mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-27 06:11:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11

feat(i18n): localize all gateway commands + web dashboard, add 8 new locales (16 total) (#22914)

Browse source 
* feat(i18n): localize /model command output

Reported by @tianma8888: when Chinese users run /model, the labels
("Provider:", "Context:", "_session only_", etc.) are still English.
This routes the static prose through the existing i18n catalog so it
follows display.language / HERMES_LANGUAGE.

Changes:
- locales/{en,zh,ja,de,es,fr,tr,uk}.yaml: add 17 keys under
  gateway.model.* covering switched/provider/context/max_output/cost/
  capabilities/prompt_caching/warning/saved_global/session_only_hint/
  current_label/current_tag/more_models_suffix/usage_*.
- gateway/run.py _handle_model_command: replace hardcoded f-strings in
  the picker callback, the text-list fallback, and the direct-switch
  confirmation block with t("gateway.model.<key>", ...).

What stays English:
- model IDs, provider slugs, capability strings, cost figures, and the
  "[Note: model was just switched...]" prepended to the model's next
  prompt (LLM-facing, not user-facing).
- The two slightly-different session-only hints unify on a single key
  with the em-dash phrasing.

Validation: tests/agent/test_i18n.py 27/27 passing (parity contract
holds), tests/gateway/ -k 'model or i18n' 74/74 passing.

* feat(i18n): localize all gateway slash command outputs

Expands the i18n catalog from 7 strings to 234 keys across 35 gateway
slash command handlers, so non-English users see localized output for
\`/profile\`, \`/status\`, \`/help\`, \`/personality\`, \`/voice\`, \`/reset\`,
\`/agents\`, \`/restart\`, \`/commands\`, \`/goal\`, \`/retry\`, \`/undo\`,
\`/sethome\`, \`/title\`, \`/yolo\`, \`/background\`, \`/approve\`, \`/deny\`,
\`/insights\`, \`/debug\`, \`/rollback\`, \`/reasoning\`, \`/fast\`,
\`/verbose\`, \`/footer\`, \`/compress\`, \`/topic\`, \`/kanban\`,
\`/resume\`, \`/branch\`, \`/usage\`, \`/reload-mcp\`, \`/reload-skills\`,
\`/update\`, \`/stop\` (plus the \`/model\` block already added in the
previous commit).

Reported by @tianma8888 — Chinese users want command output prose in
their language, not just the labels we already had.

Translations are hand-written for all 8 supported locales (en, zh, ja,
de, es, fr, tr, uk), matching each catalog's existing style: full-width
punctuation in zh, em-dashes in zh/ja/uk, French spaced colons,
German noun capitalization, etc.

What stays English (unchanged):
- Identifiers/values: model IDs, file paths, profile names, session IDs,
  command flag names like --global, URLs, config keys.
- Backtick code spans: \`/foo\`, \`config.yaml\`.
- Log messages (logger.info/warning/error).
- LLM-facing system notes prepended to next prompt (e.g. [Note: model
  was just switched...]).
- Strings produced by external modules (gateway_help_lines,
  format_gateway, manual_compression_feedback) — those have their
  own surfaces.

New shared keys for cross-handler boilerplate:
- gateway.shared.session_db_unavailable (5 call sites: branch, title,
  resume, topic, _disable_telegram_topic_mode_for_chat)
- gateway.shared.session_not_found (1 site)
- gateway.shared.warn_passthrough (2 sites in /title's f"⚠️ {e}" pattern)

YAML gotcha fixed: \`yolo.on\` and \`yolo.off\` were originally written
unquoted, which YAML 1.1 parses as boolean True/False keys. Renamed to
\`yolo.enabled\` / \`yolo.disabled\` for both safety and clarity.

Test fix: tests/agent/test_i18n.py::test_t_missing_key_in_non_english_falls_back_to_english
now resets the catalog cache on teardown, so the fake "foo: English Foo"
locale doesn't poison the module-level cache for subsequent tests in
the same xdist worker. (Without this, every gateway slash command test
that shares a worker with the i18n suite would see the fake catalog.)

Validation:
- tests/agent/test_i18n.py: 27/27 (parity contract — every key in every
  locale, matching placeholder tokens).
- tests/gateway/: 5077 passed, 0 failed (full gateway suite).
- 180 t() call sites added across 35 handlers; 1872 catalog entries
  total (234 keys × 8 locales).

* feat(i18n): add 8 new locales — af, ko, it, ga, zh-hant, pt, ru, hu

Expands the static-message catalog from 8 → 16 languages, each with full
270-key parity against the English source-of-truth.  Every locale now
covers the same surface PR #22914 added: approval prompts plus all 35
gateway slash command outputs.

New locales:
- af  Afrikaans      (community ask in #21961 by @GodsBoy; PRs #21962, #21970)
- ko  Korean         (PRs #20297 by @tmdgusya, #22285 by @project820)
- it  Italian        (PR #20371 by @leprincep35700)
- ga  Irish/Gaeilge  (PR #20962 by @ryanmcc09-dot)
- zh-hant Traditional Chinese (PRs #20523 by @jackey8616, #13140 by @anomixer)
- pt  Portuguese     (PRs #20443 by @pedroborges, #15737 by @carloshenriquecarniatto, #22063 by @Magaav)
- ru  Russian        (PR #22770 by @DrMaks22)
- hu  Hungarian      (PR #22336 by @lunasec007)

Each locale uses native-quality translations matching the existing tone
and conventions of the older 8 locales:
- zh-hant uses 繁體 characters with TW/HK technical vocabulary (軟體
  not 软件, 連線 not 连接, 設定 not 设置, 訊息 not 消息, 工作階段 not 会话, 程式
  not 程序, 預設 not 默认, 伺服器 not 服务器), full-width punctuation 「：（）」.
- ko uses formal 합니다체 (습니다/합니다) register throughout.
- pt uses European Portuguese as baseline with neutral PT/BR vocabulary
  where possible.
- ga uses standard An Caighdeán Oifigiúil; English loanwords retained
  for tech terms without good Irish equivalents (gateway, API, JSON).
- All preserve {placeholder} tokens, backtick code spans, slash commands,
  brand names (Hermes, MCP, TTS, YOLO, OpenAI, Telegram, etc.), and emoji.

Aliases added in agent/i18n.py:
- af-za, Afrikaans → af
- ko-kr, Korean, 한국어 → ko
- it-it, italiano → it
- ga-ie, Irish, Gaeilge → ga
- zh-tw, zh-hk, zh-mo, traditional-chinese → zh-hant (note: zh-tw used to
  alias to zh; now aliases to its own zh-hant catalog)
- zh-cn, zh-hans, zh-sg → zh (unchanged from before)
- pt-pt, pt-br, brazilian, portuguese → pt
- ru-ru, Russian, русский → ru
- hu-hu, Magyar → hu

The zh-tw alias re-routing is intentional: previously typing 'zh-TW' got
the Simplified Chinese catalog (wrong vocabulary for Taiwan/HK users).
Now those users get the proper Traditional Chinese catalog.

Validation:
- tests/agent/test_i18n.py: 43/43 (parity contract holds for all 16
  languages × 270 keys = 4320 catalog entries, with matching placeholder
  tokens).
- E2E alias resolution verified for all 19 alias inputs (Afrikaans, ko-KR,
  한국어, italiano, Gaeilge, zh-TW, zh-HK, traditional-chinese, pt-BR,
  brazilian, Magyar, etc.).
- tests/gateway/: 5198 passed (3 pre-existing TTS routing failures
  unrelated to i18n).

Credit to all contributors whose PRs surfaced these language requests.
Their original PRs may now be closed as superseded with credit.

* feat(dashboard-i18n): add 14 web dashboard locales matching the static catalog

Brings the React dashboard (web/src/) up to the same 16-language
coverage the static catalog already has after the previous commits in
this PR. The Translations interface is TypeScript-typed, so every new
locale must provide every key — tsc -b is the parity guard.

Languages added (each is a complete 429-line locale file):
- af  Afrikaans
- ja  Japanese        (PR #22513 by @snuffxxx surfaced this)
- de  German          (PR #21749 by @mag1art)
- es  Spanish         (PR #21749)
- fr  French          (PRs #21749, #10310 by @foXaCe)
- tr  Turkish
- uk  Ukrainian
- ko  Korean          (PRs #21749, #18894 by @ovstng, #22285 by @project820)
- it  Italian
- ga  Irish (Gaeilge)
- zh-hant Traditional Chinese (PR #13140 by @anomixer)
- pt  Portuguese      (PRs #22063 by @Magaav, #22182 by @wesleysimplicio, #15737 by @carloshenriquecarniatto)
- ru  Russian         (PRs #21749, #22770 by @DrMaks22)
- hu  Hungarian       (PR #22336 by @lunasec007)

Each translation covers all 15 namespaces with full key parity vs en.ts,
preserves every {placeholder} token verbatim, keeps identifiers
untranslated (brand names, file paths, cron expressions, code spans),
translates the language.switchTo tooltip into the target language, and
matches existing tone conventions (zh-hant uses TW/HK vocab; ja uses
formal desu/masu; ko uses formal seumnida register; ga uses An
Caighdean Oifigiuil with English loanwords for tech vocab without good
Irish equivalents).

Plumbing:
- web/src/i18n/types.ts: Locale union expanded to all 16 codes.
- web/src/i18n/context.tsx: imports all 16 catalogs; exports
  LOCALE_META (endonym + flag per locale); isLocale() type guard.
- web/src/i18n/index.ts: re-export LOCALE_META.
- web/src/components/LanguageSwitcher.tsx: replaced two-state EN-ZH
  toggle with a click-to-open dropdown listing all 16 languages.

Note: zh-hant.ts exports zhHant (camelCase) since hyphen is invalid in
a JS identifier; the canonical 'zh-hant' string keys it in TRANSLATIONS.

Validation:
- npx tsc -b: 0 errors. Every locale satisfies Translations.
- npm run build (tsc + vite production): green, 2062 modules.
- Each locale file is exactly 429 lines.

Out of scope: plugin dashboards (kanban/achievements ship as prebuilt
bundles with no source in repo); Docusaurus docs (separate surface);
TUI (no i18n yet).

* feat(plugin-i18n): localize achievements + kanban plugin dashboards across all 16 locales

Brings the two shipped plugin dashboards (hermes-achievements, kanban)
under the same i18n umbrella as the core dashboard PR #22914 just
established.  Both bundles now read user-facing strings from the host's
i18n catalog via SDK.useI18n() instead of hardcoded English.

## Approach

Plugin dashboards ship as prebuilt IIFE bundles in
plugins/<name>/dashboard/dist/index.js — no build step, no source in
repo (upstream-authored, vendored as compiled JS).  Earlier contributor
PRs (#22594, #22595, #18747) tried direct edits but didn't actually
wire the bundles to read translations.

This change does the wiring properly:

1.  Each bundle gets a useI18n shim at IIFE scope:
        const useI18n = SDK.useI18n
          || function () { return { t: { kanban: null }, locale: "en" }; };
    Older host SDKs without useI18n still load the bundle and render
    English fallbacks.

2.  A small tx(t, path, fallback, vars) helper resolves dotted keys
    under the plugin's namespace (t.kanban.* or t.achievements.*) and
    interpolates {placeholder} tokens.

3.  Every React component starts with const { t } = useI18n() and
    each user-visible string is wrapped in tx(t, "key", "English fallback").
    Helpers called outside React components (window.prompt callers,
    constants used during init) take t as a parameter.

4.  Top-level constants that were English dictionaries (COLUMN_LABEL,
    COLUMN_HELP, DESTRUCTIVE_TRANSITIONS, DIAGNOSTIC_EVENT_LABELS in
    kanban) become getColumnLabel(t, status)-style functions backed by
    FALLBACK_* dictionaries.

## Translations added

Two new top-level namespaces added to the dashboard's TypeScript-typed
Translations interface:

- achievements: ~70 keys covering the hero, scan banner, achievement
  card, share dialog, stats, filters, and empty states.
- kanban: ~145 keys covering the board, columns (with nested
  columnLabels and columnHelp sub-dicts), card detail panel,
  bulk-actions toolbar, dependency editor, board switcher, and
  diagnostic callouts.

Each key is provided across all 16 supported locales:
en, zh, zh-hant, ja, de, es, fr, tr, uk, af, ko, it, ga, pt, ru, hu.

Total new translation entries: ~3,440 (215 keys × 16 locales).

## What stays English (deliberate)

- API paths, CSS class names, data-* attributes, JSON keys, regex
  strings, URLs, file paths (~/.hermes/kanban.db, boards/_archived/).
- State identifier strings used as lookup keys (triage / todo / ready /
  running / blocked / done / archived) — labels translate, key strings
  don't.
- The PNG share-card text rendered to canvas in the achievements
  ShareDialog (HERMES AGENT watermark, UNLOCKED stamp, tier names) —
  these become part of a globally-shared image and stay English.
- localStorage keys (hermes.kanban.selectedBoard).
- Brand names (Kanban, Hermes, WebSocket, Nous Research).

## Contributor credit

PR #22594 by @02356abc and PR #22595 by @02356abc supplied the
en + zh kanban namespace skeleton (145 keys); used as the en source-
of-truth in this commit and translated to the other 14 locales.

PR #18747 by @laolaoshiren first surfaced the achievements
localization request.

## Validation

- npx tsc -b: 0 errors. All 16 locale .ts files satisfy the
  Translations type with full key parity.
- npm run build (tsc + vite production build): green, 2062 modules,
  1.56MB JS / 95KB CSS, ~2.5s build.
- node --check on both plugin bundles: parse cleanly.
- 126 tx() call sites in kanban, 46 in achievements.

## Out of scope

- TUI (ui-tui/) has no i18n infrastructure yet.
- Docusaurus docs (website/i18n/) — already had zh-Hans; expanding
  is a separate translation workstream (Thai / Korean / Hindi PRs).
This commit is contained in:
Teknium 2026-05-10 07:14:14 -07:00 • committed by GitHub
parent 62b1c74cbc
commit c39168453d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
41 changed files with 16907 additions and 690 deletions
Download patch file Download diff file Expand all files Collapse all files

350
locales/zh-hant.yaml Normal file
View file

@ -0,0 +1,350 @@
# Hermes 靜態訊息目錄 -- 繁體中文（台灣／香港）
# See locales/en.yaml for the source of truth; keep keys in sync.
approval:
dangerous_header: "⚠️ 危險指令： {description}"
choose_long: " [o]僅此一次 | [s]本次工作階段 | [a]永久允許 | [d]拒絕"
choose_short: " [o]僅此一次 | [s]本次工作階段 | [d]拒絕"
prompt_long: " 選擇 [o/s/a/D]: "
prompt_short: " 選擇 [o/s/D]: "
timeout: " ⏱ 逾時 — 已拒絕指令"
allowed_once: " ✓ 本次允許"
allowed_session: " ✓ 本次工作階段內允許"
allowed_always: " ✓ 已加入永久允許清單"
denied: " ✗ 已拒絕"
cancelled: " ✗ 已取消"
blocklist_message: "此指令位於無條件封鎖清單中，無法被批准。"
gateway:
approval_expired: "⚠️ 批准已逾期（代理不再等待）。請讓代理重試。"
draining: "⏳ 正在等待 {count} 個活躍代理結束後重新啟動..."
goal_cleared: "✓ 目標已清除。"
no_active_goal: "目前沒有作用中的目標。"
config_read_failed: "⚠️ 無法讀取 config.yaml：{error}"
config_save_failed: "⚠️ 無法儲存設定：{error}"
model:
error_prefix: "錯誤：{error}"
switched: "已切換模型為 `{model}`"
provider_label: "提供方：{provider}"
context_label: "上下文：{tokens} tokens"
max_output_label: "最大輸出：{tokens} tokens"
cost_label: "費用：{cost}"
capabilities_label: "能力：{capabilities}"
prompt_caching_enabled: "提示快取：已啟用"
warning_prefix: "警告：{warning}"
saved_global: "已儲存到 config.yaml（`--global`）"
session_only_hint: "_（僅本次工作階段有效 — 加上 `--global` 可永久儲存）_"
current_label: "目前：`{model}`（{provider}）"
current_tag: "（目前）"
more_models_suffix: "（還有 {count} 個）"
usage_switch_model: "`/model <name>` — 切換模型"
usage_switch_provider: "`/model <name> --provider <slug>` — 切換提供方"
usage_persist: "`/model <name> --global` — 永久儲存"
agents:
header: "🤖 **作用中的代理與任務**"
active_agents: "**作用中代理：** {count}"
this_chat: " · 目前聊天"
more: "... 還有 {count} 個"
running_processes: "**執行中的背景程序：** {count}"
async_jobs: "**閘道非同步任務：** {count}"
none: "沒有作用中的代理或執行中的任務。"
state_starting: "啟動中"
state_running: "執行中"
approve:
no_pending: "沒有待批准的指令。"
once_singular: "✅ 指令已批准。代理正在恢復…"
once_plural: "✅ 指令已批准（{count} 條指令）。代理正在恢復…"
session_singular: "✅ 指令已批准（本次工作階段內允許該模式）。代理正在恢復…"
session_plural: "✅ 指令已批准（本次工作階段內允許該模式）（{count} 條指令）。代理正在恢復…"
always_singular: "✅ 指令已批准（永久允許該模式）。代理正在恢復…"
always_plural: "✅ 指令已批准（永久允許該模式）（{count} 條指令）。代理正在恢復…"
background:
usage: "用法：/background <提示>\n範例：/background 摘要今天 HN 上的熱門故事\n\n在獨立工作階段中執行該提示。你可以繼續聊天 — 完成後結果將顯示於此。"
started: "🔄 背景任務已啟動：「{preview}」\n任務 ID：{task_id}\n你可以繼續聊天 — 完成後結果將顯示於此。"
branch:
db_unavailable: "工作階段資料庫無法使用。"
no_conversation: "沒有可分支的對話 — 請先傳送一則訊息。"
create_failed: "建立分支失敗：{error}"
switch_failed: "分支已建立，但無法切換到該分支。"
branched_one: "⑂ 已分支至 **{title}**（已複製 {count} 則訊息）\n原始：`{parent}`\n分支：`{new}`\n使用 `/resume` 切換回原始工作階段。"
branched_many: "⑂ 已分支至 **{title}**（已複製 {count} 則訊息）\n原始：`{parent}`\n分支：`{new}`\n使用 `/resume` 切換回原始工作階段。"
commands:
usage: "用法：`/commands [page]`"
skill_header: "⚡ **技能指令**："
default_desc: "技能指令"
none: "沒有可用的指令。"
header: "📚 **指令**（共 {total} 個，第 {page}/{total_pages} 頁）"
nav_prev: "`/commands {page}` ← 上一頁"
nav_next: "下一頁 → `/commands {page}`"
out_of_range: "_（請求的第 {requested} 頁超出範圍，顯示第 {page} 頁。）_"
compress:
not_enough: "對話內容不足，無法壓縮（至少需要 4 則訊息）。"
no_provider: "未設定提供方 — 無法壓縮。"
nothing_to_do: "目前沒有可壓縮的內容（對話記錄仍全部為受保護的上下文）。"
focus_line: "聚焦：\"{topic}\""
summary_failed: "⚠️ 摘要產生失敗（{error}）。{count} 則歷史訊息已被移除並以佔位符取代；先前的上下文已無法復原。建議檢查 auxiliary.compression 模型設定。"
aux_failed: "ℹ️ 設定的壓縮模型 `{model}` 失敗（{error}）。已使用主要模型復原 — 上下文完整 — 但您可能想檢查 config.yaml 中的 `auxiliary.compression.model`。"
failed: "壓縮失敗：{error}"
debug:
upload_failed: "✗ 無法上傳除錯報告：{error}"
header: "**除錯報告已上傳：**"
auto_delete: "⏱ 貼上的內容將於 6 小時後自動刪除。"
full_logs_hint: "如需上傳完整紀錄，請在 CLI 中使用 `hermes debug share`。"
share_hint: "請將這些連結分享給 Hermes 團隊以取得支援。"
deny:
stale: "❌ 指令已拒絕（批准已過期）。"
no_pending: "沒有待拒絕的指令。"
denied_singular: "❌ 指令已拒絕。"
denied_plural: "❌ 指令已拒絕（{count} 條指令）。"
fast:
not_supported: "⚡ /fast 僅適用於支援 Priority Processing 的 OpenAI 模型。"
status: "⚡ Priority Processing\n\n目前模式：`{mode}`\n\n_用法：_ `/fast <normal|fast|status>`"
unknown_arg: "⚠️ 未知參數：`{arg}`\n\n**有效選項：** normal、fast、status"
saved: "⚡ ✓ Priority Processing：**{label}**（已儲存到設定）\n_（下一則訊息生效）_"
session_only: "⚡ ✓ Priority Processing：**{label}**（僅本次工作階段）"
label_fast: "FAST"
label_normal: "NORMAL"
status_fast: "fast"
status_normal: "normal"
footer:
status: "📎 執行階段頁尾：**{state}**\n欄位：`{fields}`\n平台：`{platform}`"
usage: "用法：`/footer [on|off|status]`"
saved: "📎 執行階段頁尾：**{state}**{example}\n_（已全域儲存 — 下一則訊息生效）_"
example_line: "\n範例：`{preview}`"
state_on: "ON"
state_off: "OFF"
goal:
unavailable: "此工作階段不支援目標功能。"
no_goal_set: "未設定目標。"
paused: "⏸ 目標已暫停：{goal}"
no_resume: "沒有可恢復的目標。"
resumed: "▶ 目標已恢復：{goal}\n傳送任意訊息繼續，或等待 — 我會在下一輪繼續推進。"
invalid: "無效目標：{error}"
set: "⊙ 目標已設定（{budget} 輪預算）：{goal}\n我會持續工作直到目標完成、你暫停／清除目標，或預算耗盡。\n控制指令：/goal status · /goal pause · /goal resume · /goal clear"
help:
header: "📖 **Hermes 指令**\n"
skill_header: "\n⚡ **技能指令**（{count} 個作用中）："
more_use_commands: "\n... 還有 {count} 個。使用 `/commands` 檢視完整分頁清單。"
insights:
invalid_days: "無效的 --days 值：{value}"
error: "產生洞察時發生錯誤：{error}"
kanban:
error_prefix: "⚠ kanban 錯誤：{error}"
subscribed_suffix: "（已訂閱 — 當 {task_id} 完成或被封鎖時將通知您）"
truncated_suffix: "…（已截斷；如需完整輸出請在終端機執行 `hermes kanban …`）"
no_output: "（無輸出）"
personality:
none_configured: "`{path}/config.yaml` 中未設定人格"
header: "🎭 **可用人格**\n"
none_option: "• `none` —（不套用人格覆寫）"
item: "• `{name}` — {preview}"
usage: "\n用法：`/personality <name>`"
save_failed: "⚠️ 儲存人格變更失敗：{error}"
cleared: "🎭 已清除人格 — 使用基礎代理行為。\n_（下一則訊息生效）_"
set_to: "🎭 人格已設定為 **{name}**\n_（下一則訊息生效）_"
unknown: "未知人格：`{name}`\n\n可用：{available}"
profile:
header: "👤 **設定檔：** `{profile}`"
home: "📂 **主目錄：** `{home}`"
reasoning:
level_default: "medium（預設）"
level_disabled: "none（已停用）"
scope_session: "工作階段覆寫"
scope_global: "全域設定"
status: "🧠 **推理設定**\n\n**強度：** `{level}`\n**範圍：** {scope}\n**顯示：** {display}\n\n_用法：_ `/reasoning <none|minimal|low|medium|high|xhigh|reset|show|hide> [--global]`"
display_on: "開啟 ✓"
display_off: "關閉"
display_set_on: "🧠 ✓ 推理顯示：**開啟**\n在 **{platform}** 上每次回應前將顯示模型的思考過程。"
display_set_off: "🧠 ✓ **{platform}** 上的推理顯示：**關閉**"
reset_global_unsupported: "⚠️ 不支援 `/reasoning reset --global`。請使用 `/reasoning <level> --global` 變更全域預設值。"
reset_done: "🧠 ✓ 已清除本工作階段的推理覆寫；回退至全域設定。"
unknown_arg: "⚠️ 未知參數：`{arg}`\n\n**有效級別：** none, minimal, low, medium, high, xhigh\n**顯示：** show, hide\n**持久化：** 加上 `--global` 可跨工作階段儲存"
set_global: "🧠 ✓ 推理強度已設定為 `{effort}`（已儲存到設定）\n_（下一則訊息生效）_"
set_global_save_failed: "🧠 ✓ 推理強度已設定為 `{effort}`（僅本工作階段 — 設定儲存失敗）\n_（下一則訊息生效）_"
set_session: "🧠 ✓ 推理強度已設定為 `{effort}`（僅本工作階段 — 加上 `--global` 可持久化）\n_（下一則訊息生效）_"
reload_mcp:
cancelled: "🟡 已取消 /reload-mcp。MCP 工具未變更。"
always_followup: "ℹ️ 後續 `/reload-mcp` 呼叫將不再要求確認。可在 `config.yaml` 中將 `approvals.mcp_reload_confirm: true` 重新啟用。"
confirm_prompt: "⚠️ **確認 /reload-mcp**\n\n重新載入 MCP 伺服器會為本工作階段重建工具集，並**使提供方提示快取失效** — 下一則訊息將重新傳送完整輸入 token。在長上下文或高推理模型上，這可能成本較高。\n\n請選擇：\n• **批准一次** — 立即重新載入\n• **永遠批准** — 立即重新載入並永久關閉此提示\n• **取消** — 保持 MCP 工具不變\n\n_文字備援：回覆 `/approve`、`/always` 或 `/cancel`。_"
header: "🔄 **MCP 伺服器已重新載入**\n"
reconnected: "♻️ 已重新連線：{names}"
added: "➕ 已新增：{names}"
removed: "➖ 已移除：{names}"
none_connected: "沒有已連線的 MCP 伺服器。"
tools_available: "\n🔧 來自 {servers} 個伺服器的 {tools} 個工具可用"
failed: "❌ MCP 重新載入失敗：{error}"
reload_skills:
header: "🔄 **技能已重新載入**\n"
no_new: "未偵測到新技能。"
total: "\n📚 {count} 個技能可用"
added_header: "➕ **新增技能：**"
removed_header: "➖ **移除技能：**"
item_with_desc: " - {name}：{desc}"
item_no_desc: " - {name}"
failed: "❌ 技能重新載入失敗：{error}"
reset:
header_default: "✨ 工作階段已重設！重新開始。"
header_new: "✨ 新工作階段已啟動！"
header_titled: "✨ 新工作階段已啟動：{title}"
title_rejected: "\n⚠️ 標題遭拒絕：{error}"
title_error_untitled: "\n⚠️ {error} — 工作階段以未命名方式啟動。"
title_empty_untitled: "\n⚠️ 清理後標題為空 — 工作階段以未命名方式啟動。"
tip: "\n✦ 提示：{tip}"
restart:
in_progress: "⏳ 閘道重新啟動已在進行中……"
restarting: "♻ 正在重新啟動閘道。如果 60 秒內未收到通知，請在主控台執行 `hermes gateway restart` 重新啟動。"
resume:
db_unavailable: "工作階段資料庫無法使用。"
no_named_sessions: "找不到已命名的工作階段。\n使用 `/title 我的工作階段` 為目前工作階段命名，然後使用 `/resume 我的工作階段` 返回。"
list_header: "📋 **已命名工作階段**\n"
list_item: "• **{title}**{preview_part}"
list_preview_suffix: " — _{preview}_"
list_footer: "\n用法：`/resume <工作階段名稱>`"
list_failed: "無法列出工作階段：{error}"
not_found: "找不到符合 '**{name}**' 的工作階段。\n使用不帶參數的 `/resume` 檢視可用的工作階段。"
already_on: "📌 已在工作階段 **{name}** 上。"
switch_failed: "切換工作階段失敗。"
resumed_one: "↻ 已恢復工作階段 **{title}**（{count} 則訊息）。對話已還原。"
resumed_many: "↻ 已恢復工作階段 **{title}**（{count} 則訊息）。對話已還原。"
resumed_no_count: "↻ 已恢復工作階段 **{title}**。對話已還原。"
retry:
no_previous: "沒有可重試的上一則訊息。"
rollback:
not_enabled: "檢查點未啟用。\n請在 config.yaml 中啟用：\n```\ncheckpoints:\n enabled: true\n```"
none_found: "找不到 {cwd} 的檢查點"
invalid_number: "無效的檢查點編號。請使用 1-{max}。"
restored: "✅ 已還原至檢查點 {hash}：{reason}\n已自動儲存回復前的快照。"
restore_failed: "❌ {error}"
set_home:
save_failed: "無法儲存主頻道：{error}"
success: "✅ 主頻道已設定為 **{name}**（ID：{chat_id}）。\n排程任務和跨平台訊息將傳送至此處。"
status:
header: "📊 **Hermes 閘道狀態**"
session_id: "**工作階段 ID：** `{session_id}`"
title: "**標題：** {title}"
created: "**建立時間：** {timestamp}"
last_activity: "**最近活動：** {timestamp}"
tokens: "**Token 數：** {tokens}"
agent_running: "**代理執行中：** {state}"
state_yes: "是 ⚡"
state_no: "否"
queued: "**排隊中的後續：** {count}"
platforms: "**已連線平台：** {platforms}"
stop:
stopped_pending: "⚡ 已停止。代理尚未啟動 — 你可以繼續此工作階段。"
stopped: "⚡ 已停止。你可以繼續此工作階段。"
no_active: "沒有可停止的作用中任務。"
title:
db_unavailable: "工作階段資料庫無法使用。"
warn_prefix: "⚠️ {error}"
empty_after_clean: "⚠️ 清理後標題為空。請使用可列印字元。"
set_to: "✏️ 已設定工作階段標題：**{title}**"
not_found: "在資料庫中找不到此工作階段。"
current_with_title: "📌 工作階段：`{session_id}`\n標題：**{title}**"
current_no_title: "📌 工作階段：`{session_id}`\n尚未設定標題。用法：`/title 我的工作階段名稱`"
topic:
not_telegram_dm: "/topic 指令僅在 Telegram 私人聊天中可用。"
no_session_db: "工作階段資料庫無法使用。"
unauthorized: "您無權在此 bot 上使用 /topic。"
restore_needs_topic: "若要恢復工作階段，請先建立或開啟一個 Telegram topic，然後在該 topic 中傳送 /topic <session-id>。若要建立新 topic，請開啟 All Messages 並在其中傳送任意訊息。"
topics_disabled: "此 bot 尚未啟用 Telegram topics。\n\n啟用方法：\n1. 開啟 @BotFather。\n2. 選擇您的 bot。\n3. 開啟 Bot Settings → Threads Settings。\n4. 開啟 Threaded Mode，並確保允許使用者建立新 thread。\n\n然後再次傳送 /topic。"
topics_user_disallowed: "Telegram topics 已啟用，但不允許使用者建立 topics。\n\n開啟 @BotFather → 選擇您的 bot → Bot Settings → Threads Settings，然後關閉 'Disallow users to create new threads'。\n\n然後再次傳送 /topic。"
enable_failed: "啟用 Telegram topic 模式失敗：{error}"
bound_status: "此 topic 已連結至：\n工作階段：{label}\nID：{session_id}\n\n使用 /new 將此 topic 取代為新工作階段。\n如需平行作業，請開啟 All Messages 並在其中傳送訊息以建立另一個 topic。"
thread_ready: "Telegram 多工作階段 topics 已啟用。\n\n此 topic 將作為獨立的 Hermes 工作階段使用。使用 /new 取代此 topic 目前的工作階段。如需平行作業，請開啟 All Messages 並在其中傳送訊息以建立另一個 topic。"
untitled_session: "未命名工作階段"
undo:
nothing: "沒有可復原的內容。"
removed: "↩️ 已復原 {count} 則訊息。\n已移除：「{preview}」"
update:
platform_not_messaging: "✗ /update 僅在訊息平台上可用。請在終端機執行 `hermes update`。"
not_git_repo: "✗ 不是 git 儲存庫 — 無法更新。"
hermes_cmd_not_found: "✗ 找不到 `hermes` 指令。Hermes 正在執行，但更新指令無法在 PATH 上或透過目前的 Python 解譯器找到執行檔。請嘗試在終端機中手動執行 `hermes update`。"
start_failed: "✗ 啟動更新失敗：{error}"
starting: "⚕ 正在啟動 Hermes 更新…… 進度將在此處顯示。"
usage:
rate_limits: "⏱️ **速率限制：** {state}"
header_session: "📊 **工作階段 token 使用情況**"
label_model: "模型：`{model}`"
label_input_tokens: "輸入 token：{count}"
label_cache_read: "快取讀取 token：{count}"
label_cache_write: "快取寫入 token：{count}"
label_output_tokens: "輸出 token：{count}"
label_total: "總計：{count}"
label_api_calls: "API 呼叫次數：{count}"
label_cost: "費用：{prefix}${amount}"
label_cost_included: "費用：已包含"
label_context: "上下文：{used} / {total}（{pct}%）"
label_compressions: "壓縮次數：{count}"
header_session_info: "📊 **工作階段資訊**"
label_messages: "訊息數：{count}"
label_estimated_context: "預估上下文：~{count} 個 token"
detailed_after_first: "_（首次代理回應後可檢視詳細使用情況）_"
no_data: "此工作階段沒有可用的使用資料。"
verbose:
not_enabled: "`/verbose` 指令未在訊息平台上啟用。\n\n請在 `config.yaml` 中啟用：\n```yaml\ndisplay:\n tool_progress_command: true\n```"
mode_off: "⚙️ 工具進度：**OFF** — 不顯示任何工具活動。"
mode_new: "⚙️ 工具進度：**NEW** — 工具變更時顯示（預覽長度：`display.tool_preview_length`，預設 40）。"
mode_all: "⚙️ 工具進度：**ALL** — 顯示每次工具呼叫（預覽長度：`display.tool_preview_length`，預設 40）。"
mode_verbose: "⚙️ 工具進度：**VERBOSE** — 顯示每次工具呼叫及完整參數。"
saved_suffix: "_（已為 **{platform}** 儲存 — 下一則訊息生效）_"
save_failed: "_（無法儲存到設定：{error}）_"
voice:
enabled_voice_only: "語音模式已啟用。\n當你傳送語音訊息時，我會以語音回覆。\n使用 /voice tts 讓所有訊息都收到語音回覆。"
disabled_text: "語音模式已停用。僅文字回覆。"
tts_enabled: "自動 TTS 已啟用。\n所有回覆都將包含一則語音訊息。"
status_mode: "語音模式：{label}"
status_channel: "語音頻道：#{channel}"
status_participants: "參與人數：{count}"
status_member: " - {name}{status}"
speaking: "（正在說話）"
enabled_short: "語音模式已啟用。"
disabled_short: "語音模式已停用。"
label_off: "關閉（僅文字）"
label_voice_only: "開啟（僅對語音訊息進行語音回覆）"
label_all: "TTS（對所有訊息進行語音回覆）"
yolo:
disabled: "⚠️ 本工作階段 YOLO 模式 **已關閉** — 危險指令將需要批准。"
enabled: "⚡ 本工作階段 YOLO 模式 **已開啟** — 所有指令自動批准。請謹慎使用。"
shared:
session_db_unavailable: "工作階段資料庫無法使用。"
session_db_unavailable_prefix: "工作階段資料庫無法使用"
session_not_found: "資料庫中找不到此工作階段。"
warn_passthrough: "⚠️ {error}"