUGGESTED (pending confirmation)
+  [e5f6a7b8] blocks LUM-55 "Migrate DB schema" TODO · shared_files(4 shared files: src/db/schema.ts, src/db/migrate.ts, ...)
+      confirm: lumo task deps confirm LUM-42 e5f6a7b8 (add --reverse if direction is flipped; false positive: dismiss)
+  [c9d0e1f2] blocked by LUM-38 "Add OAuth scopes" IN_REVIEW · task_mention(description)
+      confirm: lumo task deps confirm LUM-42 c9d0e1f2 (add --reverse if direction is flipped; false positive: dismiss)
 
 DISMISSED
-  [b3c4d5e6] blocks LUM-12 · 已忽略
+  [b3c4d5e6] blocks LUM-12 · dismissed
 ```
 
-CONFIRMED and SUGGESTED rows show the other task's identifier, title, current status, and source/evidence. DISMISSED rows render as `[shortId] <direction> <identifier> · 已忽略` only — no title, status, or source.
+CONFIRMED and SUGGESTED rows show the other task's identifier, title, current status, and source/evidence. DISMISSED rows render as `[shortId] <direction> <identifier> · dismissed` only — no title, status, or source.
 
 When there are no edges at all the output is:
 
 ```
-Dependencies for LUM-42: 无依赖边。
+Dependencies for LUM-42: no dependency edges.
 ```
 
 **Evidence fields by detection signal:**
 
-- `shared_files` — `shared_files(N 个共享文件: path1, path2, …)` — number of shared write-touched files in the 14-day window, plus up to 5 sample paths.
+- `shared_files` — `shared_files(N shared files: path1, path2, …)` — number of shared write-touched files in the 14-day window, plus up to 5 sample paths.
 - `task_mention` — `task_mention(description)` or `task_mention(comment)` — the surface where the mention appeared.
 
 CONFIRMED rows also show `source`: `MANUAL` (user-declared via `deps add`) or `DETECTED` (auto-found then confirmed via `deps confirm`).
@@ -314,7 +314,7 @@ lumo task deps dismiss LUM-42 e5f6a7b8
 lumo task deps dismiss LUM-42 LUM-38
 ```
 
-Output: `Dismissed: [e5f6a7b8] LUM-38「Add OAuth scopes」(不再建议)`
+Output: `Dismissed: [e5f6a7b8] LUM-38 "Add OAuth scopes" (won't be suggested again)`
 
 Use `dismiss` for false positives. Use `rm` only when you want the pair to be eligible for re-detection in the future (the detection service can re-suggest pairs with no existing row).
 
@@ -352,6 +352,6 @@ Output: `Removed [a1b2c3d4] from LUM-42`
 
 - **After `session attach` output shows a blocker warning or candidate-count hint** → run `lumo task deps list <LUM-N>` to review the full edge list, then `confirm` or `dismiss` each SUGGESTED candidate.
 - **User says "X needs to wait for Y" or "LUM-42 is blocked by LUM-9"** → run `lumo task deps add LUM-42 --blocked-by LUM-9`.
-- **Agent sees a `## ⚠ 依赖告警` block (form A — live blockers) at session-start** → evaluate whether to wait for the blocker to merge before starting work; if the edge is stale or wrong, clean it with `deps rm` or `deps dismiss`.
-- **Agent sees only a standalone hint line `检测到 N 条候选依赖待确认…` (form B — no live blockers)** → no immediate blocker, but run `lumo task deps list <LUM-N>` to review and confirm/dismiss SUGGESTED candidates. See [sessions.md](sessions.md) for the full alert format.
+- **Agent sees a `## ⚠ Dependency alerts` block (form A — live blockers) at session-start** → evaluate whether to wait for the blocker to merge before starting work; if the edge is stale or wrong, clean it with `deps rm` or `deps dismiss`.
+- **Agent sees only a standalone hint line `Detected N candidate dependencies awaiting confirmation…` (form B — no live blockers)** → no immediate blocker, but run `lumo task deps list <LUM-N>` to review and confirm/dismiss SUGGESTED candidates. See [sessions.md](sessions.md) for the full alert format.
 - **User reports a false positive dependency suggestion** → `lumo task deps dismiss <LUM-N> <edge>` to permanently suppress it for this pair.

package/assets/skill/references/verify.md

@@ -1,11 +1,11 @@
-# lumo verify — machine verification loop（机器验收循环）
+# lumo verify — machine verification loop
 
 `lumo verify` is the machine half of the acceptance system (Acceptance v1,
 LUM-343). It executes every **MACHINE** criterion's checkpointer in the local
 repo, reports one structured PASS/FAIL verdict per criterion to the server,
 and prints what to do next. The judge lives server-side: round numbering, the
 3-round cap, escalation, and the IN_REVIEW transition all happen there
-(执行在客户端，裁判在服务端).
+(execution on the client, adjudication on the server).
 
 ## The claim-done rule
 
@@ -71,7 +71,7 @@ the failures — re-running without changes burns a round and (at round 3)
 pages a human. A FAIL round never changes task status; only an all-pass round
 moves it (to IN_REVIEW, never further).
 
-## lumo task status — the read half（自查入口）
+## lumo task status — the read half (self-check entry point)
 
 `lumo task status [task] [--json]` is the read-only counterpart of the loop
 (LUM-344): pure read, milliseconds, no LLM, never writes — running it costs

package/dist/cli/src/commands/doc-diff.js

@@ -0,0 +1,82 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.docDiff = docDiff;
+const config_1 = require("../lib/config");
+const api_1 = require("../lib/api");
+const resolve_doc_id_1 = require("../lib/resolve-doc-id");
+const sanitize_1 = require("../lib/sanitize");
+const doc_input_1 = require("../lib/doc-input");
+const path_guard_1 = require("../lib/path-guard");
+const unified_diff_1 = require("../lib/unified-diff");
+/**
+ * `lumo doc diff <doc> --file <local.md>` (LUM-408).
+ *
+ * Compares the server-side markdown source (Document.sourceMarkdown — the
+ * byte-identical last markdown upload) against a local file, so a
+ * remote/local split-brain is visible on demand instead of discovered from
+ * memory after a stale upload clobbers someone's edit.
+ *
+ * Exit codes: 0 = sources byte-identical, 1 = divergent (or error).
+ */
+async function docDiff(reference, opts) {
+    if (!reference) {
+        console.error('Error: missing <doc>. Usage: lumo doc diff <doc> --file <local.md>');
+        return 1;
+    }
+    if (!opts.file) {
+        console.error('Error: --file <local.md> is required for doc diff');
+        return 1;
+    }
+    const creds = (0, config_1.readCredentials)();
+    if (!creds) {
+        console.error('Error: not logged in. Run `lumo auth login` first.');
+        return 1;
+    }
+    const apiUrl = (0, api_1.resolveAuthedApiUrl)(creds.apiUrl);
+    // Same sandbox as doc create/update --file: project-local, non-sensitive.
+    const check = (0, path_guard_1.checkArtifactFilePath)(opts.file);
+    if (!check.ok) {
+        console.error(check.reason === 'unreadable'
+            ? `Error: ${(0, doc_input_1.unreadableFileMessage)(opts.file)}`
+            : `Error: refusing to read ${opts.file} — ${check.detail}. ` +
+                `--file must be a non-sensitive path inside the project directory.`);
+        return 1;
+    }
+    const localText = await (0, doc_input_1.readFileUtf8)(check.resolved);
+    const id = await (0, resolve_doc_id_1.lookupDocId)(apiUrl, creds.token, reference);
+    if (!id) {
+        console.error(`Error: Document not found: ${reference}`);
+        return 1;
+    }
+    const res = await fetch(`${(0, api_1.trimTrailingSlash)(apiUrl)}/api/documents/${id}`, {
+        headers: { Authorization: `Bearer ${creds.token}` },
+    });
+    if (!res.ok) {
+        const text = await res.text();
+        console.error(`Error: ${res.status} ${res.statusText}: ${(0, sanitize_1.sanitizeField)(text)}`);
+        return 1;
+    }
+    const data = (await res.json());
+    const d = data.document;
+    if (!d) {
+        console.error('Error: server returned an empty document response');
+        return 1;
+    }
+    if (typeof d.sourceMarkdown !== 'string') {
+        console.error(`Error: ${d.id} has no stored markdown source to diff against (last edit ` +
+            `was HTML-direct or predates markdown source storage). Upload a markdown ` +
+            `base once (\`lumo doc update ${d.id} --file <base.md>\`) and diff from then on.`);
+        return 1;
+    }
+    if (d.sourceMarkdown === localText) {
+        console.log(`Clean: remote markdown source of ${d.id} matches ${opts.file} (${Buffer.byteLength(localText, 'utf8')} bytes)`);
+        return;
+    }
+    const diff = (0, unified_diff_1.formatUnifiedDiff)(d.sourceMarkdown, localText, `remote/${d.id} (sourceMarkdown)`, `local/${opts.file}`);
+    // Byte-level divergence with identical line sequences (e.g. trailing
+    // newline only) still counts as divergent — say so explicitly.
+    console.log(diff !== ''
+        ? (0, sanitize_1.sanitizeField)(diff)
+        : `Divergent: byte-level difference only (e.g. trailing newline) between remote ${d.id} and ${opts.file}`);
+    return 1;
+}

package/dist/cli/src/commands/doc-show.js

@@ -27,9 +27,9 @@ function formatShowOutput(vm) {
     const header = lines.join('\n');
     return vm.bodyMarkdown ? `${header}\n\n${(0, sanitize_1.sanitizeField)(vm.bodyMarkdown)}` : header;
 }
-async function docShow(reference) {
+async function docShow(reference, opts = {}) {
     if (!reference) {
-        console.error('Error: missing <doc>. Usage: lumo doc show <doc>');
+        console.error('Error: missing <doc>. Usage: lumo doc show <doc> [--raw]');
         return 1;
     }
     const creds = (0, config_1.readCredentials)();
@@ -58,6 +58,23 @@ async function docShow(reference) {
         console.error('Error: server returned an empty document response');
         return 1;
     }
+    if (opts.raw) {
+        // Byte-identical markdown source of the last markdown upload (LUM-408).
+        // Written verbatim (no header, no sanitization, no added newline) so the
+        // output is a legal edit base: `doc show --raw > base.md` round-trips.
+        // No silent fallback to the lossy HTML→markdown reverse render — that
+        // fallback is exactly what flattened tables in LUM-349.
+        if (typeof d.sourceMarkdown !== 'string') {
+            console.error(`Error: ${d.id} has no stored markdown source (last edit was HTML-direct ` +
+                `or predates markdown source storage). --raw refuses to fall back to the ` +
+                `lossy HTML→markdown render. Rebuild a base instead: run \`lumo doc show ${d.id}\`, ` +
+                `reconstruct the markdown faithfully, then \`lumo doc update ${d.id} --file <rebuilt.md>\` ` +
+                `— from then on --raw works.`);
+            return 1;
+        }
+        process.stdout.write(d.sourceMarkdown);
+        return;
+    }
     // Server returns `contentMarkdown` derived from the HTML body (LUM-83+).
     // Fall back to parsing the raw content as legacy Tiptap JSON for docs
     // written before the storage shape changed.

package/dist/cli/src/commands/milestone-show.js

@@ -34,7 +34,7 @@ function sprintCoverageLines(coverage) {
         return `  ${num}  ${status}  ${name}   ${s.doneCount}/${s.taskCount} done`;
     });
     if (coverage.unsprinted > 0) {
-        const label = '未排期'.padEnd(numW + 2 + statusW + 2 + nameW);
+        const label = 'Unscheduled'.padEnd(numW + 2 + statusW + 2 + nameW);
         rows.push(`  ${label}   ${coverage.unsprinted} task${coverage.unsprinted === 1 ? '' : 's'}`);
     }
     return ['', 'Sprint coverage:', ...rows];

package/dist/cli/src/commands/next.js

@@ -97,7 +97,7 @@ function formatNextOutput(ranked, totalOpen) {
     lines.push('');
     lines.push(`Next: lumo session attach ${first.identifier} && lumo task context ${first.identifier}`);
     if (ranked.length > 1) {
-        lines.push('（也可换成列表里任意一个 LUM-N）');
+        lines.push('(or pick any other LUM-N from the list)');
     }
     return lines.join('\n');
 }

package/dist/cli/src/commands/session-attach.js

@@ -20,7 +20,7 @@ const line_prompt_1 = require("../lib/line-prompt");
  * longer silently clobbers `Session.taskId` (LUM-266): the server returns
  * the current binding and we confirm before overwriting —
  *   - `--force` skips the prompt and overwrites directly;
- *   - on a TTY we ask `已绑定 LUM-X，覆盖为 LUM-Y? [y/N]`;
+ *   - on a TTY we ask `Already bound to LUM-X. Rebind to LUM-Y? [y/N]`;
  *   - off a TTY (the usual agent case) we refuse and point at `--force`.
  */
 async function sessionAttach(identifier, options = {}) {
@@ -95,9 +95,9 @@ async function sessionAttach(identifier, options = {}) {
                 '(or run `lumo session detach` first).');
             return 0;
         }
-        const answer = await (0, line_prompt_1.promptLine)(`已绑定 ${body.currentTaskIdentifier}，覆盖为 ${identifier}? [y/N] `);
+        const answer = await (0, line_prompt_1.promptLine)(`Already bound to ${body.currentTaskIdentifier}. Rebind to ${identifier}? [y/N] `);
         if (!/^y(es)?$/i.test(answer)) {
-            console.log(`已取消，仍绑定 ${body.currentTaskIdentifier}。`);
+            console.log(`Cancelled — still bound to ${body.currentTaskIdentifier}.`);
             return 0;
         }
         const second = await bind(true);
@@ -112,7 +112,8 @@ async function sessionAttach(identifier, options = {}) {
     }
     console.log(`Attached session ${sessionId} to ${body.taskIdentifier} "${(0, sanitize_1.sanitizeField)(body.taskTitle)}"`);
     console.log(`Re-tagged ${body.retaggedEventCount} previously-untagged event${body.retaggedEventCount === 1 ? '' : 's'} in this session.`);
-    // 告警先于 contract/memory:与 hook 注入顺序一致,短且可操作的信息优先。
+    // Warnings come before contract/memory: matches the hook injection order —
+    // short, actionable information first.
     if (body.blockerWarningSection) {
         console.log('');
         console.log((0, sanitize_1.sanitizeField)(body.blockerWarningSection));

package/dist/cli/src/commands/task-criteria-set.js

@@ -99,7 +99,7 @@ async function taskCriteriaSet(identifier, options) {
         Authorization: `Bearer ${creds.token}`,
         'Content-Type': 'application/json',
     };
-    // Session 出处 for HUMAN_EDIT transcriptions — the server records the
+    // Session provenance for HUMAN_EDIT transcriptions — the server records the
     // revision (with this session id) as a task comment.
     const sessionId = process.env.CLAUDE_CODE_SESSION_ID;
     if (sessionId)

package/dist/cli/src/commands/task-deps.js

@@ -10,7 +10,7 @@ exports.taskDepsRm = taskDepsRm;
 const config_1 = require("../lib/config");
 const api_1 = require("../lib/api");
 const sanitize_1 = require("../lib/sanitize");
-/** 短 id = 前 8 位，展示与 selector 都用它。 */
+/** Short id = first 8 chars; used for both display and selectors. */
 const shortId = (id) => id.slice(0, 8);
 /**
  * Resolve a user-supplied edge selector against the task's edge list. Accepts
@@ -35,7 +35,7 @@ function resolveEdgeSelector(edges, selector) {
  */
 function formatDepsList(identifier, edges) {
     if (edges.length === 0)
-        return `Dependencies for ${identifier}: 无依赖边。`;
+        return `Dependencies for ${identifier}: no dependency edges.`;
     const lines = [
         `Dependencies for ${identifier} (${edges.length})`,
         '',
@@ -43,7 +43,7 @@ function formatDepsList(identifier, edges) {
     const dirLabel = (e) => e.direction === 'BLOCKED_BY' ? 'blocked by' : 'blocks';
     const evidence = (e) => {
         if (e.reason === 'shared_files')
-            return ` · shared_files(${e.detail?.count ?? '?'} 个共享文件${e.detail?.sample?.length ? ': ' + e.detail.sample.join(', ') : ''})`;
+            return ` · shared_files(${e.detail?.count ?? '?'} shared files${e.detail?.sample?.length ? ': ' + e.detail.sample.join(', ') : ''})`;
         if (e.reason === 'task_mention')
             return ` · task_mention(${e.detail?.surface ?? ''})`;
         return '';
@@ -60,14 +60,14 @@ function formatDepsList(identifier, edges) {
     const suggested = edges.filter(e => e.status === 'SUGGESTED');
     const dismissed = edges.filter(e => e.status === 'DISMISSED');
     section('CONFIRMED', confirmed, e => [
-        `  [${shortId(e.id)}] ${dirLabel(e)} ${e.other.identifier}「${e.other.title}」 ${e.other.status} · ${e.source}${evidence(e)}`,
+        `  [${shortId(e.id)}] ${dirLabel(e)} ${e.other.identifier} "${e.other.title}" ${e.other.status} · ${e.source}${evidence(e)}`,
     ]);
-    section('SUGGESTED(待确认)', suggested, e => [
-        `  [${shortId(e.id)}] ${dirLabel(e)} ${e.other.identifier}「${e.other.title}」 ${e.other.status}${evidence(e)}`,
-        `      确认: lumo task deps confirm ${identifier} ${shortId(e.id)}(方向反了加 --reverse;误报: dismiss)`,
+    section('SUGGESTED (pending confirmation)', suggested, e => [
+        `  [${shortId(e.id)}] ${dirLabel(e)} ${e.other.identifier} "${e.other.title}" ${e.other.status}${evidence(e)}`,
+        `      confirm: lumo task deps confirm ${identifier} ${shortId(e.id)} (add --reverse if direction is flipped; false positive: dismiss)`,
     ]);
     section('DISMISSED', dismissed, e => [
-        `  [${shortId(e.id)}] ${dirLabel(e)} ${e.other.identifier} · 已忽略`,
+        `  [${shortId(e.id)}] ${dirLabel(e)} ${e.other.identifier} · dismissed`,
     ]);
     return lines.join('\n').trimEnd();
 }
@@ -160,11 +160,11 @@ async function fetchDeps(ctx, taskDbId) {
 function printSelectorCandidates(edges, selector) {
     console.error(`Error: no unique dependency edge matches "${selector}". Candidates:`);
     if (edges.length === 0) {
-        console.error('  (无依赖边)');
+        console.error('  (no dependency edges)');
         return;
     }
     for (const e of edges) {
-        console.error((0, sanitize_1.sanitizeField)(`  [${shortId(e.id)}] ${e.status} ${e.other.identifier}「${e.other.title}」`));
+        console.error((0, sanitize_1.sanitizeField)(`  [${shortId(e.id)}] ${e.status} ${e.other.identifier} "${e.other.title}"`));
     }
 }
 /**
@@ -247,7 +247,7 @@ async function taskDepsConfirm(identifier, selector, opts) {
     }, 'dependency confirm');
     if (typeof res === 'number')
         return res;
-    console.log((0, sanitize_1.sanitizeField)(`Confirmed: [${shortId(edge.id)}] ${task.identifier} ${edge.direction === 'BLOCKED_BY' ? 'blocked by' : 'blocks'} ${edge.other.identifier}「${edge.other.title}」${opts.reverse ? ' (reversed)' : ''}`));
+    console.log((0, sanitize_1.sanitizeField)(`Confirmed: [${shortId(edge.id)}] ${task.identifier} ${edge.direction === 'BLOCKED_BY' ? 'blocked by' : 'blocks'} ${edge.other.identifier} "${edge.other.title}"${opts.reverse ? ' (reversed)' : ''}`));
 }
 /** `lumo task deps dismiss <LUM-N> <edge>` */
 async function taskDepsDismiss(identifier, selector) {
@@ -262,7 +262,7 @@ async function taskDepsDismiss(identifier, selector) {
     const res = await depsFetch(ctx, `/api/tasks/${encodeURIComponent(task.id)}/dependencies/${encodeURIComponent(edge.id)}`, { method: 'PATCH', body: JSON.stringify({ action: 'dismiss' }) }, 'dependency dismiss');
     if (typeof res === 'number')
         return res;
-    console.log((0, sanitize_1.sanitizeField)(`Dismissed: [${shortId(edge.id)}] ${edge.other.identifier}「${edge.other.title}」(不再建议)`));
+    console.log((0, sanitize_1.sanitizeField)(`Dismissed: [${shortId(edge.id)}] ${edge.other.identifier} "${edge.other.title}" (won't be suggested again)`));
 }
 /** `lumo task deps rm <LUM-N> <edge> --yes` */
 async function taskDepsRm(identifier, selector, opts) {

package/dist/cli/src/commands/verify.js

@@ -14,7 +14,7 @@ function tail(s, max) {
     return s.length > max ? `…${s.slice(-max)}` : s;
 }
 /**
- * Execute one MACHINE checkpointer in the local repo (执行在客户端 — the
+ * Execute one MACHINE checkpointer in the local repo (runs client-side — the
  * server can't run repo tests) and fold the result into a structured verdict.
  * Exit 0 = PASS with a `cmd:` evidence pointer; non-zero = CRITERION_UNMET;
  * spawn failure or timeout = CHECK_EXECUTION_ERROR.

package/dist/cli/src/commands/wrap/blocked-prompt-section.js

@@ -14,7 +14,7 @@ const failure_summary_api_1 = require("../../lib/failure-summary-api");
  */
 class BlockedPromptSection {
     deps;
-    title = '卡住检测';
+    title = 'Blocked check';
     draft = null;
     constructor(deps) {
         this.deps = deps;
@@ -28,14 +28,14 @@ class BlockedPromptSection {
         if (!draft || !draft.shouldPrompt || !draft.taskIdentifier)
             return;
         const top = draft.topFailure;
-        const where = top ? (0, sanitize_1.sanitizeField)(top.label) : '某个操作';
+        const where = top ? (0, sanitize_1.sanitizeField)(top.label) : 'an operation';
         const count = top ? top.count : 0;
-        process.stdout.write(`看起来本次会话反复卡在 ${where}(${count} 次失败)。\n`);
+        process.stdout.write(`This session looks repeatedly stuck on ${where} (${count} failures).\n`);
         if (top?.lastErrorSummary) {
-            process.stdout.write(`最后错误：${(0, sanitize_1.sanitizeField)(top.lastErrorSummary)}\n`);
+            process.stdout.write(`Last error: ${(0, sanitize_1.sanitizeField)(top.lastErrorSummary)}\n`);
         }
         if (opts.dryRun) {
-            process.stdout.write(`(dry-run，未改动；确认后会给 ${draft.taskIdentifier} 标 blocked)\n`);
+            process.stdout.write(`(dry-run, no changes; confirming would tag ${draft.taskIdentifier} blocked)\n`);
             return;
         }
         // Tagging the shared board is opt-in: it requires an explicit interactive
@@ -43,10 +43,10 @@ class BlockedPromptSection {
         // does NOT auto-tag — silently flipping shared board state is exactly what
         // LUM-153 set out to avoid. We surface the suggestion and move on.
         if (opts.yes) {
-            process.stdout.write(`(--yes 不自动标记；如确认请交互式回答 y，或手动 \`lumo task update ${draft.taskIdentifier} --add-tag blocked\`)\n`);
+            process.stdout.write(`(--yes does not auto-tag; answer y interactively, or run \`lumo task update ${draft.taskIdentifier} --add-tag blocked\` manually)\n`);
             return;
         }
-        const choice = (await (0, line_prompt_1.promptLine)(`要在 ${draft.taskIdentifier} 标 blocked 吗？[y] 标记  [s] 跳过 > `))
+        const choice = (await (0, line_prompt_1.promptLine)(`Tag ${draft.taskIdentifier} as blocked? [y] tag  [s] skip > `))
             .trim()
             .toLowerCase();
         if (choice === 'y') {
@@ -54,11 +54,11 @@ class BlockedPromptSection {
             return;
         }
         // Empty / 's' / anything else → do nothing. Tagging is opt-in.
-        process.stdout.write('已跳过，未标记。\n');
+        process.stdout.write('Skipped — not tagged.\n');
     }
     async mark() {
         const { taskIdentifier, tag } = await (0, failure_summary_api_1.markTaskBlocked)(this.deps.creds, this.deps.sessionId);
-        process.stdout.write(`已给 ${taskIdentifier} 标 ${tag}。\n`);
+        process.stdout.write(`Tagged ${taskIdentifier} with ${tag}.\n`);
     }
 }
 exports.BlockedPromptSection = BlockedPromptSection;

package/dist/cli/src/commands/wrap/fragment-usage-section.js

@@ -24,7 +24,7 @@ function parseUsedHandles(spec) {
  */
 class FragmentUsageSection {
     deps;
-    title = '上下文使用投票';
+    title = 'Fragment-usage vote';
     draft = null;
     constructor(deps) {
         this.deps = deps;
@@ -38,19 +38,19 @@ class FragmentUsageSection {
         if (!draft || draft.candidates.length === 0)
             return;
         if (draft.alreadyVoted) {
-            process.stdout.write('本 session 已投票,跳过。\n');
+            process.stdout.write('This session already voted — skipping.\n');
             return;
         }
-        process.stdout.write('本次会话注入的 context fragment:\n');
+        process.stdout.write('Context fragments injected in this session:\n');
         draft.candidates.forEach((c, i) => {
             process.stdout.write(`  [${i + 1}] ${(0, sanitize_1.sanitizeField)(c.label)}\n`);
         });
         if (opts.dryRun) {
-            process.stdout.write('(dry-run,未改动)\n');
+            process.stdout.write('(dry-run, no changes)\n');
             return;
         }
         if (this.deps.used === undefined) {
-            process.stdout.write('用 `lumo session wrap --used <序号>`(或 `--used none`)记录你实际用到的 fragment。\n');
+            process.stdout.write('Use `lumo session wrap --used <indices>` (or `--used none`) to record which fragments you actually used.\n');
             return;
         }
         const idx = parseUsedHandles(this.deps.used);
@@ -60,7 +60,7 @@ class FragmentUsageSection {
             fragmentId: draft.candidates[i].fragmentId,
         }));
         const { used, unused } = await (0, fragment_usage_api_1.applyFragmentUsage)(this.deps.creds, this.deps.sessionId, { usedRefs });
-        process.stdout.write(`已记录:用过 ${used} 个,未用 ${unused} 个。\n`);
+        process.stdout.write(`Recorded: ${used} used, ${unused} unused.\n`);
     }
 }
 exports.FragmentUsageSection = FragmentUsageSection;

package/dist/cli/src/commands/wrap/memory-review-section.js

@@ -32,7 +32,7 @@ function parseReviewInstruction(line) {
  */
 class MemoryReviewSection {
     deps;
-    title = '记忆审阅';
+    title = 'Memory review';
     draft = null;
     constructor(deps) {
         this.deps = deps;
@@ -45,19 +45,19 @@ class MemoryReviewSection {
         const draft = this.draft;
         if (!draft || !draft.watermark || draft.memories.length === 0)
             return;
-        process.stdout.write(`本次会话新增了这 ${draft.memories.length} 条 memory：\n`);
+        process.stdout.write(`This session recorded ${draft.memories.length} new memories:\n`);
         process.stdout.write(`${(0, sanitize_1.sanitizeField)((0, memory_content_1.formatMemoryReviewList)(draft.memories))}\n`);
         if (opts.dryRun) {
-            process.stdout.write('(dry-run，未改动)\n');
+            process.stdout.write('(dry-run, no changes)\n');
             return;
         }
         if (opts.yes) {
             await this.apply(draft.watermark, [], []);
             return;
         }
-        const line = (await (0, line_prompt_1.promptLine)('[回车] 全部保留  [d 1,3] 删除  [p 2] 提升到项目级  [s] 跳过 > ')).trim();
+        const line = (await (0, line_prompt_1.promptLine)('[Enter] keep all  [d 1,3] delete  [p 2] promote to project  [s] skip > ')).trim();
         if (line.toLowerCase() === 's') {
-            process.stdout.write('已跳过本节。\n');
+            process.stdout.write('Section skipped.\n');
             return;
         }
         if (line === '') {
@@ -75,7 +75,7 @@ class MemoryReviewSection {
     }
     async apply(watermark, deleteIds, promoteIds) {
         const { deleted, promoted } = await (0, session_memory_api_1.applyMemoryReview)(this.deps.creds, this.deps.sessionId, { watermark, deleteIds, promoteIds });
-        process.stdout.write(`已删除 ${deleted} 条，提升 ${promoted} 条到项目级。\n`);
+        process.stdout.write(`Deleted ${deleted}, promoted ${promoted} to project scope.\n`);
     }
 }
 exports.MemoryReviewSection = MemoryReviewSection;

package/dist/cli/src/commands/wrap/progress-comment-section.js

@@ -6,7 +6,7 @@ const sanitize_1 = require("../../lib/sanitize");
 const line_prompt_1 = require("../../lib/line-prompt");
 const editor_1 = require("../../lib/editor");
 const progress_comment_api_1 = require("../../lib/progress-comment-api");
-const HEADER = '本次会话进度';
+const HEADER = 'Session progress';
 /** Join turn summaries into a bulleted progress comment body under a header. */
 function formatProgressBody(summaries) {
     return [HEADER, ...summaries.map(s => `- ${s}`)].join('\n');
@@ -18,7 +18,7 @@ function formatProgressBody(summaries) {
  */
 class ProgressCommentSection {
     deps;
-    title = '进度评论';
+    title = 'Progress comment';
     draft = null;
     body = '';
     constructor(deps) {
@@ -37,31 +37,31 @@ class ProgressCommentSection {
         if (!draft || !draft.watermark)
             return;
         // Preview: sanitize the server free-text before it hits the terminal.
-        process.stdout.write(`将发到 ${draft.taskIdentifier} "${(0, sanitize_1.sanitizeField)(draft.taskTitle ?? '')}":\n`);
+        process.stdout.write(`Will post to ${draft.taskIdentifier} "${(0, sanitize_1.sanitizeField)(draft.taskTitle ?? '')}":\n`);
         process.stdout.write(`${(0, sanitize_1.sanitizeField)(this.body)}\n`);
         if (opts.dryRun) {
-            process.stdout.write('(dry-run，未发送)\n');
+            process.stdout.write('(dry-run, not posted)\n');
             return;
         }
         if (opts.yes) {
             await this.post(draft.watermark, this.body);
             return;
         }
-        const choice = (await (0, line_prompt_1.promptLine)('[y] 发送  [e] 编辑  [s] 跳过 > ')).toLowerCase();
+        const choice = (await (0, line_prompt_1.promptLine)('[y] post  [e] edit  [s] skip > ')).toLowerCase();
         if (choice === 's' || choice === '') {
-            process.stdout.write('已跳过。\n');
+            process.stdout.write('Skipped.\n');
             return;
         }
         if (choice === 'e') {
             const edited = (await (0, editor_1.editInEditor)(this.body)).trim();
             if (edited.length === 0) {
-                process.stdout.write('正文为空，已跳过。\n');
+                process.stdout.write('Empty body — skipped.\n');
                 return;
             }
             process.stdout.write(`${(0, sanitize_1.sanitizeField)(edited)}\n`);
-            const confirm = (await (0, line_prompt_1.promptLine)('[y] 发送  [s] 跳过 > ')).toLowerCase();
+            const confirm = (await (0, line_prompt_1.promptLine)('[y] post  [s] skip > ')).toLowerCase();
             if (confirm !== 'y') {
-                process.stdout.write('已跳过。\n');
+                process.stdout.write('Skipped.\n');
                 return;
             }
             await this.post(draft.watermark, edited);
@@ -71,11 +71,11 @@ class ProgressCommentSection {
             await this.post(draft.watermark, this.body);
             return;
         }
-        process.stdout.write('无法识别的选择，已跳过。\n');
+        process.stdout.write('Unrecognized choice — skipped.\n');
     }
     async post(watermark, body) {
         const { commentId } = await (0, progress_comment_api_1.postProgressComment)(this.deps.creds, this.deps.sessionId, { body, watermark });
-        process.stdout.write(`已发送进度评论 (comment ${commentId})\n`);
+        process.stdout.write(`Posted progress comment (comment ${commentId})\n`);
     }
 }
 exports.ProgressCommentSection = ProgressCommentSection;

package/dist/cli/src/index.js

@@ -107,6 +107,7 @@ const doc_import_gdoc_1 = require("./commands/doc-import-gdoc");
 const doc_sync_1 = require("./commands/doc-sync");
 const doc_update_1 = require("./commands/doc-update");
 const doc_show_1 = require("./commands/doc-show");
+const doc_diff_1 = require("./commands/doc-diff");
 const doc_list_1 = require("./commands/doc-list");
 const doc_delete_1 = require("./commands/doc-delete");
 const doc_bind_1 = require("./commands/doc-bind");
@@ -396,7 +397,7 @@ taskCriteria
     .command('set <task>')
     .description('Submit the whole acceptance contract from a JSON file. Default = initial agent draft (locked once submitted); --human records a HUMAN_EDIT revision (desired final list; items with "id" keep/update, missing ones are deleted).')
     .requiredOption('--file <path>', 'JSON array of criteria: [{"statement","verifierType":"MACHINE"|"HUMAN","checkpointer?","evidenceRequired?","id?"}]')
-    .option('--human', 'Record a human contract revision (HUMAN_EDIT) transcribed from the conversation, with session 出处')
+    .option('--human', 'Record a human contract revision (HUMAN_EDIT) transcribed from the conversation, with session provenance')
     .option('--cause <tag>', 'Why the contract drifted (with --human): NEW_INFO | SCOPE_CHANGE | DRAFT_BLIND_SPOT | GRANULARITY | OTHER')
     .action(wrap((taskId, options) => (0, task_criteria_set_1.taskCriteriaSet)(taskId, options)));
 taskCriteria
@@ -665,8 +666,14 @@ doc
     .action(wrap((reference, opts) => (0, doc_update_1.docUpdate)(reference, opts)));
 doc
     .command('show <doc>')
-    .description('Show document header and body (doc = title or cuid)')
-    .action(wrap(reference => (0, doc_show_1.docShow)(reference)));
+    .description('Show document header and body (doc = title or cuid). --raw prints the byte-identical markdown source of the last markdown upload (a legal edit base); it errors when no markdown source is stored instead of falling back to the lossy HTML→markdown render.')
+    .option('--raw', 'Print the stored markdown source verbatim (no header); errors if absent')
+    .action(wrap((reference, opts) => (0, doc_show_1.docShow)(reference, opts)));
+doc
+    .command('diff <doc>')
+    .description('Compare the server-side markdown source against a local file. Exit 0 when byte-identical, 1 with a unified diff when divergent. Requires the doc to have a stored markdown source.')
+    .requiredOption('--file <path>', 'Local markdown file to compare against')
+    .action(wrap((reference, opts) => (0, doc_diff_1.docDiff)(reference, opts)));
 doc
     .command('list')
     .description('List documents visible to the current user')