Compare commits

...

129 Commits

Author SHA1 Message Date
Innei 571697b251 🐛 fix(conversation): keep workflow errors visible 2026-05-13 16:45:02 +08:00
Innei 4b0e1911a7 🐛 fix(conversation): reserve workflow scrollbar space 2026-05-13 16:04:09 +08:00
LobeHub Bot 2cfe9f6180 🌐 chore: translate non-English comments to English in file-loaders (#14744)
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-13 15:34:53 +08:00
Neko c9bb82d09d 🐛 fix(builtin-tool-memory): clarify memory retrieval sufficiency rules (#14753) 2026-05-13 15:19:43 +08:00
Rdmclin2 6933ddc4e5 🔨 chore: Online Messager (#14755)
* feat: add line integration Banner

* chore: remove messenger lab switch

* feat: add messenger banner

* feat: add messenger promo

* chore: update i18n files
2026-05-13 14:17:07 +07:00
Arvin Xu ef8aa72af5 🐛 fix(brief): add ignore action next to retry on error briefs (#14742)
*  feat(brief): add ignore action next to retry on error briefs

Lets users dismiss error briefs without re-running the task. The button
is hardcoded in the UI alongside the retry primary action; brief.actions
stays untouched.

*  feat(agent-runtime): wire trigger field across all execAgent call sites

- Add Cli / Openapi / Notify values to RequestTrigger enum
- Pass trigger:'cli' from CLI command, trigger:'openapi' from OpenAPI service
- Pass trigger:RequestTrigger.Eval from all 4 agentEvalRun call sites
- Pass trigger:RequestTrigger.Notify from agentNotify router
- Default trigger to RequestTrigger.Chat in execAgent/execAgents tRPC handler
- execGroupAgent passes trigger:RequestTrigger.Chat explicitly
- execSubAgentTask inherits trigger from parent operation (best-effort DB lookup)
- Expose trigger as optional input on ExecAgentSchema so callers can override
- Remove dead aiAgent.createOperation tRPC mutation and its frontend counterpart
- Delete test file that only covered the removed createOperation method

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* 💄 style(loading): use shiny text animation for operation labels

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* 🐛 fix(error): broaden heterogeneous agent error guard to match any error type

The previous guard required `error.type` to be `AgentRuntimeError` or absent,
which missed cases like `ServerAgentRuntimeError`. Extract the detection into a
proper type guard (`isHeterogeneousAgentStatusGuideError`) that checks only the
body shape (agentType + code), making it resilient to wrapper error types.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-13 15:12:24 +08:00
Neko 8618699888 🐛 fix(server/toolExecution): support server-owned memory embedding runtime (#14754) 2026-05-13 15:09:17 +08:00
Neko bfc4820a17 🐛 fix(server/userMemories): return locomo ingestion session results (#14752) 2026-05-13 15:09:10 +08:00
LiJian d8bfc58f22 🐛 fix(casc): replace new Function() template with safe string builders (#14751)
* 🐛 fix(casc): replace new Function()-based template with safe string builders and self-fetching ChangelogModal

- Remove es-toolkit/compat template (uses new Function()) from ShareModal, ShareMessageModal, and parserPlaceholder; replace with plain string building and String.replace
- ChangelogModal now self-fetches latest changelog id via lambdaClient instead of relying on async server component wrapper; setTimeout starts after data arrives
- Remove ChangelogService/gray-matter import from route component

* 🐛 fix(casc): add missing deps to changelog timer effect
2026-05-13 14:59:50 +08:00
Neko 690098dcb9 🐛 fix(agent-signal,server): both skill bundle and skill index should be considered as primary skill documents (#14748) 2026-05-13 13:11:59 +08:00
Neko a12079d338 🐛 fix(server): user id context missing in tool outcome for signal (#14749) 2026-05-13 13:11:49 +08:00
LiJian 8d1584eb78 🐛 fix(cc): preserve trailing suffix after partial deltas (#14745)
* 🐛 fix(cc): preserve trailing suffix after partial deltas

* 🐛 fix(cc): clear streamed delta buffers after reconciliation

* 🐛 fix(cc): clear streamed buffers per modality
2026-05-13 12:56:00 +08:00
LiJian c3bb289c44 🐛 fix(market-auth): add offline_access scope and guard expiresIn default (#14743)
Add `offline_access` to the OIDC authorization scope so the server
returns a refresh_token, fixing silent session expiry after ~24h.

Guard `tokenResponse.expiresIn` with `?? 3600` to prevent `NaN`
propagation into `expiresAt` when the server omits the field.

Co-authored-by: Claude <claude@anthropic.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-13 11:30:07 +08:00
lobehubbot c19f87fdb2 Merge remote-tracking branch 'origin/main' into canary 2026-05-13 01:59:32 +00:00
Arvin Xu 9d03349c46 🚀 release: 20260513 (#14739)
# 🚀 LobeHub Release (20260513)

**Hotfix Scope:** Ship the canary backlog (111 PRs) onto main as a
fast-tracked patch — operator-focused, no weekly-style write-up.

> Brings the accumulated canary work into main: agent/task improvements,
hetero-agent fixes, desktop & onboarding polish, and several reliability
caps.

##  What's Included

- **Agent & tasks** — Self-review proposal-to-action automation,
sub-agent dispatch consolidated to `lobe-agent`, AskUserQuestion wiring
for Claude Code, scheduler/hotkey/TodoList polish. (#14583, #14657,
#14715, #14639, #14732, #14707, #14713)
- **Home & onboarding** — Daily brief with linkable welcome + paired
input hint, inline skill auth in recommended task templates, cleanup of
captcha-on-signin and marketplace early-exit. (#14589, #14676, #14573,
#14598)
- **Bots & integrations** — Slack MPIM support, Discord DM fix,
slash-command + connect-error fixes, gateway client-tool plugin state.
(#14733, #14591, #14596)
- **Desktop & CLI** — Windows `.cmd` shim detection for `claude` /
`codex` CLIs, auth focus & pending-login reset fixes. (#14720, #14694,
#14695)
- **Reliability** — Cap web-crawler body size and image binary at safe
limits, attach error listeners to Neon/Node pools, reject inactive OIDC
access. (#14660, #14711, #14606, #14674)
- **Database** — `agent_operations` table + persist agent operations
from the runtime; switch user memory search to `paradedb.match(...)`.
(#14416, #14736, #14590)

## ⚙️ Upgrade

- **Self-hosted:** pull the latest image and restart. Drizzle migrations
(including the new `agent_operations` table) run automatically on boot.
2026-05-13 09:58:47 +08:00
Zhijie He 1a745382b5 💄 style: add spark-x2-flash support (#14731)
* style: add spark-x2-flash support

* fix: fix deployname not send to api

fix: fix deployname not send to api

fix: fix deployname not send to api

fix: fix deployname not send to api

fix: fix deployname func

fix: fix deployname func
2026-05-13 03:08:55 +08:00
Arvin Xu a77234107e feat(agent-runtime): persist agent operations to agent_operations table (#14736)
*  feat(agent-runtime): persist agent operations to `agent_operations` table

Wire start-time INSERT and terminal UPDATE into the agent runtime so
operation history outlives the 2-hour Redis TTL. Adds
`AgentOperationModel` with `recordStart` / `recordCompletion` /
`findById` (scoped by userId so a leaked operationId can't flip another
user's row) and threads both calls through `CompletionLifecycle`, which
now owns both ends of the persistence lifecycle. Also plumbs
`parentOperationId` through `ExecAgentParams` → `OperationCreationParams`
so sub-agent invocations carry their parent lineage. Per-step aggregate
updates are intentionally out of scope.

Refs LOBE-8848

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(agent-runtime): update CompletionLifecycle test constructor to 2 args

CompletionLifecycle now constructs MessageModel internally from
(db, userId), so the test builder passing a third messageModel arg
tripped tsgo --noEmit.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:14 +08:00
Rdmclin2 729265ab5d feat: support slack mpim and fix discord dm problem (#14733)
* feat: support mpim

* chore: add errorMsg

* fix: discord commands thinking error

* fix: discord typing error

* feat: add oauth process for discord
2026-05-13 02:57:14 +08:00
Arvin Xu 5174c13ef1 🐛 fix(hetero-agent): wire AskUserBridge response events to renderer (#14732)
Close the wire-protocol gap that left CC's AskUserQuestion form stuck on
"pending" after the bridge gave up. AskUserBridge now emits an
agent_intervention_response event on every terminal path (timeout,
user resolve, cancel, cancelAll), and heterogeneousAgentExecutor handles
it by stamping pluginIntervention.status = 'rejected' for timeout /
session_ended (user-driven paths are filtered out — already optimistic).

Layered defenses so a late Submit no longer throws "Operation not found":
- cleanupCompletedOperations: find→filter so every messageOperationMap
  entry pointing to the cleaned op is removed (assistant + tool message
  pairs previously stranded one entry as a dangling reference).
- internal_getConversationContext: log + fall back to global state when
  the op has been GC'd, instead of throwing.
- submitHeteroIntervention: detect a stale opId before passing it into
  the optimistic chain.

Scoped as a short-term backstop until LOBE-8746 retires the AskUser MCP
bridge entirely.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:14 +08:00
Arvin Xu dcc9f78091 ♻️ refactor(builtin-tool): move sub-agent dispatch from lobe-gtd to lobe-agent (#14715)
* ♻️ refactor(builtin-tool): move sub-agent dispatch from lobe-gtd to lobe-agent

Move the `execTask` / `execTasks` capability out of `packages/builtin-tool-gtd/`
and into `packages/builtin-tool-lobe-agent/`, renaming the public APIs to
`callSubAgent` / `callSubAgents`. The "subtask" naming inside GTD overlapped
with the new lobe-task tool's task model and conflated planning with
sub-agent dispatch.

- API names: `execTask` → `callSubAgent`, `execTasks` → `callSubAgents`
- TS types: `ExecTaskParams` → `CallSubAgentParams`, etc.; introduce
  `SubAgentTask` to replace `ExecTaskItem`
- Client UI (Inspector / Render / Streaming) ported under
  `packages/builtin-tool-lobe-agent/src/client/`
- Central registries (`packages/builtin-tools/src/{inspectors,renders,streamings}.ts`)
  updated to register lobe-agent
- GTD `meta.description` and system role no longer mention async tasks;
  they point to lobe-agent for sub-agent dispatch
- `isSubTask` filtering in `agentConfigResolver` now excludes `lobe-agent`
  (new owner of sub-agent dispatch) instead of `lobe-gtd`
- i18n: new `builtins.lobe-agent.apiName.callSubAgent*` and
  `workflow.toolDisplayName.callSubAgent*` keys in default/zh-CN/en-US

Kept the executor's emitted `state.type` values (`execTask` / `execTasks` /
`execClientTask` / `execClientTasks`) unchanged so the agent-runtime
instruction layer (`exec_task` / `exec_tasks` / `exec_client_task*`) and all
downstream tests / heterogeneous executors (`builtin-tool-agent-management`,
server `agentManagement` runtime) continue to work without modification.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor(chat): rename isSubTask flag to isSubAgent

After moving sub-agent dispatch from lobe-gtd to lobe-agent, the flag name
no longer matches what it controls. Rename `isSubTask` → `isSubAgent` across
the chat / agent runtime layer and update related comments and test labels.

- `agentConfigResolver` context field + filter helper
- `streamingExecutor.internal_createAgentState` + `executeClientAgent`
  signatures and call sites
- `createAgentExecutors` (exec_task / exec_client_task handlers) and
  `GroupOrchestrationExecutors` (batch_exec_async_tasks)
- `chatService.createAssistantMessageStream` `resolvedAgentConfig` docs
- Test descriptions and assertions in `agentConfigResolver.test.ts` and
  `streamingExecutor.test.ts`

No behavior change — the flag's filter target (`lobe-agent` identifier) is
unchanged.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor(agent-runtime): rename exec_task wire identifiers to exec_sub_agent

Bring the agent-runtime "wire" naming in line with the lobe-agent
callSubAgent / callSubAgents API rename. Three layers are renamed in lockstep
to keep the bridge between tool executors and the runtime consistent:

1. Tool-emitted state.type discriminators
   - 'execTask' → 'execSubAgent'
   - 'execTasks' → 'execSubAgents'
   - 'execClientTask' → 'execClientSubAgent'
   - 'execClientTasks' → 'execClientSubAgents'

2. AgentInstruction.type and matching TS interfaces
   - 'exec_task' / 'exec_tasks' / 'exec_client_task' / 'exec_client_tasks'
     → 'exec_sub_agent' / 'exec_sub_agents' / 'exec_client_sub_agent' /
       'exec_client_sub_agents'
   - AgentInstructionExecTask → AgentInstructionExecSubAgent (and the three
     siblings)
   - ExecTaskItem → SubAgentTask

3. AgentRuntimeContext.phase + matching payload types
   - 'task_result' → 'sub_agent_result'
   - 'tasks_batch_result' → 'sub_agents_batch_result'
   - TaskResultPayload → SubAgentResultPayload
   - TasksBatchResultPayload → SubAgentsBatchResultPayload

Also renames the operation-type discriminator 'execClientTask' /
'execClientTasks' to 'execClientSubAgent' / 'execClientSubAgents' and updates
its locale string in default / zh-CN / en-US.

Tests / fixtures / mocks updated in lockstep:
- packages/agent-runtime/src/agents/{GeneralChatAgent.ts,__tests__/...}
- packages/builtin-tool-{lobe-agent,agent-management}/src/...
- src/server/services/toolExecution/serverRuntimes/agentManagement.ts
- packages/agent-mock/src/cases/builtins/todo-write-stress.ts (helper renamed
  to callSubAgent)
- src/store/chat/agents/createAgentExecutors.ts + exec-task / exec-tasks tests
  + fixtures/mockInstructions.ts (createExecSubAgent[s]Instruction)
- src/store/chat/slices/aiChat/actions/streamingExecutor.ts (phase check)
- packages/conversation-flow/src/__tests__/fixtures/**/*.json (8 fixtures
  retargeted from lobe-gtd/execTask[s] to lobe-agent/callSubAgent[s] with the
  new state.type wire values)

No behavior change — the agent runtime, executors and tests all go through
the same code paths; only the strings on the wire change.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor(builtin-tool): absorb GTD tool (plan + todo) into lobe-agent

Delete `packages/builtin-tool-gtd/` and fold its full surface — plan, todo,
ExecutionRuntime, all client UI (Inspector / Render / Streaming /
Intervention / SortableTodoList) and the system role — into
`packages/builtin-tool-lobe-agent/`. Single `lobe-agent` identifier now
owns: plan + todo management, sub-agent dispatch, and visual media analysis.

Also restructures the lobe-agent package so the executor lives under
`./client/` alongside the UI it ships with, and drops the dedicated
`./executor` export — consumers go through `./client` for everything
client-side.

Package-level changes:
- DELETE `packages/builtin-tool-gtd/` entirely.
- `packages/builtin-tool-lobe-agent/`
  - Move `src/executor/` → `src/client/executor/`. Drop `./executor` from
    `package.json` exports; expose `lobeAgentExecutor` via `./client` only.
  - Rename `GTDExecutionRuntime` → `PlanExecutionRuntime` and place under
    `src/client/executor/PlanRuntime/`. Re-export from package root so the
    server runtime can consume it without pulling in client UI deps.
  - Extend `LobeAgentExecutor` with `createPlan` / `updatePlan` /
    `createTodos` / `updateTodos` / `clearTodos`, all delegated to the
    shared runtime.
  - Add Plan + Todo API entries to the manifest (with their original
    descriptions, humanIntervention, renderDisplayControl).
  - Move all GTD client UI verbatim:
    `Inspector/{ClearTodos,CreatePlan,CreateTodos,UpdatePlan,UpdateTodos}`,
    `Render/{CreatePlan,TodoList}`, `Streaming/CreatePlan`,
    `Intervention/{AddTodo,ClearTodos,CreatePlan}`,
    `components/SortableTodoList`. Register them in
    `LobeAgentInspectors / Renders / Streamings`, add new
    `LobeAgentInterventions`.
  - Merge GTD system role into lobe-agent's (`<plan_and_todos>` plus the
    existing `<sub_agents>` and `<run_in_client>` sections).
  - `package.json`: pick up `@lobechat/prompts` dep and `@lobehub/editor` +
    `antd` + `lucide-react` peer-deps inherited from GTD.

Central registries (`packages/builtin-tools/src/*`) and consumers:
- Remove every `GTDManifest / Inspectors / Renders / Streamings /
  Interventions` import + registration; existing `LobeAgent*` registrations
  now cover them.
- Replace `[GTDManifest.identifier]: GTDInterventions` with
  `[LobeAgentManifest.identifier]: LobeAgentInterventions`.
- Drop `@lobechat/builtin-tool-gtd` workspace dep from
  `packages/builtin-tools/package.json`, `packages/builtin-agents/package.json`
  and root `package.json`.
- Remove `gtdExecutor` from `src/store/tool/slices/builtin/executors/index.ts`;
  switch `lobeAgentExecutor` import to `/client`.
- Replace `serverRuntimes/gtd.ts` with a service factory
  `serverRuntimes/lobeAgentPlan.ts` (`createServerPlanRuntimeService`).
  `serverRuntimes/lobeAgent.ts` instantiates `PlanExecutionRuntime` with
  that service so the registry exposes one runtime per `lobe-agent`
  identifier covering both visual analysis and plan/todo.
- `services/chat/mecha/contextEngineering.ts`: gate plan/todo injection on
  `LobeAgentIdentifier` instead of `GTDIdentifier`.
- `agentConfigResolver.test.ts`: switch fixture plugin IDs to
  `LobeAgentIdentifier`.
- `packages/const/src/recommendedSkill.ts`: drop the standalone `lobe-gtd`
  recommendation — `lobe-agent` already covers it via `defaultToolIds`.

i18n migration (default + zh-CN + en-US; other locales regenerate on
`pnpm i18n`):
- `builtins.lobe-gtd.*` → `builtins.lobe-agent.*` in `plugin.ts/json`.
- `lobe-gtd.*` (tool namespace) → `lobe-agent.*` in `tool.ts/json`.
- Remove `tools.builtins.lobe-gtd.{description,readme,title}` from
  `setting.ts/json` (lobe-agent has its own meta now).
- Update all client component `t(...)` keys to the new namespace.

Mocks / fixtures / tests:
- `packages/agent-mock/src/cases/builtins/todo-write-stress.ts`: all
  `identifier: 'lobe-gtd'` → `'lobe-agent'`; helper comments updated.
- `packages/types/src/stepContext.ts`: comment refers to
  `builtin-tool-lobe-agent` (the only consumer of `StepContextTodoItem`).
- `packages/model-runtime/src/core/streams/google/google-ai.test.ts`:
  function-call names from `lobe-gtd____createPlan` etc. → `lobe-agent____*`.
- `src/store/chat/slices/message/selectors/dbMessage.test.ts`: same.
- `src/features/DevPanel/RenderGallery/fixtures/lobe-gtd.ts` deleted; its
  plan/todo fixtures are folded into `fixtures/lobe-agent.ts` alongside the
  existing `callSubAgent[s]` ones.
- Replace `console.log` → `console.info` in moved client components to
  satisfy lobe-agent's stricter ESLint rules (GTD package allowed
  `console.log`; lobe-agent inherits the repo-wide `no-console` rule).

No behavior change for end users: `lobe-agent` now owns all the APIs,
identifiers, and UI that previously lived in `lobe-gtd`, but as a single
consolidated package under a single tool identifier.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor(context-engine): drop residual GTD naming, rename to PlanInjector / TodoInjector

Follow-up to 9ca5c9d (which absorbed the GTD tool package into lobe-agent).
That commit moved the package surface but left the GTD vocabulary embedded
in context-engine providers, types, metadata fields, XML tags, and a pile
of comments. This change finishes the sweep so the only remaining GTD
references are user-facing docs and the legitimate Productivity & GTD Coach
methodology suggestion.

context-engine
- `GTDPlanInjector` → `PlanInjector`; types `GTDPlan`/`GTDPlanInjectorConfig`
  → `Plan`/`PlanInjectorConfig`; metadata `gtdPlanId`/`gtdPlanInjected` →
  `planId`/`planInjected`; XML tag `<gtd_plan>` → `<plan>`; debug channel
  `provider:GTDPlanInjector` → `provider:PlanInjector`.
- `GTDTodoInjector` → `TodoInjector`; types `GTDTodoItem`/`GTDTodoList`/
  `GTDTodoStatus`/`GTDTodoInjectorConfig` → `TodoItem`/`TodoList`/
  `TodoStatus`/`TodoInjectorConfig`; metadata `gtdTodo*` → `todo*`;
  XML tag `<gtd_todos>` → `<todos>`, wrapper `gtd_todo_context` →
  `todo_context`; debug channel renamed similarly.
- `MessagesEngineParams.gtd?: GTDConfig` → `planTodo?: PlanTodoConfig`;
  internal vars `isGTDPlanEnabled`/`isGTDTodoEnabled` →
  `isPlanEnabled`/`isTodoEnabled`. Re-exports updated in `providers/index.ts`
  and `engine/messages/{index,types}.ts`.

prompts
- `packages/prompts/src/prompts/gtd/` → `planTodo/` (only export was
  `formatTodoStateSummary`, which kept its name). Updated `prompts/index.ts`
  re-export.

src/services
- `contextEngineering.ts`: `GTDConfig` import → `PlanTodoConfig`;
  `isGTDEnabled`/`gtdConfig` → `isPlanTodoEnabled`/`planTodoConfig`; payload
  field `gtd` → `planTodo`; log message wording.

Tests
- `dbMessage.test.ts`: helper `createGTDToolMessage` →
  `createLobeAgentToolMessage`; `gtdMessage` → `lobeAgentMessage`; all `it`
  descriptions reworded to "lobe-agent" instead of "GTD".
- `agentConfigResolver.test.ts`: test descriptions reworded.

Comments / docs (no behavior change)
- agent-runtime (`instruction.ts`, `runtime.ts`, `generalAgent.ts`,
  `messageSelectors.ts`), `types/{stepContext,tool/builtin}.ts`,
  `builtin-agents/group-supervisor`, `builtin-tool-claude-code/types.ts`,
  `builtin-tool-lobe-agent/Render/TodoList`, `createAgentExecutors.ts:1426`,
  `AssistantGroup/{constants,Fallback.test}`, `agent-mock/todo-write-stress`,
  `.agents/skills/builtin-tool/references/architecture.md`.

Intentionally left alone
- `docs/usage/agent/gtd.{mdx,zh-CN.mdx}` and other docs — user-facing
  product brand "GTD Tools".
- `src/locales/default/suggestQuestions.ts` "Productivity & GTD Coach" —
  references the methodology, not the tool.
- `ToolSystemRoleProvider.test.ts` `'gtd-tool'` fixture — generic test
  identifier, unrelated.
- Translated locale files still carrying `lobe-gtd.*` keys — regenerated by
  `pnpm i18n` from the updated default namespace.

Verified: `bun run type-check` passes; touched test files
(dbMessage, agentConfigResolver) and full context-engine + prompts test
suites pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(builtin-tool-lobe-agent): reset TodoList auto-save status to idle

`performSave` (the debounced auto-save path) was leaving `saveStatus` stuck
on 'saved' forever — `saveNow` had the 1.5s setTimeout-to-idle but the
auto-save twin didn't, so the inline indicator never eased back to idle
after a settle. Add the same idle-reset to performSave so both paths
behave the same.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:14 +08:00
Arvin Xu 266d10206b 💄 style: use @lobehub/ui built-in HtmlPreview instead of custom component (#14703)
* 💄 style(home,i18n): use 已阅 for brief confirm/confirmDone in zh-CN

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(home): use 确认完成 for brief.action.confirmDone in zh-CN

confirmDone signals the terminal transition (task marked complete),
not just dismissing the brief, so 已阅 loses the semantic distinction
from `confirm`. Use 确认完成 to match the EN intent ("Confirm complete").

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor: use @lobehub/ui built-in HtmlPreview instead of custom component

- Upgrade @lobehub/ui from ^5.10.1 to ^5.10.4
- Replace custom HtmlPreviewAction with lobe-ui's enableHtmlPreview
- Wire lobe-ui's onExpand callback to existing HtmlPreviewDrawer
- Remove HtmlPreviewAction.tsx (no longer needed)
- Keep HtmlPreviewDrawer for the expanded full-screen view

* 🐛 fix(task): sync useMarkdown destructuring with assistant MessageContent

* 🐛 fix(task): correct mangled search.X JSX expressions in MessageContent

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(review): move revert icon to right edge of file row

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:13 +08:00
LobeHub Bot 71a49b033f 🌐 chore: translate non-English comments to English in src (#14654)
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-13 02:57:13 +08:00
Arvin Xu fc275ca4dc 🐛 fix(home): blank user bubble when sending the placeholder hint (#14678)
When the home input was empty and the user clicked send, `useSend`
correctly fell back to the daily-brief hint for `message`, but it also
forwarded `mainInputEditor.getJSONState()` as `editorData`. An empty
editor still returns a non-null JSON state (e.g. `{ type: 'doc' }`),
which makes `UserMessageContent.hasEditorData` truthy — so the renderer
took the RichTextMessage branch and drew nothing, while the agent
happily processed the hint text behind a blank user bubble.

Skip `editorData` when the hint is being used so the renderer falls
back to the markdown `content`. Adds a regression test.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:13 +08:00
Arvin Xu cb8b616546 feat(database): add agent_operations table (#14416)
 feat(database): add agent_operations table

Adds an `agent_operations` table to persist agent runtime operations
beyond the 2-hour Redis TTL. Each row captures one agent operation
(operationId) with denormalized cost/token aggregates, lifecycle
timestamps, runtime config snapshot, and a `trace_s3_key` pointer to
the full ExecutionSnapshot in S3.

- `user_id` is intentionally not a FK so operation history survives
  user deletion (auditable historical data).
- `agent_id` / `topic_id` / `thread_id` / `task_id` / `chat_group_id`
  use ON DELETE SET NULL to preserve operations when their parent
  entity is removed.
- `parent_operation_id` self-references for sub-agent (callAgent) ops.
- `human_interventions` and `human_waiting_time_ms` are nullable since
  most operations have no human interaction at all.
- Indexes optimize per-user listing and per-status / per-entity lookups;
  `metadata` has a GIN index for jsonb filters.
2026-05-13 02:57:13 +08:00
Innei 217afcf1af 🐛 fix(conversation): prevent synthetic scroll from shrinking spacer (#14584)
🐛 fix: prevent synthetic scroll from shrinking spacer
2026-05-13 02:57:13 +08:00
Arvin Xu 2f33932198 ♻️ refactor(agent-runtime): extract CompletionLifecycle, HumanInterventionHandler, stepPresentation (#14441)
* ♻️ refactor(agent-runtime): extract CompletionLifecycle

Pull terminal-state handling out of AgentRuntimeService into a dedicated
class:

- buildLifecycleEvent (was buildCompletionLifecycleEvent)
- emitSignalEvents (was emitCompletionSignalEvents)
- dispatchHooks (was dispatchCompletionHooks)
- extractErrorMessage

These four methods formed one cohesive vertical: build the lifecycle
event payload, emit completion AgentSignal source events, dispatch
onComplete/onError hooks, and write error back onto the assistant
message row. extractErrorMessage was a private helper used by all three
plus by the trace-snapshot finalize call site, so it becomes a public
method on the class.

Call sites in executeStep / executeSync change from
`this.{emit|dispatch|extract...}` to `this.completionLifecycle.{...}`.

Tests: extractErrorMessage.test.ts → CompletionLifecycle.test.ts,
instantiating CompletionLifecycle directly instead of going through
AgentRuntimeService — drops a pile of unrelated mocks.

AgentRuntimeService.ts: 2084 → 1918 (-166).

All 81 agentRuntime tests pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor(agent-runtime): extract HumanInterventionHandler

Pull the 165-line `handleHumanIntervention` method out of
AgentRuntimeService into its own class, splitting the three branches
(approve / rejectAndContinue / rejectAndHalt) into private methods so
each fits in one screen. Routing in `process()` now reads top-to-bottom:
detect approval, then rejection, then unsupported humanInput.

The handler depends only on `serverDB` (for the messagePlugins lookup)
and `messageModel` (for tool/plugin updates) — much narrower than
AgentRuntimeService's full surface, so the extracted unit is easier to
unit-test in isolation.

Drop the unused `runtime: AgentRuntime` parameter from the public API:
the original method threaded it through but never called it.

Tests: handleHumanIntervention.test.ts → HumanInterventionHandler.test.ts
— same 17 cases, but instantiate the handler directly instead of
constructing a full AgentRuntimeService with 11 module mocks. Tighter
arrange step, same coverage.

AgentRuntimeService.ts: 1918 → 1742 (-176).

All 81 agentRuntime tests pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor(agent-runtime): extract step presentation builder

Pull the ~150-line `phase`-branching block out of executeStep into a
pure `buildStepPresentation` function. The block did three things in
sequence: derive content/reasoning/toolsCalling/toolsResult from the
runtime step result, build a one-line stepSummary for logging, and
assemble the StepPresentationData DTO consumed by afterStep hooks /
snapshot recorder / callbacks.

The function takes only the stepResult and an executionTimeMs; no
service state needed. Comes with a `formatTokenCount` helper for the
log line (12345 → 12.3k, 2_500_000 → 2.5m).

executeStep keeps the log call inline (one line, references presentation
fields directly) and reads `content` / `toolsCalling` off presentation
for downstream tracking + truncation logic.

13 new unit tests: phase=tool_result (json + string + isSuccess paths),
phase=tools_batch_result, done event, llm_result with content/reasoning/
tools, empty fallback, cumulative usage zero-fallback, stepUsage
forwarding, and formatTokenCount edges.

AgentRuntimeService.ts: 1742 → 1601 (-141).

All 94 agentRuntime tests pass (was 81, +13 new).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:13 +08:00
Arvin Xu df0e635c45 🐛 fix(task-card): localize task card date independent of dayjs global locale (#14730)
* 🐛 fix(task-card): localize date format independent of dayjs global locale

Task card was rendering "5月 12" under English UI because t('time.formatThisYear')
returned the English "MMM D" format, but dayjs's global locale was still zh-cn,
making MMM resolve to the Chinese short month name. Thread the i18n language
into formatTaskItemDate so the date is rendered with the same locale as the
format string, decoupling it from dayjs's global state.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(task-card): import missing GenericItemType + type Run now onClick

Pre-existing CI regression from #14727 surfacing on every PR: the Run now
context menu satisfies-clause references GenericItemType without importing
it, and the onClick lacks a MenuInfo annotation, so tsgo widens the divider
literal's `type` to `string` and rejects the whole context menu array.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:13 +08:00
Arvin Xu 2202189ac1 🐛 fix(web-crawler): cap response body size to prevent serverless OOM (#14660)
* 🐛 fix(web-crawler): cap response body size to prevent serverless OOM

Production saw repeated SIGABRT crashes on `/trpc/tools/search.webSearch`
where Node aborted with V8 "allocation failed" — the naive crawler buffered
entire response bodies into heap before the 1 MB downstream truncation could
apply, so a single large page (or a batch of three under default
concurrency=3) could push rss past the lambda memory ceiling.

- ssrfSafeFetch: add opt-in `maxContentLength` that streams the response
  body via `for await` and stops at the cap (soft truncation — still a
  successful response). Breaking the iterator destroys the underlying
  stream and releases the connection. Default behaviour (full
  `arrayBuffer()` read) unchanged when the option is absent.
- naive crawler: pass `maxContentLength: MAX_HTML_SIZE` so any body beyond
  1 MB is dropped at the network layer instead of being materialised in heap.
- htmlToMarkdown: explicitly call `window.happyDOM.close()` in a finally
  block so the parsed DOM tree is released as soon as parsing finishes,
  rather than waiting for the function scope to drop.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  test(ssrf-safe-fetch): add OOM regression tests for response body cap

Verify that the maxContentLength cap actually prevents the production SIGABRT
scenario, not just produces a truncated body.

- Source-pull bound: a body source with 200 MB available, capped at 1 MB,
  must not be drained beyond ~1 MB. Asserts on bytes pulled from the
  generator, which is the property that prevents OOM.
- Concurrency bound: matches production CRAWL_CONCURRENCY=3 — three
  concurrent oversized fetches should pull at most ~3 MB total, not 300 MB.
- Heap-delta bound (gated on --expose-gc): under real GC pressure,
  fetching a 50 MB body with a 1 MB cap should grow heapUsed by < 10 MB.
  Run with `NODE_OPTIONS=--expose-gc bunx vitest run` to exercise; skipped
  by default so CI doesn't false-fail on GC timing.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:13 +08:00
Innei 4e4294f57e 🐛 fix(desktop): focus onboarding auth success state (#14694) 2026-05-13 02:57:13 +08:00
Arvin Xu 79152fa222 feat(markdown): user_feedback card + task card polish + Run now context menu (#14727)
*  feat(markdown): render <user_feedback> task prompt blocks as a card

`buildTaskRunPrompt` wraps the user's pre-run comments in a
`<user_feedback>` block alongside `<task>`. The Task plugin captured
`<task>` into a card, but `<user_feedback>` had no plugin and leaked
into the chat as raw XML. Because CommonMark only treats tag names
matching `[a-zA-Z][a-zA-Z0-9-]*` as html, the underscore in
`user_feedback` puts the opening/closing tags inside a `paragraph` as
plain text — so the new remark plugin walks paragraph children rather
than html nodes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(task-card): drop standalone status row + Agent/Parent/Topics, inline semantic status badge

The status/Priority row, Agent, Parent and Topics fields aren't useful
when the task card is rendered inside the topic chat drawer (the drawer
already exposes that context). Move the task status to a compact badge
beside the identifier and reuse `taskDetail.status.*` for the label so
"scheduled" reads as "Scheduled" / "已排期".

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(user-feedback): compact one-line header + left-border quote-style card

Slims the card down to a single 12px header line ("User feedback · N
comments") with a small 12px icon, and wraps the whole block in a
subtle fill + 2px left-border accent so it reads as a quoted aside and
visually separates from the task card that follows in the same user
message body.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(user-feedback): drop fill + radius, render as plain left-rail blockquote

The filled card competed visually with the unstyled task block that
sits beside it in the same message body. Reducing to a 2px left-rail
quote without background or border-radius lets both blocks read as
parts of the same user message.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(user-feedback): collapsible card with task-style head + bottom divider

Default-collapsed `<details>` whose summary mirrors the task title row
(32px icon + bold label + small count badge), with a bottom split-line
that doubles as a divider between the user feedback head and the task
card that follows in the same message body.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(user-feedback): strip default markdown details card chrome

@lobehub/ui Markdown applies bg + padding (0.75em 1em) + box-shadow +
border-radius to every nested <details>, which made the user_feedback
head read as a wide standalone card sitting awkwardly on top of the
inline task title. Override the chrome (with !important — the lib
selector wins on specificity otherwise) so the head sits flat in the
message body, with only the bottom split line separating it from the
task that follows. The lib's right-side disclosure chevron is kept.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(user-feedback): match task card's 12px symmetric divider spacing

Add a 12px margin-bottom so the gap below the user_feedback bottom rule
mirrors the 12px above it, matching the symmetric 12px the task card
already uses around its own internal divider. Without this, the
user_feedback rule sat flush against the T-31 row while the next rule
below T-31 had a 12px gap on both sides — visually uneven.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(task-card): drop status badge from task title row

The task drawer header and the schedule strip on the task detail page
already convey status; surfacing it again on the task card inside the
chat body just added noise. Drop the badge along with the now-unused
KNOWN_STATUSES / isKnownStatus / TaskStatusIcon / useTranslation
plumbing.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  feat(tasks): add "Run now" item to task card context menu

Available only for backlog and completed tasks; mirrors the inbox-agent
fallback used by the detail-page Run Now action.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(topic-list): preserve `#` icon placeholder for heterogeneous agents

Returning null for the icon slot collapsed the row layout, so titles on
heterogeneous-agent topics (Claude Code, Codex, …) no longer aligned
with sibling rows. Render the same HashIcon with visibility:hidden so
the box is preserved without showing the glyph.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:13 +08:00
brone1323 ece409195a 🌐 i18n: add missing task-schedule and review strings to 16 locales (#14728)
🌐 i18n: add missing translations for task-schedule and review keys across 16 locales

Adds 14 missing i18n keys to all non-zh-CN locales (ar, bg-BG, de-DE,
es-ES, fa-IR, fr-FR, it-IT, ja-JP, ko-KR, nl-NL, pl-PL, pt-BR, ru-RU,
tr-TR, vi-VN, zh-TW):

chat.json (11 keys):
- taskSchedule.summary.everyNHoursHalfPast
- taskSchedule.summary.hourlyHalfPast
- taskSchedule.timezoneSearchEmpty
- taskSchedule.timezoneSearchPlaceholder
- workingPanel.review.revert (and 7 sub-keys)

plugin.json (1 key):
- builtins.lobe-task.apiName.setTaskSchedule

setting.json (2 keys):
- serviceModel.modelAssignments.title
- serviceModel.optionalFeatures.title

These were added in recent commits but the automated i18n sync had not
yet propagated them to non-Chinese locales.
2026-05-13 02:57:13 +08:00
Innei e56edab711 💄 style: polish desktop header icons, sidebar density, and task menus (#14724)
* 💄 style: shrink desktop header icons and tighten sidebar/home density

Switches all desktop header action icons from DESKTOP_HEADER_ICON_SIZE to
DESKTOP_HEADER_ICON_SMALL_SIZE, and tightens vertical gaps in the home
sidebar, recents list, and nav header layout for a denser, calmer look.

* ♻️ refactor(agent-tasks): migrate task menus and scheduler select to @lobehub/ui base-ui

- TaskPriorityTag / TaskStatusTag: replace antd Dropdown with base-ui
  DropdownMenu and adopt the ContextMenuItem / MenuInfo typings.
- useTaskItemContextMenu: drop the DOM data-attribute submenu marker in
  favour of an internal activeSubmenuRef tracked via onOpenChange.
- TaskScheduleConfig / SchedulerForm: swap @lobehub/ui Select for the
  base-ui Select and replace the custom SearchBar dropdownRender with
  antd Select showSearch for timezone filtering.

* ♻️ refactor(review): migrate review dropdowns to @lobehub/ui base-ui DropdownMenu

Swap the antd Dropdown trios (mode picker, base-ref picker, more menu) in
the agent working-sidebar Review pane for the base-ui driven DropdownMenu,
matching the recent task menus / scheduler migration. Also tighten the
sidebar header paddingInline from 16 to 4 to align with the surrounding
density polish.

* 🐛 fix(tasks): replace unsupported onOpenChange with onTitleMouseEnter in context menu
2026-05-13 02:57:13 +08:00
René Wang 3a4bd4a83d fix: Docs image (#14726)
fix: image
2026-05-13 02:57:12 +08:00
René Wang 19912fe02d 📝 docs: add May 11 weekly changelog (#14651) 2026-05-13 02:57:12 +08:00
Arvin Xu a40fe91fa4 🐛 fix(desktop): detect Windows npm .cmd shims for CLI agents (claude/codex/…) (#14720) 2026-05-13 02:57:12 +08:00
LobeHub Bot ae2afe860a 🌐 chore: translate non-English comments to English in cli-migrate (#14708)
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-13 02:57:12 +08:00
Arvin Xu d3f8f760b2 ⬆️ chore: bump @lobehub/ui to 5.10.5 2026-05-13 02:57:12 +08:00
Arvin Xu 846e648fea 💄 style(review-panel): hover revert button to discard per-file working-tree changes (#14716)
 feat(review-panel): hover revert button to discard per-file working-tree changes

Add a hover-revealed Undo icon to each file row in the Review panel's
unstaged view. Clicking opens a Popconfirm; confirming runs a new
`git.revertGitFile` IPC that restores the file from HEAD (or unstages +
deletes when the path doesn't exist at HEAD, covering staged-add and
untracked entries).

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:12 +08:00
Innei 0007984637 feat(documents): add optimistic create/delete and inline rename for document tree (#14714)
- Insert pending rows immediately on create folder/document, with
  optimistic SWR mutation that rolls back on server error
- Auto-focus rename input on newly created items via onPendingInserted
  callback
- Defer rename commits for pending rows until the server create resolves,
  then rename against the real row id
- Optimistic recursive delete closes the confirm modal instantly, removes
  target + descendants from the tree, and rolls back on failure
- Fix folder path canonicalization in ExplorerTree rename lookup
  (toCanonicalTreePath ensures trailing slash for folders)
- Export getItemPathFromEventPath for composed-path–based item resolution
- Add unit tests for toCanonicalTreePath and ExplorerTree event helpers
2026-05-13 02:57:12 +08:00
Arvin Xu eea742fd5f fix: update Task page placeholder copy (#14704)
* fix: update Task page placeholder copy

* fix: update Task page placeholder copy (en-US)
2026-05-13 02:57:12 +08:00
Innei ca9a781bdd 💄 style: standardize header action icon sizes (#14717)
💄 style: standardize header action icons to DESKTOP_HEADER_ICON_SMALL_SIZE

Unify icon sizing across sidebar and header action buttons by replacing
hardcoded sizes and DESKTOP_HEADER_ICON_SIZE with
DESKTOP_HEADER_ICON_SMALL_SIZE for consistent visual density.

Affected components:
- SideBarHeaderLayout back button
- ToggleLeftPanelButton default size
- BackButton default size
- Agent sidebar header chevron
- InboxButton notification icon
2026-05-13 02:57:12 +08:00
Innei 18b1c25371 feat(devtools): add dev-only feature flag override panel (#14565)
Add a client-side feature flag override panel that lives behind a
floating button in dev builds. Overrides are persisted to localStorage
and merged into useServerConfigStore.featureFlags so existing flag
consumers see the toggled value without any callsite changes.

The panel is gated by NODE_ENV plus a localStorage opt-in
(LOBE_DEV_FEATURE_FLAG_PANEL_ENABLED = "1"); prod builds tree-shake
the entire feature.
2026-05-13 02:57:12 +08:00
Arvin Xu 5ff4590fc1 🐛 fix(builtin-tool-task): expose lobe-task and add setTaskSchedule (#14713)
*  feat(builtin-tool-task): expose lobe-task to users and add schedule config

The task tool is now generally available — flip it from a scenario-only
internal tool to a user-toggleable recommended skill, and let the LLM
configure recurring execution (cron or heartbeat) via createTask / editTask.

- Drop `discoverable: false` + `hidden: true` from TaskManifest registration
- Add `lobe-task` to RECOMMENDED_SKILLS so it stays installed by default
- Remove the USER_HIDDEN_BUILTIN_TOOL_IDS allowlist (only contained lobe-task);
  update selectors and AgentTool to stop filtering it out
- Extend createTask / createTasks / editTask with `automationMode`,
  `schedulePattern`, `scheduleTimezone`, `heartbeatInterval`; editTask also
  accepts `maxExecutions`
- Route schedule columns through taskService.update and maxExecutions through
  taskService.updateConfig (server merges into tasks.config.schedule);
  refresh detail once at the end of editTask

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor(builtin-tool-task): split schedule config into dedicated setTaskSchedule tool

editTask was the wrong place for schedule fields — schedule needs its own
verb so the LLM (and any future human-in-the-loop review) can audit cron /
heartbeat changes separately from generic field edits, and createTask should
stay a pure "make a task" verb without automation knobs.

- Drop automationMode / schedulePattern / scheduleTimezone / heartbeatInterval
  from createTask + createTasks, and drop them plus maxExecutions from editTask
- Add new `setTaskSchedule(identifier, automationMode?, schedulePattern?,
  scheduleTimezone?, heartbeatInterval?, maxExecutions?)` API with its own
  manifest entry, executor method, types, i18n key, and inspector
- Schedule columns still route through taskService.update; maxExecutions still
  routes through taskService.updateConfig (server merges into
  tasks.config.schedule) — same wiring, just moved into the dedicated tool
- Update systemRole to advertise setTaskSchedule + keep editTask description
  clean of schedule mentions

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:12 +08:00
AmAzing- eb924ec881 feat: add service model assignments settings (#14712)
*  Add default agent model setting

* 💄 Refine service model assignments UI

* 💄 Clarify optional service model features
2026-05-13 02:57:12 +08:00
Innei 51cefe0154 🐛 fix(desktop): reset pendingLoginMethod on auth failure/cancel paths (#14695)
* 🐛 fix(desktop): focus onboarding auth success state

* 🐛 fix(desktop): reset pendingLoginMethod on auth failure/cancel paths

Clear pendingLoginMethod in authorizationFailed, authorizationProgress
cancelled, and remoteServerSyncError handlers to prevent users getting
stuck without a Get Started path when a re-auth attempt fails but a
prior authorization is still valid.

* Delete src/routes/(desktop)/desktop-onboarding/features/LoginStep.test.tsx

---------

Co-authored-by: Innei <inbox@innei.in>
2026-05-13 02:57:12 +08:00
Innei cd3716d5e7 ♻️ refactor(spa): use __DEV__ define instead of process.env.NODE_ENV (#14696)
* ♻️ refactor(spa): use __DEV__ define instead of process.env.NODE_ENV

The Vite `__DEV__` define and its global type declaration are already
in place (plugins/vite/sharedRendererConfig.ts, src/types/global.d.ts).
Replace `process.env.NODE_ENV` checks across SPA-only files with the
`__DEV__` boolean so the bundler can statically eliminate dev-only
branches in production builds.

Server-side files (app/, server/, libs/next, libs/trpc, libs/better-auth,
envs, instrumentation) and modules that are also imported by Next.js
SSR pages (e.g. components/Loading/BrandTextLoading) are intentionally
left untouched to avoid runtime `__DEV__ is not defined` errors.

* fix(vitest): define __DEV__ and related constants for test environment

Vitest runs outside the Vite SPA build pipeline, so the __DEV__ define
injected by sharedRendererDefine was not available during tests. This
caused ReferenceError: __DEV__ is not defined in any test file that
transitively imports code using the __DEV__ constant.

Add a  block to vitest.config.mts that mirrors the SPA defines:
- __DEV__: true (test is not production)
- __CI__: mirrors process.env.CI
- __ELECTRON__/__MOBILE__: false (not testing platform-specific code)

* fix: replace missed isDevEnv reference with __DEV__ in AgentMockDevtools
2026-05-13 02:57:12 +08:00
Neko def9acee66 ♻️ refactor(agent-signal,prompts,database,builtin-tool-self-iteration): unified structure of service, unified tool, unified name and concepts (#14699) 2026-05-13 02:57:12 +08:00
Arvin Xu 948e48beba 🐛 fix(utils): cap image binary at 3.75MB so base64 payload stays under Anthropic 5MB limit (#14711)
* 🐛 fix(utils): cap image binary at 3.75MB so base64 payload stays under Anthropic's 5MB limit

Anthropic enforces the 5MB image cap on the base64-encoded payload, not the
binary file. Base64 inflates by ~4/3, so a 4.7MB binary file becomes 6.27MB
once encoded and trips `messages.*.content.*.image.source.base64: image
exceeds 5 MB maximum`. The previous MAX_IMAGE_BYTES of 5MB matched against
file.size, letting these images through compression untouched.

Lower the threshold to floor(5MB * 3/4) ≈ 3.75MB in both the frontend
canvas compressor and the server-side Sharp fallback so the progressive
shrink loop keeps going until the base64 payload is safely under the cap.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(utils): tighten image binary cap to 3MB for extra base64 headroom

Drop MAX_IMAGE_BYTES from 3.75MB (exact 5MB-base64 boundary) to a flat 3MB
so the encoded payload lands around 4MB — clear of any per-provider rounding
or jitter at the 5MB hard limit.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:12 +08:00
Arvin Xu 1ae774d55e 🐛 fix(tasks): scheduler, hotkey, comment & TodoList polish (#14707)
* 🐛 fix(portal): allow TodoList to scroll when expanded content exceeds max-height

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(tasks): route 1–N hotkey to the open submenu instead of defaulting to status

The base-ui SubmenuTrigger doesn't propagate antd's `onTitleMouseEnter`, so
the hover ref in the right-click context menu never updated and every number
press fell back to the status submenu. The standalone Priority/Status tag
dropdowns also showed 1–N hints without binding any handler at all.

- Detect the currently open submenu via `data-popup-open` + a per-submenu
  `data-task-submenu` marker on the icon; numbers are ignored when no
  submenu is open.
- Install a keydown listener on TaskPriorityTag / TaskStatusTag while their
  dropdown is open so the hint numbers actually fire.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(scheduler): keep Continuous unchanged while editing Max runs

Clearing the Max runs input previously emitted maxExecutions=null, which the
form re-interpreted as Continuous and auto-checked the checkbox mid-edit
(disabling the input before the user could type the replacement number).

Track Continuous as its own state derived from the persisted prop. On clear
we hold the input empty locally without touching Continuous or emitting,
and unrelated emits fall back to the persisted value so they can't flip the
checkbox either.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(tasks): always show comment Send button and unify action labels

- Make the Send button visible by default in CommentInput / FeedbackInput
  (greyed out when empty) so the field reads as an input instead of vanishing
  affordance.
- Align topic action menu labels to Title Case (Stop Run / Open Run /
  Copy Topic ID / Copy Operation ID / Copy Link) to match the rest of the
  Action microcopy.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  perf(scheduler): seed SchedulerForm from props once and own state locally

The previous prop→state useEffects re-synced every time the parent prop
updated, which during the async updateSchedule → refreshTaskDetail roundtrip
clobbered the user's in-flight edits with stale store values — felt awful
on rapid changes.

Drop the three sync useEffects and seed local state from props only at
mount via a lazy useState initializer. The form now owns its values
optimistically; cross-task safety comes from `key={taskId}` on the
parent so the form remounts cleanly when switching tasks.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(scheduler): Notion-style timezone picker — drop underscores, offset on the right

Underscored labels like 'America/New_York (EST/EDT, UTC-5/-4)' read poorly in
the dropdown. Split each option into `label` (underscore → space) and `offset`,
and render the row with the city on the left and a subtle gray offset on the
right, in line with how Notion's timezone picker presents this.

IANA `value` keeps the underscore so cron and Drizzle stay happy. Search now
filters by the human label only.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(scheduler): keep zone abbreviations in the timezone offset column

Show 'EST/EDT · UTC−5/−4' instead of just 'UTC−5/−4' so users can recognize
the zone by its common abbreviation alongside the offset.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(scheduler): drop awkward ':30' suffix from hourly summary

'Every hour:00' / 'Every 2 hours:30' read like glitched concatenations. Cron
storage always rounds to 0 or 30 minutes, so call out the non-zero case as
'at half past' and stay implicit on the top of the hour.

- Every hour
- Every hour at half past
- Every 2 hours
- Every 2 hours at half past

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(scheduler): collapse advanced settings by default

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  perf(tasks): coalesce post-write refresh and add timezone search

Two follow-up fixes for the AgentTasks scheduler popover.

##### Optimistic schedule writes, single coalesced refresh

Rapid edits in the scheduler form (toggling daily/hourly/weekly, weekday
chips, time, etc.) each triggered `taskService.update` + a full
`internal_refreshTaskDetail` per call. With overlapping requests the
refreshes returned intermediate server state and bounced TaskTriggerTag /
summary text away from the user's latest choice.

- Add `#withCoalescedRefresh` on the task config slice: it tracks a per-task
  pending-writes count and only fires `internal_refreshTaskDetail` after the
  LAST in-flight write settles.
- Give `updateSchedule` an optimistic `internal_dispatchTaskDetail` so
  external readers see the new pattern/timezone/maxExecutions immediately.
- Route both `updateSchedule` and `setAutomationMode` through the coalescer.

##### Timezone picker — search input at the top

The dropdown had antd's implicit type-into-trigger search, which most users
miss. Add a `SearchBar` inside `dropdownRender`, filter the options against
label/value/offset locally, and show an empty state when nothing matches.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(scheduler): weekday chips only show background when selected

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(tasks): dispatch optimistic schedule under nested 'schedule' field

`TaskDetailData` exposes schedule as `schedule.{pattern,timezone,maxExecutions}`,
not flat columns. The previous optimistic dispatch used the DB-style flat keys,
which broke type-check and would never reach the in-memory selectors.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(tasks): drop Cmd+Backspace shortcut on the Delete menu item

Header dropdown only advertised the hotkey (no handler), and the right-click
context-menu handler is gone too — keeps the visual claim honest and
removes the irreversible-by-keystroke footgun.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  test(agent-signal): pin `now` in proposal activity tests to fixture window

Two cases relied on the real system clock; once today crossed the
fixture's default `expiresAt` (2026-05-12), pending proposals were
classified as expired and the assertions broke.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(tasks): hide '#' placeholder icon for heterogeneous agent topics

Claude Code / Codex topics aren't chat topics in the usual sense, so the
fallback HashIcon in the sidebar row reads as noise. Skip it when the
current agent has a heterogeneousProvider.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🧪 test(tasks): provide agentMap in TopicItem store mock

`isCurrentAgentHeterogeneous` walks through `currentAgentConfig` which
indexes `s.agentMap[agentId]`. Extend the mocked store state to include
an empty `agentMap` so the selector resolves to `undefined` (= not
heterogeneous) instead of throwing.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:12 +08:00
Arvin Xu 94e4ea6712 🐛 fix(cli): remove stale cron entry from generated man page (#14709)
* 🐛 fix(cli): remove stale cron entry from generated man page

The cron command was removed from program.ts but the generated man page
still listed it. Regenerated via bun run man:generate.

* 🔖 chore(cli): release 0.0.15

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:11 +08:00
Arvin Xu bfa28506af 💄 style(tool): add word wrap toggle to tool arguments display (#14706)
 feat(tool): add word wrap toggle to tool arguments display

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:11 +08:00
Rdmclin2 fdedc9697d 🐛 fix: sidebar add agent (#14693)
* fix: sidebar add agent and group error

* feat: add billboard cta
2026-05-13 02:57:11 +08:00
Innei 877052fc1f 💄 style(nav): unify ActionIcon sizing and improve TodoList encapsulation (#14692)
- Extract SIDEBAR_HEADER_ACTION_ICON_SIZE constant for consistent sidebar header ActionIcon sizing
- Pass size prop to ToggleLeftPanelButton
- Simplify Agent selector ActionIcon to use 'small' size preset
- Move layout wrapper styles from Body into TodoList root for better component encapsulation
- Increase Nav gap from 1 to 4 for proper spacing
2026-05-13 02:57:11 +08:00
YuTengjing 4490e3ef76 feat: inline skill auth in recommended task templates (#14676)
*  feat: support refreshing recommended task templates

- Add optional `refreshSeed` through `listDailyRecommend` API, service, and
  client; SWR key includes it so a refresh actually refetches.
- Frontend stores the seed in sessionStorage (via `useSessionStorageState`)
  so a new tab or next day returns to the default daily picks.
- Home Daily Brief shows a "Refresh" affordance on the Recommendations
  subtitle row.
- Fix first-card pinning when matched candidates < RECOMMEND_COUNT: fold
  the fallback pool in so seed reorders the whole batch instead of locking
  position 0 to a single-match template.

Linear: LOBE-8689

*  feat: resolve task-template icon priority

Render the task-template card icon as self > skill provider > interest > Sparkles. Skill icons read required[0] then optional[0], skipping unresolvable providers. URL icons render via @lobehub/ui Image, component icons keep the 28x28 tile.

*  feat: inline skill auth in task template card

Single click "Add task" is now the entire flow: the button stays put, and if a required skill is missing we chain its OAuth popups and create the task automatically. Unauthorized providers (required + optional) appear as compact inline rows above the footer; the provider that already drives the card's main icon is suppressed to avoid duplicating the same logo.

*  feat: add task template detail modal

Open a detail modal when the recommended task template card is clicked,
exposing the full instruction (markdown) plus inline skill auth and the
add-task action. Rename i18n `${id}.prompt` -> `${id}.instruction` to
align with the task table column, and write both `description` and
`instruction` when creating the task. Extract shared `TemplateBriefIcon`,
`useScheduleText`, `useTaskTemplateCreate` and `useVisibleAuthSpecs` so
the card and the modal share the same creation flow and OAuth chaining.

* 🐛 fix: missing Block import in TaskTemplateCard

*  feat: render recommended templates on empty Tasks page

Replace the bare "no tasks" placeholder with a hero landing: greeting,
enlarged inline composer (hero variant), and a 2-column grid of up to
10 recommended task templates. Plumbs a new `count` option through the
service, both routers, the client service, and the recommendations hook
so the home page keeps its 3-card layout while the empty Tasks page
asks for 10.

* 🐛 fix: type cast in resolveTemplateIcon test for unknown interest

* 🌐 i18n: update translations for task template empty-state and other namespaces
2026-05-13 02:57:11 +08:00
Innei 7349ad0f53 🐛 fix: replace ScrollShadow with ScrollArea to fix React #185 infinite render loop (#14689)
Migrate all ScrollShadow usages to ScrollArea (scrollFade) to eliminate
the effect → setState → render → effect cycle that caused React error
#185 (Maximum update depth exceeded) in the scroll overflow hook.

Affected components:
- StreamingMarkdown
- AgentCouncil AutoScrollShadow
- AssistantGroup ContentBlocksScroll
- Conversation Thinking

Fixes lobehub/lobehub#14650
2026-05-13 02:57:11 +08:00
LiJian 744059c1bc 🐛 fix(heteroFinish): trigger task lifecycle on cloud sandbox agent completion (#14681)
* 🐛 fix(heteroFinish): trigger task lifecycle transition on sandbox agent completion

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* 🐛 fix(heteroFinish): guard onTopicComplete against duplicate finish calls

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-13 02:57:11 +08:00
LiJian aa4533e6cb 📝 docs(cloudHeteroContext): add sandbox persistence & gh push rules (#14682)
* 📝 docs(cloudHeteroContext): add sandbox persistence & gh push rules

Inject ephemeral-sandbox warnings and mandatory GitHub push rules into
the cloud CC context block so every Claude Code run knows:
- The sandbox is wiped after inactivity — local changes will be lost
- All code changes must be committed and pushed before task is complete
- Use gh CLI (pre-authenticated) for GitHub operations

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* 🐛 fix(cloudHeteroContext): address review comments on sandbox persistence rules

- Remove gh push guidance (gh has no push subcommand; git push is correct)
- Gate gh-auth instructions behind githubToken availability to avoid
  auth-dependent commands failing in no-token sandbox runs

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* 📝 docs(cloudHeteroContext): add git push auth fallback guidance

Tell CC that the sandbox has git credentials ready, but if git push
fails it can self-recover via:
1. gh auth setup-git (reconfigures git credential helper)
2. inline token URL as last resort (oauth2:$GITHUB_TOKEN@github.com)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-13 02:57:11 +08:00
YuTengjing ea1d926de4 📝 docs(skills): frontmatter cleanup + argument-hint (#14683)
* 🔨 chore: control skill triggering via frontmatter flags

- Rename debug skill to debug-package (avoid confusion with debugging workflows)
- Add disable-model-invocation to add-* skills so they are manual-only
- Add user-invocable: false to reference/architecture skills so they auto-load only when relevant

* 🔨 chore: rename skill reference dirs to plural references

Align with the skill-creator convention (scripts/, references/, assets/).

* 📝 docs(skills): split oversized SKILL.md files and refine triggers

- upstash-workflow: 1126L → 189L, extract implementation / best-practices / examples references
- data-fetching: 854L → 613L, move parent-keyed-map walkthrough to references
- store-data-structures: 625L → 314L, extract types and reducer references
- upstash-workflow/cloud.md, version-release/release-notes-style.md: add TOCs
- linear: rewrite ALL-CAPS MUSTs into prose explaining why; mark user-invocable: false
- version-release: mark disable-model-invocation: true (manual /version-release only)
- debug-package: expand description with concrete trigger phrases and tokens

* 📝 docs(skills): regularize microcopy structure

Move language-specific guidelines into references/zh.md and references/en.md
so SKILL.md can point to them via the standard progressive-disclosure pattern.
Previously the two files sat next to SKILL.md but were not referenced anywhere,
making them invisible to Claude Code loading.

* 📝 docs(skills): move builtin-tool refs into references subdir

Aligns builtin-tool with the references/ layout used elsewhere
(microcopy, store-data-structures). 3 md files move, SKILL.md
links updated.

* 📝 docs(skills): broaden trigger descriptions for core skills

Adds concrete API names, file paths and natural-language phrases so
auto-triggering catches more relevant prompts. Touches zustand,
drizzle, i18n, react, typescript, modal, hotkey.

* 📝 docs(skills): add argument-hint to user-only skills
2026-05-13 02:57:11 +08:00
𝑾𝒖𝒙𝒉 dfe19323b8 🐛 fix(hotkey): remove redundant onClear to prevent double updateHotkey calls (#14663)
Previously, clicking the clear button on HotkeyInput triggered both
`onClear` and `onChange` (since HotkeyInput internally calls
`setHotkeyValue('')` which fires `onChange`). This caused two
concurrent requests to `updateDesktopHotkey` and showed two toast
messages (success/error) for a single user action.

Fix: remove the redundant `onClear` prop. HotkeyInput's clear action
already fires `onChange('')`, so the single `onChange` handler is
sufficient.

Co-authored-by: Innei <i@innei.in>
2026-05-13 02:57:10 +08:00
Innei 0e58fa7126 ♻️ refactor(web-onboarding): merge agent-marketplace identifier into onboarding tool (#14672)
* ♻️ refactor(web-onboarding): merge agent-marketplace identifier into onboarding tool

Drop the standalone `lobe-agent-marketplace` builtin tool and fold its
`showAgentMarketplace` / `submitAgentPick` APIs into `lobe-web-onboarding`
so onboarding exposes a single tool identifier.

- Move marketplace API entries (with humanIntervention/renderDisplayControl)
  into WebOnboardingManifest; extend WebOnboardingApiName.
- Compose AgentMarketplaceExecutionRuntime inside WebOnboardingExecutionRuntime;
  the client WebOnboardingExecutor now owns showAgentMarketplace/submitAgentPick
  with telemetry hooks. Drop the separate client/server executor + runtime files.
- Merge marketplace Inspector / Intervention / Render maps under the
  web-onboarding identifier. Remove AgentMarketplace* entries from
  builtin-tools registries and from the builtin web-onboarding agent's
  plugins list.
- Switch customInteractionHandlers to route by (identifier, apiName) so
  the marketplace picker handler fires only on `showAgentMarketplace`.
- Drop the `lobe-agent-marketplace` fallback string in
  OnboardingActionHintInjector; match by apiName only.
- Rename plugin/setting locale keys under `lobe-web-onboarding.*`.

* 🐛 fix(onboarding): reserve scroll headroom for agent marketplace overlay

- Add a footerSlot spacer in ChatList matching the marketplace panel height so the latest message can be scrolled into view above the absolute overlay.
- Nudge the marketplace overlay inset by 2px to hide subpixel border seams.
- Document turn output order in the onboarding system role to avoid trailing filler text after tool calls.
2026-05-13 02:57:10 +08:00
YuTengjing b79c5d8e70 🐛 fix: reject inactive OIDC access (#14674)
* 🐛 fix: reject inactive OIDC access

* 🐛 fix: honor expired OIDC bans

* 🐛 fix: decouple OIDC inactive error from tRPC

*  test: fix OIDC auth type checks
2026-05-13 02:57:10 +08:00
Arvin Xu f591f7ac34 💄 style(web-onboarding): add Render for saveUserQuestion & showAgentMarketplace (#14667)
 feat(builtin-tool-web-onboarding): add Render for saveUserQuestion + showAgentMarketplace

Tool messages for `saveUserQuestion` and `showAgentMarketplace` previously
fell back to the raw Arguments/Response table once the call resolved
because neither API had a Render registered. Wire both up:

- `saveUserQuestion`: new Render mirroring the Intervention's detail-card
  style — agent identity (emoji + name), full name, and interests chips —
  rendered conditionally per the fields actually saved.
- `showAgentMarketplace`: reuse the existing `SubmitAgentPick` Render.
  After the picker submits, `customInteractionHandlers` rewrites the
  `showAgentMarketplace` tool message's `pluginState` to the same
  `{ summaries, installedAgentIds, ... }` shape, so the card grid
  renders without a new component.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:10 +08:00
Arvin Xu 3f43e69fa6 ♻️ refactor(knowledge-base): share RAG runtime across client/server via KnowledgeBaseSearchService (#14673)
* ♻️ refactor(knowledge-base): share runtime across client/server via KnowledgeBaseSearchService

Extract a server-side `KnowledgeBaseSearchService` (semanticSearchForChat
fan-out + getFileContents branching + groupAndRankFiles) so both the lambda
chunk router and the builtin tool server runtime orchestrate RAG through one
implementation. Wire the builtin knowledge-base tool to the shared
ExecutionRuntime in the package by moving the client executor to
`src/client/executor/` and registering a thin server runtime factory.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor(knowledge-base): move PG 23505 handling into adapters, restore executor path

ExecutionRuntime is dual-end so it cannot detect PG error codes — only the
server adapter can. Move the unique-constraint check there and translate the
lambda router's `FILE_ALREADY_IN_KNOWLEDGE_BASE` sentinel in the client
adapter, so the runtime's generic catch surfaces the human-readable message
on both code paths. Restore `src/executor/` as a top-level sibling of
`src/client/` to match the convention of every other builtin tool.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor(knowledge-base): collapse executor into /client, drop ./executor export

The executor is just another client-only adapter (alongside Inspector and
Render) — no reason for it to sit at the package root with a dedicated
subpath. Move it under `src/client/executor/`, re-export from
`src/client/index.ts`, drop the `./executor` entry from package.json, and
update the consumer to import from `@lobechat/builtin-tool-knowledge-base/client`.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  test(knowledge-base): cover KnowledgeBaseSearchService

13 unit tests across both methods:
- getFileContents: docs_* direct read, missing doc, file_* via findByFileId,
  parseFile fallback, parse failure surfaces as error entry, missing file,
  mixed batch.
- semanticSearchForChat: chunk grouping + relevance ranking, BM25 skip when
  no knowledgeIds, knowledgeIds → fileIds expansion, vector/BM25 isolated
  failure capture (preserves the other path's results + structured
  rejections), full failure path.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:10 +08:00
Arvin Xu 314619d798 ♻️ refactor(bot): close activator bypass + converge device-access checks (#14664)
* ♻️ refactor(aiAgent): introduce deviceToolRegistry as single source of truth

Centralise "what counts as a device tool" into one module so the next
device-tool addition only touches one file. Removes the hardcoded
`new Set(['local-system', 'remote-device'])` from `deviceToolAudit.ts`,
which had drifted from `LocalSystemManifest.identifier` /
`RemoteDeviceManifest.identifier` imports elsewhere.

Foundation for the LOBE-8768 activator-bypass fix landing next.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(aiAgent): block activator from bypassing canUseDevice gate

External bot senders could still reach the owner's machine by having the
LLM call `lobe-activator.activateTools(["lobe-remote-device"])`, because
`enableCheckerFactory.allowExplicitActivation` short-circuits before the
canUseDevice rule, and the engine's `manifestSchemas` always contained
the full builtin list (LOBE-8768 B1).

Fix by filtering builtin manifests **physically** through
`buildAllowedBuiltinTools` at both feed-points (ToolsEngine input and
the activator-discovery `toolManifestMap`). When `canUseDevice=false`,
the device manifests no longer exist in either map, so explicit
activation cannot resolve them — the rule-layer gate becomes
defense-in-depth instead of the sole barrier.

Validates with the prod incident's repro path: an external sender's
`<available_tools>` no longer advertises `lobe-remote-device`, and an
activator call to enable it returns "not found".

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor(bot,messenger): centralise isOwner derivation in buildBotContext

The same fail-closed expression
`!!operatorUserId && senderExternalUserId === operatorUserId` was
duplicated across `BotMessageRouter.onNewMention`, `.onSubscribedMessage`,
the DM catch-all, and `MessengerRouter.dispatchToAgent` — four sites,
one rule, one place to silently regress.

Route all four through `buildBotContext`. The helper now owns the
fail-closed contract referenced by `ChatTopicBotContext.isOwner`'s
docstring, so adding the next platform/router can't accidentally
default to "trusted when in doubt".

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(aiAgent): apply device filter post-merge across all manifest sources

The previous fix only filtered the `builtinTools` source. An installed
plugin or a Skill/Klavis manifest declaring
`identifier: 'lobe-remote-device'` would still survive in
`manifestSchemas` and reach `toolManifestMap` via either
`getEnabledPluginManifests` or the direct ingest loops in
`aiAgent/index.ts` — letting an external bot sender activate the device
identifier through the activator.

Two changes close the gap:

  1. `ServerAgentToolsEngineConfig.excludeIdentifiers` — applied **after**
     combining plugin + builtin + additional manifests in
     `createServerToolsEngine`. `createServerAgentToolsEngine` passes
     `DEVICE_TOOL_IDENTIFIERS` whenever `canUseDevice` is false.

  2. `isManifestIngestAllowed` in `aiAgent.execAgent` — a single
     identifier guard reused at every `toolManifestMap` / `toolSourceMap`
     write (engine-returned plugin manifests, lobehub-skill loop,
     klavis loop). New ingest points inherit the wall automatically.

New test pins the regression: a plugin + an additional manifest
spoofing the device identifiers are dropped from `availablePlugins`
when `excludeIdentifiers` is set.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:10 +08:00
Arvin Xu d9fe275a4c ♻️ refactor(task): snapshot agent model into task.config at create time (#14670)
*  feat(task): snapshot agent model into task.config at create time

Pin the assignee agent's current model/provider into task.config when a
task is created so later changes to the agent's default model don't
silently affect already-created tasks. On first run, backfill the
snapshot for tasks created before this change.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(task-runner): fall back to inbox agent when task has no assignee

`TaskRunnerService.runTask` previously threw `BAD_REQUEST` for any task
without `assigneeAgentId`, which broke runs created without `--agent`.
Resolve and persist the user's built-in inbox agent instead, surfacing
an `INTERNAL_SERVER_ERROR` only if that resolution itself fails.

Picked from #14671 (closes once landed).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor(task): collapse router orchestration into TaskService

Move multi-step task verbs out of the TRPC router into `TaskService`:
`createTask`, `cancelTopic`, `deleteTopic`, `runReview`, `updateStatus`,
`previewSubtaskLayers`, `runReadySubtasks`. The router keeps only input
validation + error wrapping; the tool runtime now shares the same
`createTask` path (was duplicating the model snapshot + parent
resolution).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🚨 ci: fix tsgo errors from TaskService extraction

`runReadySubtasks` router was rebuilding the `data` payload via a
conditional spread, which forced TS to infer a discriminated union that
broke `result.data.skipped` access in the integration test. Pass the
service result straight through so `skipped` stays a single optional
field. Also cast the stubbed `taskService` in the tool runtime unit
tests to bypass strict structural typing — same pattern the other
dep stubs already use.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:10 +08:00
YuTengjing 03b3e2fc12 🔥 chore: drop task template tracking (#14666)
* 🔥 chore: drop task template tracking

The recommendation surface is about to be redesigned, so the analytics
funnel added in #14517 is being removed up front. A fresh tracking
schema will land alongside the redesigned UI.

- Delete `analytics.ts` plus its test and the tracking-focused
  `TaskTemplateCard.test.tsx`.
- Drop `RecommendedTaskTemplate` / `TaskTemplateRecommendationSource` /
  `TaskTemplateFallbackPool` and revert the service to plain
  `TaskTemplate[]`.
- Strip impression, dismiss, create-clicked/result and
  skill-connect-clicked/result calls from `TaskTemplateCard.tsx`, while
  keeping the createTask + navigate-to-task flow from #14540.
- Remove `recommendationBatchId` / `userInterestCount` / `onCreated`
  plumbing from `useDailyBriefRecommendationsUI`,
  `DailyBriefRecommendationsView`, and the card props.
- Revert `useSkillConnection` to the pre-tracking variant (no
  onConnectResult / SkillConnectionResult).

* 🐛 fix: remove created template from recommendation cache

After #14540 changed the create-task flow to auto-navigate to
`/task/{id}`, removing the `onCreated` plumbing from #14517 in the same
sweep meant the SWR recommendation cache was never mutated on success.
Combined with the server-side `recordCreated` being a no-op and
`listDailyRecommend` not excluding created IDs, returning to Home
showed the same recommendation as actionable again — letting users
trigger duplicate scheduled tasks from the same template.

Re-add the minimal cache-eviction plumbing (no analytics):

- TaskTemplateCard exposes `onCreated` and calls it on success
- useDailyBriefRecommendationsUI shares `removeTemplateFromList` for
  both dismiss and created flows
- DailyBriefRecommendationsView passes `onCreated` through
2026-05-13 02:57:10 +08:00
YuTengjing b0ee35dd35 🐛 fix: drop unreachable aihubmix empty-apiKey test (#14669)
* 🐛 fix: drop unreachable aihubmix empty-apiKey test

The `should return empty array when API key is missing` test asserts a
contract that doesn't hold: RouterRuntime.models() constructs the
underlying runtime via the OpenAI-compatible factory before calling
modelsOption, and the factory throws InvalidProviderAPIKey on empty
apiKey at construction time — so aihubmix's own `if (!apiKey) return []`
short-circuit can never actually fire.

Just delete the dead test. The defensive guard in aihubmix's modelsOption
stays as intent documentation. Also tighten an implicit-any in the
adjacent `should normalize model_id field to id` test.

* 🔥 chore: drop dead empty-apiKey guard in aihubmix modelsOption

* 💄 style: tighten aihubmix apiKey assertion to string
2026-05-13 02:57:10 +08:00
Zhijie He a1fac45b3a 💄 style: add reasoning_effort support for Grok 4.3 (#14642)
* style: add reasoning_effort for Grok 4.3

* style: remove grok 4.1 series & grok-imagine-image-pro (Model retirement)

style: remove grok 4.1 series & grok-imagine-image-pro (Model retirement)

style: remove grok 4.1 series & grok-imagine-image-pro (Model retirement)
2026-05-13 02:57:10 +08:00
Arvin Xu e0ead0c47a 💄 style: increase chat topic title length (#14659)
* 💄 style: increase chat topic title length

- bump initial topic title slice from 20 to 40 chars
- bump dev fallback slice from 30 to 40 chars
- bump thread title slice from 20 to 40 chars
- raise LLM summary title prompt limit from 50/10w to 80/15w

* 💄 style: bump topic/thread title slice from 40 to 80 chars

Align slice limits with the LLM summary prompt cap (80 chars) so the
initial visible title is no shorter than what the summarizer can return.
2026-05-13 02:57:10 +08:00
Bianzinan f4de472e82 fix(aihubmix): use full models endpoint to return complete model list (#14511)
* fix(aihubmix): use full models endpoint to return complete model list

The /v1/models endpoint at api.aihubmix.com returns only per-user-group
models (~256). The new endpoint at aihubmix.com/api/v1/models returns
the complete catalog (800+). Fetch from the full endpoint directly.

* fix(aihubmix): normalize model_id to id from full models endpoint

The https://aihubmix.com/api/v1/models endpoint uses `model_id` instead
of `id`. Map it to `id` before passing to processMultiProviderModelList
to prevent toLowerCase() errors and empty model list.

* fix(aihubmix): add apiKey guard, AbortController timeout, and better error messages

- Extract apiKey with runtime guard to fail fast when key is missing
- Add AbortController with 10s timeout to prevent indefinite hanging
- Include response body in error message for easier debugging
- Add APP-Code header comment pointing to docs
- Expand tests: mock global fetch, cover missing key / HTTP error / network error / AbortError cases

* fix(aihubmix): add field mapping adapter and fix timeout scope

Address review feedback from #14511:

- Update AiHubMixModelCard interface to reflect the new endpoint schema
  with full JSDoc (model_id, desc, types, features, input_modalities,
  context_length, max_output, pricing.cache_read/cache_write)
- Add mapAiHubMixModel() to adapt API response fields to LobeHub model
  card fields before passing to processMultiProviderModelList:
    desc             -> description
    model_name       -> displayName
    context_length   -> contextWindowTokens
    max_output       -> maxOutput
    types            -> type  (llm/t2t->chat, image_generation/t2i->image,
                               video/t2v->video, tts, stt, embedding,
                               rerank/reranking->rerank)
    pricing.cache_read  -> pricing.cachedInput
    pricing.cache_write -> pricing.writeCacheInput
    features(tools/function_calling) -> functionCall
    features(thinking)               -> reasoning
    features(web)                    -> search
    input_modalities(image)          -> vision
- Fix timeout scope: move clearTimeout into the finally block so the
  AbortController stays active during response.json() body read, not
  just during the initial fetch() call
- Update baseURL from https://api.aihubmix.com to https://aihubmix.com
  to match official integration docs (https://docs.aihubmix.com/cn/api/Aihubmix-Integration)
- Strengthen normalize test: assert list.some(m => m.id === 'some-model')
  instead of just Array.isArray to detect normalization failures
- Add field-mapping test using vi.spyOn on processMultiProviderModelList
  to assert that all adapted fields are passed correctly

* fix(aihubmix): filter out unsupported rerank types to prevent chat fallback

- Remove rerank/reranking from TYPE_MAP; they have no LobeHub AiModelType
  equivalent and would silently fall back to 'chat' in processModelCard
- Add UNSUPPORTED_AIHUBMIX_TYPES set and filter before mapAiHubMixModel()
- Add regression test asserting rerank/reranking models are excluded and
  llm models still pass through

---------

Co-authored-by: Bianzinan <bianzinan@users.noreply.github.com>
2026-05-13 02:57:10 +08:00
Innei 5f14b7e463 feat(activator): require activation reason (#14597) 2026-05-13 02:57:09 +08:00
Innei a9eb904cf4 🐛 fix(onboarding): skip marketplace on early exit, drop CJK in prompts (#14598)
* 🐛 fix(onboarding): skip marketplace on early exit, drop CJK examples in prompts

Honor the user's wish to leave: when the onboarding agent detects a true
early-exit signal in any phase, persist what is known, send a brief
farewell, and call finishOnboarding directly. The marketplace handoff is
mandatory only on normal Phase 4 / Summary completion. Previously the
spec forced the agent to invent categoryHints from environment cues
when discovery was thin, producing noisy recommendations for users who
explicitly asked to stop.

- Replace systemRole §Early Exit with a 4-step flow (no marketplace, no
  summary), and remove the trailing "respect their time" rationale that
  contradicted the new policy.
- Update toolSystemRole turn-protocol exception accordingly; mark
  persistence as best-effort (do not retry on failure) since the
  Pre-Finish Checklist is overridden on early exit.
- Update OnboardingActionHintInjector L101/L127 hints to match the new
  flow, and append an EXCEPTION clause to the Summary not-opened hint
  so a true exit signal in Summary skips the marketplace too.
- Strip CJK example phrases from prompt text; rely on the LLM's
  multilingual recognition with "equivalents in any language" hints.

* 🔨 refactor(FollowUpChips): remove unused consume function and reset editor state on chip click
🔨 style(InterventionBar): remove overflow hidden from container style

Signed-off-by: Innei <tukon479@gmail.com>

* 🐛 fix(ci): align FollowUpChips test with removed consume and increase timeout for PGlite cold-start

---------

Signed-off-by: Innei <tukon479@gmail.com>
2026-05-13 02:57:09 +08:00
Neko 1374fd29e8 feat(agent-signal,server,prompts): consolidate in self-review implemented (#14657) 2026-05-13 02:57:09 +08:00
Arvin Xu 31e9130cf0 💄 style(hetero-agent): read-only SubAgent threads with breadcrumb header and thread switcher (#14658)
*  feat(hetero-agent): read-only SubAgent threads with breadcrumb header and thread switcher

- Hide chat input on SubAgent threads (execution is driven by the parent agent) and replace it with an inline read-only hint
- Render the hint as the last item inside the virtual list so it scrolls with messages instead of being pinned to the viewport bottom
- ChatList exposes a new `footerSlot` prop that VirtualizedList injects as a synthetic trailing data item
- Header now shows `topic / thread` breadcrumb; thread title is a popover trigger that lists sibling threads in the same topic for one-click switching
- Hide the working-directory tag while inside a thread — directory switching doesn't belong in this read-only view
- Unify user-facing strings to "SubAgent" (badge, hint, open/close labels)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(chat-input): soften queue tray preview borders

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(conversation): scrollToBottom lands on the true last VList item

scrollToBottom targeted displayMessages.length - 1, which leaves any
trailing synthetic items (spacer, SubAgent footer hint) below the
viewport. In SubAgent threads this kept atBottom = false after the
BackBottom click or auto-scroll, so the button appeared stuck.

VirtuaScrollMethods now exposes getTotalCount, which VirtualizedList
fills from the live data length (messages + spacer + optional
footerSlot) via a ref. scrollToBottom uses that to scroll to the real
last index.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:09 +08:00
Arvin Xu 84b802cf96 💄 style(chat-input): show skeleton in action bar while config is loading (#14656)
* 💄 style(chat-input): show skeleton in action bar while config is loading

Before agent / group config hydrates, action buttons read DEFAULT_*
fallbacks and the send button would dispatch against a not-yet-ready
target. Add an `isConfigLoading` prop on DesktopChatInput that swaps the
action bar + send area for skeleton placeholders. The chat page passes
`agentSelectors.isAgentConfigLoading`, group chat passes
`agentGroupSelectors.isGroupsInit`. The editor itself stays usable so
users can start typing immediately.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(home,i18n): use 已阅 for brief confirm/confirmDone in zh-CN

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(home): use 确认完成 for brief.action.confirmDone in zh-CN

confirmDone signals the terminal transition (task marked complete),
not just dismissing the brief, so 已阅 loses the semantic distinction
from `confirm`. Use 确认完成 to match the EN intent ("Confirm complete").

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(home): use "Confirm complete" for brief.action.confirmDone in en-US

Match the semantic distinction the call site relies on:
`confirm` is dismiss-only for recurring scheduled runs, while
`confirmDone` marks the terminal completion transition. The test
mock already used "Confirm complete" — align the source defaults.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:09 +08:00
Arvin Xu e261a6ff98 💄 style(home): add Recommendations module with hetero agent action library (#14645)
*  feat(home): add Recommendations module with hetero agent action library

Introduce a `Recommendations` section that renders above the existing daily-brief
task templates. The module is driven by an extensible action registry with per-action
eligibility checks; the first registered actions surface "Add Claude Code agent" and
"Add Codex agent" cards on desktop when the matching local CLI is detected and the
user hasn't added that hetero agent yet.

- New `src/features/Recommendations/` with action types, registry, hetero-agent
  factory, eligibility hook, parallel CLI detection (SWR-cached) and card UI.
- Extract `createHeterogeneousAgent` from `useCreateMenuItems` into a shared
  `useCreateHeteroAgent` hook so the sidebar menu and Recommendations card share
  one creation path (create + refresh sidebar + navigate to chat).
- `DailyBrief` now renders `<Recommendations />` in place of the standalone
  template-only section; visibility is driven by the new
  `useRecommendationsVisible` hook.
- Add `recommendations.*` i18n keys to the `home` namespace (default + zh-CN +
  en-US dev preview).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(home): polish Recommendations card with brand avatar and tighter copy

Use brand Avatar icons with rounded square shape, drop the duplicate title, and tighten copy (Coding Agent tag, Add Agent CTA).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:09 +08:00
Rdmclin2 3fb8daaa08 🔨 chore: optimize system bot (#14649)
* feat: add already consumed alert

* feat: support slack send slack commends  emphemeral in channel

* chore: handle parse commands imperial

* fix: slack messenger callback ok

* feat: add messager connectionId per user

* fix: add userId to webhookbody

* fix: test case
2026-05-13 02:57:09 +08:00
Arvin Xu 49c3d7e367 feat(hetero-agent): support AskUserQuestion tools for claude code (#14639)
*  feat(hetero-agent): AskUserQuestion MCP server + bridge skeleton (LOBE-8725 step 1+2)

Foundation for LOBE-8725 — interactive AskUserQuestion via local MCP. CC's
built-in tool short-circuits in `-p` mode, so we host an in-process MCP
server that exposes an equivalent `ask_user_question` tool. The handler
blocks until the consumer submits an answer (or the 5min deadline / op
shutdown fires), surfacing a structured `agent_intervention_request` /
`agent_intervention_response` round-trip on the existing event stream.

Added in this commit:

- `packages/heterogeneous-agents/src/askUser/`
  - `AskUserBridge` — per-op pending map with timeout / cancel / progress
    keepalive support; emits an async-iterable of outbound events
  - `AskUserMcpServer` — process-wide HTTP/Streamable MCP server,
    `?op=<id>` query routes via `AsyncLocalStorage` →
    `onsessioninitialized` → sessionId↔opId map; tool handler hands off
    to the matching bridge and pumps `notifications/progress` back to CC
    every 30s as wire-level keepalive (required for >5min waits, see
    spike notes)
  - `constants.ts` — shared tool/server names + the stable `apiName`
    the adapter rewrites to
  - Unit tests cover bridge lifecycle (resolve / cancel / timeout /
    progress / event stream) and an end-to-end MCP probe via
    `StreamableHTTPClientTransport`

- `packages/agent-gateway-client/src/types.ts` — wire-level
  `agent_intervention_request` / `agent_intervention_response` event
  variants + payload interfaces. Re-exported through the package barrel.

- `packages/heterogeneous-agents/src/adapters/claudeCode.ts` — when CC's
  `tool_use` carries `mcp__lobe_cc__ask_user_question`, the adapter
  rewrites `apiName` to `askUserQuestion` so the renderer routes on a
  clean domain key. Identifier stays `claude-code`. Applied to both the
  main-agent and subagent paths for symmetry (subagent ask isn't
  expected today, but doesn't hurt).

- `src/server/routers/lambda/aiAgent.ts` — Zod input schema for
  `aiAgent.heteroIngest` extended with the two new event types so the
  CLI sandbox can forward them through the server.

No producer wiring yet — Steps 3-5 plug this into Electron main, the
renderer executor, and the new UI.

*  feat(hetero-agent): wire AskUserQuestion MCP into Electron CC driver (LOBE-8725 step 3)

Plug the Step 1 skeleton (`AskUserMcpServer` + `AskUserBridge`) into the
desktop Claude Code spawn path. CC's local MCP `ask_user_question` tool now
goes live during real prompts; renderer-submitted answers route back via
new IPC.

Changes
- `apps/desktop/src/main/modules/heterogeneousAgent/types.ts` — add
  optional `mcpConfigPath` to `HeterogeneousAgentBuildPlanParams` so
  controller-managed temp configs flow into the driver.
- `apps/desktop/src/main/modules/heterogeneousAgent/drivers/claudeCode.ts`
  — append `--mcp-config <path>` when provided. Disallowed-tools pin
  stays so CC's built-in AskUserQuestion remains off (avoids double-
  registration of the same tool name).
- `apps/desktop/src/main/controllers/HeterogeneousAgentCtr.ts`
  - Lazy-singleton `AskUserMcpServer` started on first claude-code prompt
    (de-duped concurrent first-callers via in-flight promise).
  - Per-op `setupInterventionForOp(opId, sessionId)`: registers an
    `AskUserBridge`, writes `os.tmpdir()/lobe-cc-mcp-<opId>.json` with
    `alwaysLoad: true` so CC eager-loads the tool (1-hop call, no
    ToolSearch detour — see LOBE-8725 spike), pumps `bridge.events()`
    into the existing `heteroAgentEvent` broadcast.
  - Cleanup paths: exit handler `await intervention.cleanup()` settles
    pending MCP handlers + unlinks the temp config; pre-spawn errors
    short-circuit the same cleanup so we don't leak bridges on
    `buildSpawnPlan` / trace-session failures.
  - `before-quit` stops the MCP server (in addition to killing CC
    processes).
  - New `@IpcMethod() submitIntervention({ operationId, toolCallId,
    result?, cancelled?, cancelReason? })` — renderer side will dispatch
    answers / cancellations through this in Step 4/5.
  - codex unchanged — bridge setup is gated on `agentType === 'claude-code'`.
- `src/services/electron/heterogeneousAgent.ts` — renderer-side proxy
  for `submitIntervention`.
- New `claudeCode.test.ts` covers the four driver-arg paths
  (`--mcp-config` presence, ordering vs `--resume`, AskUserQuestion stay
  disallowed). Existing 28 controller tests still pass.

What still doesn't run end-to-end
- The renderer `heteroExecutor` doesn't consume `agent_intervention_request`
  yet — events go through the broadcast but the chat store ignores them.
- No UI to render the intervention card or to call `submitIntervention`.
Both lands in Steps 4/5 next.

*  feat(hetero-agent): correlate intervention with tool message + renderer handler (LOBE-8725 step 3.5+4)

Bridge now uses the caller-supplied toolCallId (CC's `claudecode/toolUseId`
from MCP `_meta`) instead of a random UUID, so the
`agent_intervention_request` event references the same id as the existing
tool message on the renderer side.

Renderer-side `heteroExecutor` learns the new event:

- Added `persistInterventionRequest(...)` next to `persistToolResult` —
  stamps `pluginState.askUserQuestion` (apiName + identifier + questions
  parsed from `arguments` + deadline + status='pending' + toolCallId)
  onto the matching tool message via `messageService.updateToolMessage`.
- New branch in `handleStreamEvent` for `'agent_intervention_request'`:
  defers behind `persistQueue` (so it lands AFTER `persistToolBatch`
  populates `toolMsgIdByCallId`), then mirrors the same pluginState onto
  the in-memory message via `internal_dispatchMessage` so the UI lights
  up immediately — no fetchAndReplaceMessages round-trip needed.
- The eventual `tool_result` for the same toolCallId hits the existing
  `tool_result` branch unchanged: it overwrites `pluginState` with
  whatever the result carries (typically undefined for our MCP tool, so
  `pluginState.askUserQuestion` clears and the intervention UI yields to
  the regular Render).

Bridge tests cover the new contract:
- caller-supplied toolCallId becomes the wire correlation key
- duplicate-toolCallId pendings reject loudly so two-handler clobbers
  surface immediately

153 package tests + 1167 desktop main tests + 51 hetero executor tests
still green; type-check clean.

*  feat(claude-code): AskUserQuestion intervention render component (LOBE-8725 step 5)

Dedicated Render for the synthetic `askUserQuestion` apiName the adapter
rewrites the local MCP `mcp__lobe_cc__ask_user_question` tool to. Lives
under CC's render registry so the existing chat tool-detail flow picks
it up automatically — no changes to the conversation framework.

- New `AskUserQuestionItem` / `AskUserQuestionArgs` /
  `AskUserQuestionPluginState` types (mirrors CC's own
  AskUserQuestion schema verbatim).
- `ClaudeCodeApiName` gains an `AskUserQuestion = 'askUserQuestion'`
  member so the renders / inspectors / streamings registries can key
  off the same enum value.
- `client/Render/AskUserQuestion/index.tsx` is the component:
  - `pluginState.askUserQuestion?.status === 'pending'` → renders the
    questions form (Select for single-select, CheckboxGroup for
    multi-select), a 5-min countdown ticking once a second, Submit /
    Skip buttons. Reads `operationId` via `messageOperationMap` so we
    can route through `heterogeneousAgentService.submitIntervention`.
  - Otherwise → renders the questions as muted captions plus the
    final answer text from `content`. Surfaces a warning when the
    tool_result was an error (timeout / cancelled / session ended).
  - Submit button stays disabled until every question has a
    selection; Skip always enabled (sends `cancelled: true`).
- `ClaudeCodeRenders[ClaudeCodeApiName.AskUserQuestion]` registers
  the new component.

What this does NOT do
- Doesn't touch `BuiltinToolInterventions` — the form is rendered
  inside the regular tool body (Render slot), not the canonical
  intervention slot. Cleanest for now: the framework intervention
  flow assumes `submitToolInteraction` store actions, which would
  fight our IPC path. We can refactor onto that surface later if
  CC grows additional interactions (approval, file picker).
- Doesn't translate strings — i18n in a follow-up.

Type-check clean. Step 6 (real desktop e2e via CC) is next.

*  feat(claude-code): render AskUserQuestion form during pending state (LOBE-8725 step 5 follow-up)

Step 5 registered the Render component but stopped at the registry — the
chat tool-detail still returned the loading placeholder while
`isToolCalling` was true, so users only ever saw a spinner during the 5
min intervention window.

Detect `pluginState.askUserQuestion?.status === 'pending'` (only set on
CC + apiName=askUserQuestion tool messages) and route to the registered
builtin Render inline before the placeholder branch. Once the
intervention resolves, the eventual `tool_result` clears
`pluginState.askUserQuestion` and the regular Render takes over.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  feat(hetero-agent): wire regenerate / continue for hetero runtime (LOBE-8519 follow-up)

LOBE-8519 left two TODOs in `generationSlice` where hetero runtime
silently fell through to client mode — regenerate would secretly hit the
agent's underlying LLM, and continue would synthesize a fake "please
continue" turn that confuses CC / Codex.

- regenerateMessage: re-create the assistant row branched off the same
  user message, resolve resume sessionId (drop on cwd mismatch), then
  spawn a child `execHeterogeneousAgent` op so Stop only kills the
  executor, not the parent regenerate op. Mirrors sendMessage's hetero
  branch.
- continueGenerationMessage: hetero CLIs have no continue primitive —
  each prompt is a fresh user turn — so bail out instead of polluting
  the session.
- continueGenerationMessage: gateway mode now branches a server-side
  resume run instead of falling through to client.

Surfaced while testing CC AskUserQuestion end-to-end on the
LOBE-8725 branch (regenerating after an answered question went through
the wrong runtime).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(local-testing): electron-dev.sh boots on macOS bash 3.2

Two bugs surfaced when invoking the local-testing helper from a fresh
session on macOS:

- `find_project_pids` / `do_stop` end with `grep -v '^$'` whose exit
  code propagates through `pipefail`. With `set -e`, an empty pid set
  silently kills the whole script — `do_start` reported success, no
  Electron, no error. Trail with `|| true`.
- `setsid` is GNU coreutils, not on macOS. Fall back to plain `bash -c`;
  process-tree teardown still works because `expand_descendants` walks
  the tree directly.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(hetero-agent): per-session MCP transport for sequential ops (LOBE-8725)

`AskUserMcpServer` shared a single `StreamableHTTPServerTransport` across
every CC subprocess. The SDK transport latches `_initialized=true`
after the first `initialize`, so the second op's CC subprocess sees
`Invalid Request: Server already initialized` (400) and reports the
`lobe_cc` server as `failed`. From the model's POV the MCP tool is
absent — it falls back to ToolSearch, can't find anything, and
verbalizes the question instead.

Refactor to the canonical multi-tenant pattern: one transport + one
`McpServer` per session, looked up by the SDK-managed `mcp-session-id`
header. New transports are minted on the first POST without a session
id (must be an `initialize` request); subsequent requests route via
the stored map; `onsessionclosed` cleans up.

The first run of any process still works as before — this only matters
once a second op spins up. Added a 3-op sequential regression test
that fails on the old single-transport implementation and passes now.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor(claude-code): move AskUserQuestion onto canonical Intervention surface (LOBE-8725)

Step 5's first cut shoehorned the pending form into the Render slot and
drove submit/skip with a custom `pluginState.askUserQuestion.status`
field, which forced three layers of glue:

- `Tool/Detail` had to bypass the loading placeholder via an
  identifier+apiName hardcode so the form would surface during
  `isToolCalling`
- The executor had to `messageService.getMessages → replaceMessages`
  after `agent_intervention_request` to drag the freshly-created tool
  row into in-memory state (the framework's own `tool_end →
  fetchAndReplaceMessages` only fires after the user answers)
- The executor also had to `associateMessageWithOperation` for the tool
  row so the form could look up the running CC op for IPC

All three were patches around skipping the canonical surface. This
commit moves AskUserQuestion onto `pluginIntervention.status='pending'`
and the `BuiltinToolInterventions` registry, which the framework
already drives end-to-end:

- `packages/builtin-tool-claude-code/src/client/Intervention/AskUserQuestion.tsx`
  — pure form, no IPC, no store reads. Resolves through the standard
  `onInteractionAction({type:'submit'|'skip'|'cancel'})` callback.
- `Render/AskUserQuestion` shrinks to the answered/aborted view only;
  the framework hides Render while pending, so no status switching.
- New `Inspector/AskUserQuestion` shows a compact "askUserQuestion · {header}"
  chip in the inline tool body, matching the rest of CC's tools.
- Registries: `ClaudeCodeInspectors`, `ClaudeCodeRenders`, and the new
  `ClaudeCodeInterventions` all key off `ClaudeCodeApiName.AskUserQuestion`;
  `BuiltinToolInterventions` gains a `[ClaudeCodeIdentifier]` entry.

Hetero needs a different action handler than `submitToolInteraction`
(which spawns `executeClientAgent` — wrong for a CC subprocess that's
already blocked on an MCP call). Two thin pieces wire that:

- `submitHeteroIntervention` (chat store) — sets
  `pluginIntervention` via `optimisticUpdateMessagePlugin` (which
  already syncs DB + in-memory + parent-assistant `tools[].intervention`
  in one shot), then forwards the answer through
  `heterogeneousAgentService.submitIntervention` IPC. Operation lookup
  walks the tool message's `parentId` to hit the assistant's
  `messageOperationMap` entry — drops the explicit
  `associateMessageWithOperation` call from the executor.
- `customInteractionHandlers.isHeteroInteractionIdentifier` flags
  `ClaudeCodeIdentifier`; `Tool/Detail/Intervention` short-circuits
  there before reaching the existing `submitToolInteraction` path.

Executor change collapses to one line:
`optimisticUpdateMessagePlugin(toolMsgId, { intervention: { status: 'pending' } })`.
The post-intervention refresh, the associate call, and the
`persistInterventionRequest` helper all go away.

Removed:
- `AskUserQuestionPluginState` type (custom field is gone)
- `Tool/Detail` `askUserPending` inline-render branch
- Executor `messageService.getMessages + replaceMessages` round-trip
- Executor `associateMessageWithOperation` for tool rows
- `persistInterventionRequest` helper

Verified end-to-end against a real CC subprocess on desktop:
- Inline body shows the new Inspector chip; pending form lives in the
  bottom InterventionBar (canonical surface)
- Submit ships answer through MCP, CC continues with structured result
- Skip flips status to `rejected`, framework's RejectedResponse
  shows "User skipped"; CC receives isError and falls back to text
- `mcp_servers.lobe_cc.status === 'connected'` on a 3rd sequential op
  (the per-session transport fix from the previous commit)
- `alwaysLoad: true` still produces 1-hop calls (no ToolSearch hop)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(claude-code): inline numbered option cards for AskUserQuestion intervention (LOBE-8725)

Select dropdown was the wrong primitive — it hides options behind an extra
click and doesn't read like a question to answer. CC's underlying tool is
1-4 questions × 2-4 options, so the whole option set always fits inline.

- Each option renders as a clickable card: numbered chip (1/2/3/4) +
  bold label + secondary description on a single row. Hover tints the
  background; selected state lights up `colorPrimary` on both the chip
  and the card outline so the pick is unmistakable at a glance.
- Multi-select (`q.multiSelect`) toggles instead of replacing, with a
  "(multi-select)" hint in the question header.
- Multi-question support gets a proper visual hierarchy: each question
  past the first sits below a dashed divider, headed by a `Q1/N` tag
  + the original `q.header` chip. The `Q*/N` lets the user track
  progress without counting.
- Inspector picks up the question count too: now shows
  "askUserQuestion · {first header} +N" when multiple are queued.

Verified end-to-end on desktop with a CC-driven 2-question prompt
(4-option + 3-option). Both selections feed back to CC as a single
"User answers" payload, CC echoes both picks in its continuation.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  feat(claude-code): tabbed multi-question + draft + timeout fallback for AskUserQuestion (LOBE-8725)

- Multi-question forms now use a top tab strip; single question renders inline.
- Picking a single-select option auto-advances to the next unanswered question.
- Drafts persist to tool message `pluginState.askUserDraft` so picks survive
  remount / HMR; new `setInterventionDraft` action on the chat store dispatches
  the pluginState patch.
- Timeout fallback: when the 5-min countdown expires, auto-submit option 1 for
  every unanswered question instead of letting the bridge time out into a
  cancelled isError — model gets a structured answer it can act on.
- Visual: selected option now uses filled `colorPrimaryBg` + right-aligned
  check icon; index chip stays neutral.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(hetero-agent): synchronously unlink temp mcp.json on app quit (LOBE-8725)

The async exit-handler cleanup raced Electron's main-process teardown and
left `lobe-cc-mcp-<opId>.json` files in `os.tmpdir()` after every quit. Sync
unlink in the quit hook is the only reliable guarantee.

Also handle SIGTERM / SIGINT — `before-quit` only fires on user-driven Cmd+Q
or `app.quit()`, not on external kills (test harness, OS shutdown).

Verified by manual test: pending askUserQuestion forms now leave zero
residue after both Cmd+Q and SIGTERM paths.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  feat(claude-code): persist structured AskUserQuestion answers + Q&A render (LOBE-8725)

Submit now writes the structured `{ questionText: pickedLabel(s) }` payload
to the tool message's `pluginState.askUserAnswers` (in-memory + DB merge), so
Render no longer has to scrape the bridge's prose `User answers:` content.

Render shows one Q&A block per question — header + question + a checkmark
card per picked option (multi-select fans out into multiple rows). Falls
back to a `—` placeholder when answers are missing (older messages or
skipped flows), and keeps the existing `pluginError` warning for cancel /
no-answer paths.

Also surfaces the answers in the Skill state inspector tab, which was
previously empty for completed askUserQuestion messages.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  test(hetero-agent): cover synchronous quit cleanup of AskUserQuestion temp configs (LOBE-8725)

Locks down the regression fixed in c0de0cdb7c — async exit-handler cleanup
losing to Electron's main-process teardown. Four cases: `before-quit`
(Cmd+Q / `app.quit()` path), `SIGTERM` (test harness / OS shutdown),
`SIGINT` (Ctrl-C), and idempotency (already-deleted temp file must not
throw on the second pass).

`process.on` and `process.exit` are stubbed in the signal-path tests so the
controller's listener attaches to a spy, not the test runner's process —
otherwise we'd leak a real SIGTERM listener every test.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:09 +08:00
Neko 71ddedaa83 ️ perf(agent-signal,prompts,types,database,server): fixed many minor self-review issues, harden the structure, verified with eval (#14647) 2026-05-13 02:57:09 +08:00
Arvin Xu 60a127b1e5 💄 style(copyable-label): wrap long tool-call params instead of truncating (#14640)
* 💄 style(copyable-label): wrap long values instead of truncating

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor(copyable-label): make wrap an opt-in via Descriptions prop

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(descriptions): omit GridProps wrap to avoid type collision

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:09 +08:00
Arvin Xu b85a1ad851 💄 style: format tool execution time as Xmin Ys instead of X.Y min (#14641)
🐛 fix: format tool execution time as `Xmin Ys` instead of `X.Y min`

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:08 +08:00
Arvin Xu 7daed90d0e 🐛 fix(model-runtime): enrich stream parse errors with provider/model context (#14636)
*  feat(model-runtime): enrich stream parse errors with provider/model context

When the OpenAI / Anthropic SDK iterator throws (most often a JSON
SyntaxError on a malformed SSE chunk — e.g. an upstream response with an
illegal backslash escape), `convertIterableToStream` previously only
surfaced `message`/`name`/`stack`. Downstream error logs (agent-gateway
errors table) end up with just "Bad escaped character in JSON at
position 160050" and no way to correlate which provider/model produced
it or whether the same offset keeps recurring.

This change threads optional `{ provider, model }` context through
`convertIterableToStream` / `readableFromAsyncIterable` and enriches the
FIRST_CHUNK_ERROR payload with:

- `provider` / `model` so triage can group identical upstream failures
- `parsePosition` extracted from V8 JSON SyntaxError messages
- `causeName` / `causeMessage` when `error.cause` is set (many wrapped
  errors carry the actionable detail in `cause` and the bare triplet
  drops it)

Threaded through OpenAI/Responses/Anthropic stream handlers, which all
already receive `payload` containing provider/model.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(model-runtime): walk error.cause for parsePosition + JSON-safe payload

Two review findings on #14636:

1. Wrapped SyntaxErrors lost their parsePosition. Provider SDKs commonly
   rethrow `JSON.parse` failures wrapped in their own error class
   (e.g. `APIError(cause: SyntaxError)`), so the outer `error.name` is
   no longer `'SyntaxError'` and the previous check skipped extraction
   for the exact case this enrichment was meant to diagnose. Now
   `extractParsePosition` walks both the outer error and any `Error`
   cause, and accepts any error whose message still carries the
   `"JSON at position N"` signature even if the SyntaxError name was
   lost in wrapping.

2. Cause cloning could blow up the entire diagnostic path.
   `structuredClone` succeeds on values that `JSON.stringify` later
   throws on (BigInt, circular refs), so a non-Error cause carrying
   either would surface as `payload.cause = clonedObject`, then the
   outer `JSON.stringify(payload)` would throw inside the catch handler,
   and the FIRST_CHUNK_ERROR chunk never gets emitted. Replaced with
   `safeJsonStringify` (BigInt → string, cycles → `[Circular]`) and
   route the cause object through `toJsonSafe` so the returned shape is
   always plain JSON.

Added tests for both: a wrapped APIError(cause: SyntaxError) yields
parsePosition, and a cause containing both BigInt and a circular ref
still emits a parseable error chunk.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:08 +08:00
Arvin Xu 0babdcfc00 🐛 fix(home): strip markdown links from daily-brief input placeholder (#14635)
The daily-brief hint will start carrying `[name](url)` markdown links so
the AI can resolve referenced entities when the user submits via the
hint. The placeholder layer is the only consumer that wants the visible
label without the link syntax — extract a small `stripMarkdownLinks`
util and apply it at `InputArea/index.tsx` only. `useSend` continues to
forward the raw hint, so the agent still receives the link in the
outgoing message.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:08 +08:00
YuTengjing d445a89c85 🐛 fix: consume visual content parts in server runtime (#14637) 2026-05-13 02:57:08 +08:00
Arvin Xu 3c8101128e feat(bot): gate device tools by sender identity (#14634)
*  feat(bot): gate device tools by sender identity (LOBE-8715)

External users who @-mentioned a bot ran the agent as the bot owner and
could call LocalSystem / RemoteDevice tools — a confused-deputy hole that
let any group member indirectly read/write the owner's machine.

- `ChatTopicBotContext` carries `senderExternalUserId` + `isOwner`
- `BotMessageRouter` / `MessengerRouter` compute `isOwner` at the entry
  point (fail-closed when `settings.userId` is missing)
- `resolveDeviceAccessPolicy` maps sender identity to
  `{ canUseDevice, reason }`; trusted-list branch is reserved for future
  work without engine changes
- `AgentToolsEngine` gates `LocalSystem` + `RemoteDevice` on `canUseDevice`
- `RemoteDeviceManifest.systemRole` is no longer injected on
  external-sender turns — closes the device-list information leak
- Per-call audit log (`lobe-server:agent-device-tool-audit`) at the
  dispatch site records sender, isOwner, reason, identifier, apiName

Fixes LOBE-8715

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🚨 chore(bot): replace `any` on botContext / botPlatformContext with concrete types

Picks up the existing `BotPlatformContext` (`@lobechat/context-engine`)
and `ChatTopicBotContext` (`@lobechat/types`) — both already exported —
instead of the inherited `any` placeholders on:

- `OperationCreationParams.{botContext, botPlatformContext, deviceAccessPolicy}`
- `InternalExecAgentParams.botPlatformContext`
- `RuntimeExecutorContext.botPlatformContext`

`deviceAccessPolicy.reason` is now `DeviceAccessReason` instead of `string`.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🔒 fix(bot): clear activeDeviceId when canUseDevice=false (LOBE-8715)

The previous patch gated `LocalSystemManifest` in the engine's enabledToolIds,
but `buildStepToolDelta` re-injects local-system from `state.metadata.activeDeviceId`
on every step regardless of whether the engine excluded it. Auto-activation
in `aiAgent.execAgent` populated `activeDeviceId` whenever
`(discordContext || botContext) && onlineDevices.length === 1`, so an
external bot sender with one device online could still get local-system
tools against the owner's device.

- `aiAgent/index.ts`: skip `activeDeviceId` derivation entirely when
  `canUseDevice` is false. `deviceSystemInfo` short-circuits naturally on
  `if (activeDeviceId) {...}`, so no extra change needed there.
- `RuntimeExecutors.ts`: belt-and-suspenders — if
  `state.metadata.deviceAccessPolicy.canUseDevice` is false, swallow
  `activeDeviceId` before passing to `buildStepToolDelta`, so a future
  plumbing bug at the source can't reopen the bypass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🔒 feat(bot): allow device tools on personal-scope platforms (WeChat) (LOBE-8715)

Not every bot platform can identify an owner. WeChat's LobeHub integration
encodes every inbound thread as 1:1 (`packages/chat-adapter-wechat/src/adapter.ts:465`)
and its settings schema has no `userId` field, so `isOwner` is structurally
false on every WeChat turn. The previous policy denied every WeChat call
with `bot-owner-not-configured` — fail-closed but unusable.

This commit treats platforms whose integration is structurally personal-
scope as trusted. WeChat is the only member today; LINE is intentionally
excluded because its adapter handles group/room threads even though its
schema also lacks `userId` — those must be fixed at the schema layer
before being whitelisted.

- New `bot-personal-platform` reason in `DeviceAccessReason`
- `PERSONAL_SCOPE_BOT_PLATFORMS = new Set(['wechat'])`
- Personal-scope check sits AFTER `isOwner` so a future WeChat schema
  with a `userId` field still resolves as the more specific `bot-owner`
- Tests: WeChat without isOwner → allow; WeChat with isOwner=true → still
  `bot-owner` (more specific wins); regression guard ensuring Discord /
  Slack / Telegram / Feishu / Lark / QQ / LINE keep going through the
  standard isOwner gate

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  test(engine): opt existing device gate tests into canUseDevice=true (LOBE-8715)

The `LocalSystem` / `RemoteDevice` enable rules now short-circuit on
`canUseDevice` (default `false`), so tests that exercise the
engine-internal gates (`runtimeMode`, `deviceContext`, `clientRuntime`)
must explicitly pass `canUseDevice: true` — otherwise they assert the
right behavior for the wrong reason or fail outright (e.g. the desktop
RemoteDevice-suppression case the reviewer flagged).

- All `LocalSystem` / `RemoteDevice` / `LocalSystem + RemoteDevice` /
  `clientRuntime === "desktop" (Phase 6.4)` blocks now set
  `canUseDevice: true`.
- The "disable RemoteDevice in bot conversations" test was repurposed:
  the dropped `!isBotConversation` clause is now subsumed by `canUseDevice`,
  so for a trusted bot caller (canUseDevice=true) RemoteDevice DOES surface.
  The original intent — block when caller is untrusted — is captured in
  the new `canUseDevice gate` block.
- New `canUseDevice gate` describe block asserts:
    1. `canUseDevice=false` blocks LocalSystem even on a desktop caller
    2. `canUseDevice=false` blocks RemoteDevice with proxy configured
    3. Omitting `canUseDevice` → fail-closed default (deny)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  test(execAgent): set isOwner=true on device auto-activation tests (LOBE-8715)

These pre-existing tests model an owner using the bot through Discord and
assert that `activeDeviceId` auto-populates when one device is online.
After LOBE-8715, `activeDeviceId` is gated on `canUseDevice` from
`resolveDeviceAccessPolicy`, so a `botContext` without `isOwner: true`
resolves to `bot-external-sender` → `canUseDevice=false` →
`activeDeviceId=undefined`.

Filling out the `botContext` mocks with `isOwner: true` (plus the other
required fields the type now demands) preserves the tests' original
intent while exercising the new gate.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:08 +08:00
YuTengjing 9982de3a5c 🐛 fix: store onboarding interests as keys (#14624) 2026-05-13 02:57:08 +08:00
Arvin Xu 7f6fdd7c14 🔥 chore(web-crawler): remove WeChat URL rules (#14633)
Drop the `weixin.sogou.com` and `mp.weixin.qq.com` rules from the crawler
URL ruleset since they are no longer needed.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:08 +08:00
LobeHub Bot d13f2e3ad8 🌐 chore: translate non-English strings to English in apps/cli, apps/device-gateway, and apps/desktop scripts (#14626)
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-13 02:57:08 +08:00
LiJian 7675bd9fb5 🐛 fix(hetero-agent): sync new-step assistant across replicas (#14631)
* 🐛 fix(hetero-agent): sync new-step assistant across replicas

* 🐛 fix(hetero-agent): tighten new-step assistant fallback

* fix: slove the test
2026-05-13 02:57:08 +08:00
LiJian 457d112a74 🐛 fix: remove the old cron job from lobehub (#14630)
* fix: remove the old cron job from lobehub

* fix: add some ts back
2026-05-13 02:57:08 +08:00
LiJian 6595961e5a 🐛 fix: refresh content baseline from DB on every ingest call (#14603)
* 🐛 fix: refresh content baseline from DB on every ingest call

Vercel serverless routes consecutive batches to different Lambda
instances. A warm replica's in-memory `accumulatedContent` only
reflects batches it processed; it has no visibility into batches
handled by other replicas.

The failure pattern (worst when a repo is selected, since CC makes
tool calls early):

1. Lambda A — batch 1 (text "你好!...") → flushBatchContent writes
2. Lambda B — batch 2 (text "...任务。") → restores from DB, appends,
   writes longer text to DB
3. Lambda A — batch 3 (tools_calling only, warm state) → its stale
   `accumulatedContent` = batch-1 text → persistMainToolBatch Phase 1
   writes `{ tools, content: stale-short-text }` → OVERWRITES the
   correct longer DB value → content truncated at "你"

Fix: re-read the current assistant message from DB at the start of
every `ingest()` call. Since `flushBatchContent` writes at the end of
every batch, DB is authoritative. The refresh gives each Lambda the
latest flushed baseline, so new text in the current batch extends
the correct full string.

Cost: one extra `findById` round-trip per warm ingest call.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

*  feat: auto-inject GitHub OAuth token into CC sandbox

Previously the GitHub token was only resolved when repos were selected
AND GITHUB_CRED_KEY was explicitly configured in the agent config —
so CC running without pre-selected repos had no GitHub access and had
to ask the user for a PAT manually.

Changes:
- aiAgent/index.ts: always try to resolve the token using key 'github'
  (standard LobeHub OAuth connector default); GITHUB_CRED_KEY still
  overrides. No longer guarded behind topicRepos.length > 0.
- sandboxRunner.ts: new buildCredsSetupScript() runs before CC starts:
    mkdir -p ~/.creds
    printf 'GITHUB_ACCESS_TOKEN=%s\n' <token> > ~/.creds/env
    gh auth login --hostname github.com --with-token
  Writes ~/.creds/env in the same format as injectCredsToSandbox(["github"])
  so CC can source it in sub-shells. Creds step runs before repo clone step.
- cloudHeteroContext.ts: system prompt now tells CC that GITHUB_TOKEN is
  set, gh CLI is pre-authenticated, and ~/.creds/env has GITHUB_ACCESS_TOKEN
  with the source/auth recipe for sub-shell usage.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* 🐛 fix: adopt max-length content on DB refresh to guard flushBatch retry

The unconditional DB overwrite in ingest() broke the retry contract:
if flushBatchContent threw after events were already marked in
processedKeys, a retry on the same warm instance would read the stale
(shorter) DB value and wipe the in-memory chunks — which processedKeys
would then skip, losing them permanently.

Fix: only adopt the DB value when it is LONGER than in-memory.
This preserves both behaviours:
- Multi-replica stale (the original fix): DB has more content from
  another replica → dbContent.length > in-memory → adopt DB. ✓
- flushBatchContent retry on same Lambda: DB still has the old shorter
  value, in-memory has the correct accumulation → keep in-memory. ✓

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-13 02:57:08 +08:00
Arvin Xu ae8f9cfb27 🐛 fix(hetero-agent): disable Claude Code AskUserQuestion to avoid auto-decline (#14629)
* 🐛 fix(hetero-agent): disable Claude Code AskUserQuestion to avoid auto-decline

CC's built-in AskUserQuestion self-injects an `is_error: "Answer questions?"`
tool_result inside the CLI in `-p` non-interactive mode before the host can
surface the questions, so the model falls back to plain-text prompting after
a wasted round-trip. Add `--disallowedTools AskUserQuestion` to both spawn
sites (desktop driver + lh hetero exec) so the model goes straight to text.

To be revisited once a local MCP-backed replacement is wired to LobeHub's
intervention UI.

* ♻️ refactor(hetero-agent): share CC base args, opt-in partial deltas

- Promote CLAUDE_CODE_BASE_ARGS in `@lobechat/heterogeneous-agents/spawn` to
  the canonical source of truth for invariant CC CLI flags (`-p`, stream-json
  IO, `--verbose`, `--disallowedTools AskUserQuestion`); export it so the
  desktop driver can compose on top instead of duplicating.
- Pull `--include-partial-messages` out of the base. It's now a
  `SpawnAgentOptions.includePartialMessages` flag, off by default so
  `lh hetero exec` standalone/sandbox runs don't pay for delta noise they
  don't render. The desktop driver opts in (chat bubble streams live).
- Permission mode stays caller-specific: desktop hardcodes bypassPermissions
  (always user-mode), the package keeps its root-vs-user branch for cloud
  sandbox.

* 🎨 style(hetero-agent): pass spawn-args builders an options object

Positional list grew to four args with mixed types — switch to a single
`BuildSpawnArgsParams` object so call sites read by field name and adding
future per-agent flags doesn't push every other caller around.
2026-05-13 02:57:08 +08:00
Arvin Xu 96165e453a 🐛 fix(local-system): guard readFile against binary blobs and oversized output (#14602)
* 🐛 fix(local-system): guard readFile against binary blobs and oversized output

Previously `lobe-local-system.readFile` would happily decode any extension
as UTF-8 and return the entire content. Reading a 27KB base64-encoded git
bundle blew up the next LLM call to 3.28M tokens / 416s and triggered a
DB rollback. The default 200-line cap was bypassed because base64 was a
single very long line.

Add four layers of protection in `readLocalFile`:
- Hard-reject extensions outside the text-readable + special-parser
  whitelist with a structured error pointing the agent at runCommand.
- Sniff the first 8KB and refuse files that look binary (null bytes or
  >30% non-printable chars).
- 10MB hard size cap before the file is read into memory.
- Cap each returned line at 8K chars and total output at 500K chars,
  with `truncated` / `linesTruncated` flags surfaced in the result.

Refs LOBE-8703.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(file-loaders): preserve UTF-16 text files without a BOM in binary sniffer

The binary sniffer rejected UTF-16LE/BE files that lacked a BOM because
their alternating 0x00 bytes tripped the null-byte heuristic. `TextLoader`
already has a `detectUtf16NoBom` heuristic for these Windows-style exports;
extract it to a shared `detectUtf16` util and run it in the sniffer before
the null-byte check, decoding with the matching variant for the printable
ratio test instead of declaring the file binary.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 💄 style(local-system): render WriteFile new files as a unified diff

Switch the WriteFile render from a syntax-highlighted preview to a
synthesized "new file" unified diff via PatchDiff, matching the
EditLocalFile visual. Markdown files keep their rendered preview.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  test(local-system): exercise readFile / readFiles end-to-end

The previous LocalFileCtr.readFile / readFiles tests deep-mocked
node:fs/promises and @lobechat/file-loaders. Since the controller is a
thin pass-through to readLocalFile, the assertions ended up testing
shell internals (already covered in packages/local-file-shell), and
broke as soon as readLocalFile gained new pre-flight checks.

Move them into a sibling LocalFileCtr.readFile.test.ts that runs
against a real tmpdir + real file-loaders, so adding more upstream
guards no longer requires touching this suite.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:08 +08:00
YuTengjing 521566bdb7 feat: add user activity business hook (#14601) 2026-05-13 02:57:08 +08:00
Hardy ab7b9e3e69 ♻️ refactor(siliconcloud): sync models with API, fix duplicates, adjust reasoning params (#14464)
* ♻️ refactor(siliconcloud): sync models with API, fix duplicates, adjust reasoning params

* 🐛 fix(siliconcloud): fix GLM-4.7 checkModel casing to match model ID
2026-05-13 02:57:08 +08:00
AmAzing- fa55b3fb25 🌐 i18n: update banner copy translations (#14623) 2026-05-13 02:57:08 +08:00
AmAzing- e300766046 💬 i18n: remove trailing punctuation from banner titles (#14622) 2026-05-13 02:57:08 +08:00
YuTengjing 9b032f0773 feat: add Gemini 3.1 Flash-Lite provider cards (#14604) 2026-05-13 02:57:08 +08:00
YuTengjing 629213189b ♻️ refactor: remove model extend param options (#14607) 2026-05-13 02:57:08 +08:00
René Wang f38f0c258b 📝 docs: add intro and screenshot to task scheduler changelog (#14585) 2026-05-13 02:57:07 +08:00
Neko 38b793f41b 🐛 fix(database,utils,userMemories): should perfer to use paradedb.match(...) instead of hardcoded normalizer (#14590) 2026-05-13 02:57:07 +08:00
Arvin Xu 11ec59b8c8 🐛 fix(database): attach error listeners to Neon/Node pools to prevent Lambda crash (#14606)
* 🐛 fix(database): attach error listeners to Neon/Node pools to prevent Lambda crash

NeonPool (and NodePool) inherit pg.Pool semantics: when a backend connection
drops on an idle client the pool emits 'error'. With no listener Node
escalates that into uncaughtException — on Vercel this killed the entire
Lambda process (exit 129) and produced a 1805-crash avalanche in 5 minutes,
spiking Neon connection count from 30 to 330+ as half-closed sockets
accumulated (LOBE-8704).

Primary fix: attach `.on('error', ...)` to both pool variants in
`packages/database/src/core/web-server.ts` so the error is logged but
swallowed; the pool recovers on its own per pg docs.

Defense in depth: register `uncaughtException` / `unhandledRejection`
handlers in `instrumentation.ts` (gated to nodejs runtime) so any future
unhandled error doesn't take down the process either.

Refs: https://node-postgres.com/apis/pool#error

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🔧 chore: drop process-wide uncaughtException handler

Per review on #14606: the catch-all listener in instrumentation.ts swallowed
every uncaughtException / unhandledRejection — not just NeonPool errors —
leaving the process in an undefined state instead of letting the platform
restart it, and would mask future production bugs.

LOBE-8704 is fully addressed by the targeted pool listeners in
packages/database/src/core/web-server.ts; the broad backstop is unnecessary
and unsafe.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:07 +08:00
sxjeru 867e22a90e 💄 style: Add new DeepSeek-V4 models (#14110)
Co-authored-by: Copilot <copilot@github.com>
Co-authored-by: YuTengjing <ytj2713151713@gmail.com>
2026-05-13 02:57:07 +08:00
Arvin Xu 4bfd434552 🐛 fix: gateway client-tool pluginState + drop redundant Exit code: 0 tail (#14596)
* 🐛 fix(agent-runtime): forward pluginState through gateway client tool result

Gateway-mode client tool results lost the `state` field at three points:
the toolResult Zod schema didn't declare it (silently stripped by safeParse),
the ToolResultPayload interface didn't carry it, and projectToExecutionResult
didn't return it. As a result the "技能状态" tab was always empty for tools
dispatched via Agent Gateway, even though clients send `state` correctly and
non-gateway paths persist it as `pluginState`.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(prompts): suppress redundant `Exit code: 0` tail in command result

For successful runs, "Command completed successfully." already conveys
the same signal — appending "Exit code: 0" was just noise the LLM had
to skim past. Non-zero exit codes (130 SIGINT, 137 OOM, etc.) keep the
line so the diagnostic information remains available.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(prompts): treat non-zero exit code as command failure in result header

`success` is the envelope ("the service responded") and `exitCode` is the
command's own status — they're independent. With `success: true` +
`exitCode: 137` the prior format rendered "Command completed successfully."
on top of a SIGKILL/OOM, lying to the LLM.

Now the header is derived from both: any non-zero exit folds the message
into the failure branch as "Command failed with exit code N[: error]".
The trailing "Exit code: N" line is gone — the same info now lives in the
header, so success rendering is also free of the redundant zero tail.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:07 +08:00
sxjeru 307cd8e523 🐛 fix(gemini): handle zero cachedContentTokenCount in usage conversion (#14567)
Co-authored-by: YuTengjing <ytj2713151713@gmail.com>
2026-05-13 02:57:07 +08:00
Arvin Xu a2750098f4 💄 style(topic): add copy session ID to topic dropdown menu (#14595)
 feat(topic): add copy session ID to topic dropdown menu

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:07 +08:00
Arvin Xu 12e37f1e46 feat: home daily brief with linkable welcome + paired input hint (#14589)
*  feat: home daily brief with linkable welcome + paired input hint

Add a per-user "daily brief" surface to the home page. A cron-driven
backend (in the cloud repo) writes paired { welcome, hint } entries
into Redis under `aiGeneration:home_brief:{userId}`. This change exposes
that data through:

- `RedisKeys.aiGeneration.homeBrief` key builder
- `home.getDailyBrief` lambda router query that reads the cached payload
- `homeService.getDailyBrief` client and `useHomeDailyBrief` hook with
  shared rotating index via `useSyncExternalStore`
- `WelcomeText` runs a custom typewriter (supports real `\n` line breaks
  and parses inline `[label](url)` markdown links so cached entity
  references become clickable; falls back to the i18n welcome list)
- `InputArea` shows the matching hint as the chat input placeholder

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor: extract daily-brief Redis read into HomeService

Mirrors the AgentService pattern: the lambda home router was reaching
into Redis directly, which mixed I/O concerns with the routing layer.
Move the read into a dedicated `HomeService` so future home-page reads
have a clear home and the router stays thin.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix: keep WelcomeText typewriter index in sync with shared store

Before: DailyTypewriter held its own `sentenceIndex` state, separate
from the module-level `currentIndex` in `useHomeDailyBrief`. After
the home page rotated past the first pair, navigating away and back
remounted the typewriter and reset its local index to 0 — but the
external index stayed where it was. InputArea read the hint at the
stale external index while WelcomeText restarted at pair 0, breaking
the welcome / hint pairing.

Make the typewriter fully controlled: drop the local `sentenceIndex`,
expose `currentIndex` from `useHomeDailyBrief`, and pass it as a prop.
On `pause`, the typewriter just calls `onSentenceComplete` — the
parent flips the shared index, the new prop flows back, the reset
effect re-arms typing for the new sentence. Single source of truth,
remount-safe.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* ♻️ refactor(redis): factor JSON cache reads into getJSONFromRedis util

Three call sites were inlining the same "fetch + null-check + JSON.parse
+ try/catch" recipe against a scoped Redis client:

- AgentService.getAgentWelcomeFromRedis
- HomeService.readDailyBriefFromRedis (new)

Move the recipe into a small `getJSONFromRedis<T>` helper next to the
other Redis utilities and have both services delegate to it. Caller
keeps responsibility for resolving the right scoped client (we don't
want to hide the prefix selection inside the helper).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(home): use live editor content for Enter-to-send guard

When typing into the home input and pressing Enter immediately, the
empty-message guard sometimes wrongly bailed out. The cause: the guard
read the cached `inputMessage` in `useChatStore`, which is populated by
the editor's async `onMarkdownContentChange`. Lexical commits its
update on a microtask after each keystroke, so a fast type-then-Enter
fires the send path before the cache catches up.

`SendButtonHandler` already passes `getMarkdownContent` through — read
it instead, falling back to the cached value if the handler is invoked
without it. Also propagate the live message into all `inputActiveMode`
branches.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  feat(home): accept daily-brief hint as the message on empty Enter

Press Enter on the empty home input → send the currently displayed
daily-brief hint as the message (smart-compose / Tab-to-accept style).
Trims the cosmetic trailing ellipsis and rotates the carousel so the
next press picks up a different pair.

Falls through to the previous "no content, skip" path when there's
neither a typed message nor a hint to use.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(home): scope daily-brief SWR key + rotation index by userId

The SWR key was a constant string, so an account switch within the same
SPA session — sign out + sign in as another user, or a multi-account
swap that keeps `isSignedIn` true — could surface the previous user's
cached pairs from the same slot. The keyspace in Redis is per-user,
so the served data leaks personalization.

Include the resolved userId in the SWR key, and reset the module-level
rotation index on user change so the new account starts from pair 0
rather than inheriting a stale offset (which could also point past the
end of a smaller pairs list).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:07 +08:00
LiJian 09c66ffb4c 🐛 fix: first inject the cloudecc runtime session should use the existingStatus (#14592)
* 🐛 fix: skip reconnect when gateway action already established a connection

Race condition on new-topic first message:
1. switchTopic loads runningOperation → useGatewayReconnect fires
2. executeGatewayAgent calls connectToGateway (status: connecting)
3. reconnectToGatewayOperation overwrites with resumeOnConnect:true
4. Gateway sees resume on a brand-new session → no events → stuck

Second message works because the client store's runningOperation is
stale (from the first op), so SWR deduplications and no reconnect fires.

Fix: bail out of reconnectToGatewayOperation if gatewayConnections
already shows connecting/connected for that operationId.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* 🐛 fix: always pass --cwd /workspace for cloud CC to ensure session resume

CC stores session files at ~/.claude/projects/<encoded-cwd>/.
Without an explicit --cwd the actual working directory can differ
between sandbox invocations, so --resume <heteroSessionId> fails
to locate the previous session files even though the container is
persistent and the ID is correctly stored in topic.metadata.

Default cwd to /workspace for cloud runs (desktop keeps its own
explicit path), guaranteeing a stable session-file location across
page reloads within the same sandbox lifecycle.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* 🐛 fix: extend reconnect guard to cover all in-flight connection statuses

The previous guard only skipped reconnect for 'connecting'/'connected'
but the connection can already be in 'authenticating' or 'reconnecting'
by the time useGatewayReconnect fires, leaving the race window open.

Flip the condition: skip for any status that is not 'disconnected'.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* 🐛 fix: restore cold replica state in HeterogeneousPersistenceHandler

Vercel serverless functions are stateless per-request, so `operationStates`
is empty on every `heteroIngest` call. loadOrCreateState always cold-creates.

#14539 fixed `toolMsgIdByCallId` restoration but left `accumulatedContent`,
`toolState.payloads`, and `toolState.persistedIds` empty on cold load,
causing two bugs:

- Content truncation: cold instance starts with `accumulatedContent=''`,
  accumulates only the current batch's text, then writes that shorter string
  on the next step boundary or terminal — overwriting the longer content the
  previous write had already stored in DB.

- Tool duplication / tools[] overwrite: `persistedIds={}` on cold load
  means every `tools_calling` event re-creates already-persisted tool
  messages, and `payloads=[]` means phase 1/3 writes only the current
  batch's tools, wiping previous tools from `assistant.tools[]`.

Fix: in `loadOrCreateState`, fetch the current assistant message and restore
`accumulatedContent`, `accumulatedReasoning`, `toolState.payloads`, and
`toolState.persistedIds` from it. Cold load is now equivalent to warm load.

Also adds two regression tests covering the cold-replica scenarios.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-13 02:57:07 +08:00
Arvin Xu 909b1ec461 💄 style: use visible divider between queued messages (#14593)
💄 style(QueueTray): use visible divider color between queued messages

The previous `colorBorderSecondary` rendered the divider effectively
invisible on the elevated dark surface. Switch to `colorFillTertiary`
so stacked queued messages have a perceptible separator.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:07 +08:00
Rdmclin2 8274be0d1d 🐛 fix: slack connect error & slash commands (#14591)
* feat: displayToolCalls default undefined

* chore: restrict billboard to home page

* fix: add slack bot scope

* fix: show billboard in home nav
2026-05-13 02:57:07 +08:00
Neko b7a50206bf feat(agent-signal,prompts,database): self-review now proposal actions to briefs, and automatically execute actions (#14583) 2026-05-13 02:57:07 +08:00
Innei 5c1113031d 💄 style(intervention): polish confirmation bar layout (#14587) 2026-05-13 02:57:07 +08:00
AmAzing- fa17c75f90 chore: Refine homepage banner copy for channels and skills (#14588) 2026-05-13 02:57:07 +08:00
AmAzing- 0c659dbe22 🛠️ fix: unify SKILL.md frontmatter parsing and edit validation in agent documents (#14566) 2026-05-13 02:57:07 +08:00
LiJian d2c379c78d feat: add signOperationJwt with 4h expiry for hetero-agent operations (#14586)
*  feat: add signOperationJwt with 4h expiry for hetero-agent operations

- Add `signOperationJwt(userId)` to internalJwt.ts with 4h expiry and
  `purpose: 'hetero-operation'`, so Claude Code / Codex tasks running
  beyond 5 minutes no longer hit 401 on heteroIngest / heteroFinish
- Update `execAgent` hetero path to use `signOperationJwt` instead of
  `signUserJWT`; gatewayToken continues to use 5m `signUserJWT`
- Add unit tests in `__tests__/internalJwt.test.ts` with correct mocks
  for `jose` (SignJWT class + importJWK) and `authEnv`, covering all
  three signing functions and the expiry difference assertion

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* 🔒 security: restrict hetero-operation JWT scope to heteroIngest/heteroFinish

A leaked 4-hour sandbox LOBEHUB_JWT must not be replayable against any
other authenticated lambda route.

- Forward `purpose` claim from JWT payload through validateOIDCJWT →
  tokenData → oidcAuth context so middlewares can inspect it
- oidcAuth: reject tokens with purpose 'hetero-operation' — they cannot
  reach any normal authedProcedure route
- New heteroOperationAuth middleware: exclusively accepts
  purpose 'hetero-operation' tokens, rejects all others
- Export heteroAuthedProcedure (baseProcedure + heteroOperationAuth +
  userAuth) from trpc/lambda/index.ts
- heteroIngest / heteroFinish now use heteroAgentProcedure built on
  heteroAuthedProcedure + serverDatabase + HeterogeneousAgentService
- Tests: heteroOperationAuth (4), oidcAuth (4), update heteroIngest
  test caller to supply purpose:'hetero-operation' context (23 total)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-13 02:57:07 +08:00
Innei d73de25623 💄 style(settings): remove image avatar from lab input markdown rendering item (#14582) 2026-05-13 02:57:07 +08:00
YuTengjing a02ecbc40d 🐛 fix: polish task agent manager (#14569) 2026-05-13 02:57:07 +08:00
AmAzing- f1f2e58e01 feat: migrate Notion to LobeHub Market (#14578)
Migrate Notion to LobeHub Market
2026-05-13 02:57:06 +08:00
Arvin Xu 5f8ec8bbfb 🐛 fix(agent-runtime): recover malformed tool_call names instead of finishing silently (#14577)
* 🐛 fix(agent-runtime): recover malformed tool_call names instead of finishing silently

When an LLM emits tool_call names without the `____` separator (e.g. `activateTools`
instead of `lobe-activator____activateTools`), the resolver dropped them silently and
the harness finished with "completed without tool calls" — empty assistant bubble,
no error in dashboards.

Three layers of defense:

- Resolver fallback: when the bare name uniquely matches an API across known
  manifests, recover the identifier; ambiguous matches still drop to avoid
  false binding.
- StreamingHandler logs unresolved tool_call names so the silent-drop path is
  observable in debug output.
- GeneralChatAgent surfaces the unresolvable count and names in reasonDetail
  so dashboards can distinguish this from a genuine no-tool completion.

Fixes LOBE-8696

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(agent-runtime): restrict bare-name fallback to tools offered this turn

Address review feedback on the LOBE-8696 resolver fallback. The
manifests map passed to ToolNameResolver.resolve is broader than the
tools actually sent to the LLM (the client builds it from every
installed plugin and every builtin; the server can preserve manifests
even after a step deactivates a tool). Without a turn-scope
restriction:

- A model returning a malformed bare name could resolve to a tool that
  was not enabled for this turn.
- A disabled duplicate API name could shadow the enabled call and make
  it look ambiguous, dropping a valid call.

Pipe an `offeredToolNames` list (the names actually sent in this LLM
payload) into resolve(): when set, the missing-prefix fallback only
considers manifests whose generated tool name appears in the list.

- ToolNameResolver.resolve gains an optional `offeredToolNames` param.
- internal_transformToolCalls forwards the list through.
- createAgentExecutors builds resolvedAgentConfig before the
  StreamingHandler so the closure can bind the offered names — same
  list that gets sent to the model.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:06 +08:00
LiJian 7792f63453 feat: Cloud Claude Code V3 — repo picker, GitHub token, sandbox context (#14568)
*  feat: Cloud Claude Code V3 — repo picker, GitHub token, sandbox context

- Add CloudRepoSwitcher component (web-only multi-select repo picker)
  - Pre-topic selections buffered in module singleton (pendingTopicRepos)
  - Consumed by gateway.ts at topic creation time via appContext.initialTopicMetadata
  - Eliminates race condition where updateTopicMetadata dropped silently
- Extend ChatTopicMetadata with repos[] field for multi-repo binding
- Add initialTopicMetadata to ExecAgentAppContext so repos are written to
  topic metadata at creation time (server-side, zero race condition)
- Extend ExecAgentSchema Zod schema with initialTopicMetadata
- Inject GITHUB_TOKEN env var into sandbox so CC can use git/gh CLI
- Build cloudHeteroContext with GitHub auth section when token is available
- Add workingDirectory selector for web (repos[0] fallback)
- Add refreshTopic call in gateway path after new topic creation
- Add CloudHeterogeneousConfig profile editor for GITHUB_REPOS / GITHUB_CRED_KEY
- Extend sandboxRunner with repo clone setup script and systemContext support

* 🐛 fix: add open-source stub for pendingTopicRepos to fix Vite build

* ♻️ refactor: move pendingTopicRepos real impl into submodule, remove cloud override

* 🐛 fix: consume pendingTopicRepos only after topic creation succeeds

* 🐛 fix: add missing getPendingTopicRepos import in gateway

* 🔒 fix: address security and dead-code issues from PR review

- sandboxRunner: sanitize repo dir name to prevent shell injection
- sandboxRunner: use git insteadOf (-c flag) so token is never stored in .git/config
- cloudHeteroContext: fix return type from string|undefined to string (dead branch)
- CloudRepoSwitcher: remove unreachable empty-list branch in popover content

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* 💬 i18n: add claude setup-token hint to token description

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* 🐛 fix: remove incorrect web hetero→gateway forced routing in agentDispatcher

On web, heterogeneousProvider is ignored — routing falls through to isGatewayMode.
Cloud CC only runs when gateway mode is enabled; gateway.ts handles sandbox
spawning when it detects a hetero provider.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* 🐛 fix: restore web hetero→gateway routing; update stale test

On web, a configured heterogeneousProvider always routes to gateway —
the cloud sandbox is the only execution environment regardless of
isGatewayMode. The test assumed the pre-cloud-CC world where web
ignored hetero providers entirely.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-13 02:57:06 +08:00
Innei 2959ec3883 📝 docs(version-release): enforce git-derived PR refs and metrics (#14575)
* 📝 docs(version-release): enforce git-derived PR refs and metrics

Add the skill's first-class hard rules for computing release-note inputs
from git instead of memory: latest-tag base via `git describe`, PR refs
from commit subjects, metric counts from `wc -l`, handle resolution via
`gh pr view`, and a pre-publish `comm -23` diff that must be empty.
Also adds @cy948 to the team roster and notes Tsuki / René Wang's
commit-author aliases so contributor classification stops drifting.

* ♻️ refactor(version-release): split skill into router + per-flow references

SKILL.md was 426 lines covering three distinct flows. Split it so each
flow lives next to its own checklist:

- reference/minor-release.md — minor workflow (lifted from SKILL.md)
- reference/patch-release-scenarios.md — patch flows (existing)
- reference/release-notes-style.md — long-form changelog standard,
  template, and Computing Inputs hard rules (lifted from SKILL.md)

SKILL.md now reads as a router (~100 lines) with shared CI trigger
rules, post-release automation, precheck, and hard rules. Cross-links
between references replace the previous in-file jumps. Also fixes a
prettier-mangled redirect (`< some-pr-by-them >`) by using a `$PR`
variable instead of an angle-bracket placeholder.

* 📝 docs(version-release): add Hotfix and DB Migration variants to release-notes-style

The Canonical Structure was implicitly long-form (Minor / Weekly), and
hotfix authors had to read `changelog-example/hotfix.md` to learn it
existed. Make the divergence explicit:

- New § Variants for Shorter Releases describes Hotfix structure
  (Scope / What's Fixed / Upgrade / Owner) and DB Migration structure
  (Migration overview / Operator impact / Rollback) as overrides of the
  canonical long-form layout.
- Renamed the canonical section to "Canonical Structure (Long-Form:
  Minor / Weekly)" so the boundary is visible.
- Added Hotfix entry to Release Size Heuristics.
- Added a Hotfix subsection to Quick Checklist so the verification
  gates differ from long-form (no metric line / no Contributors / Owner
  resolved via gh).
2026-05-13 02:57:06 +08:00
YuTengjing 181b7eb117 🐛 fix: remove signin captcha flow (#14573) 2026-05-13 02:57:06 +08:00
YuTengjing 2bdd901ce2 🐛 fix: add temporary email auth error locale (#14564) 2026-05-13 02:57:06 +08:00
Rdmclin2 e4b5e52aff 🐛 fix: add bot callback service (#14570)
fix: add bot callback service
2026-05-13 02:57:06 +08:00
LiJian 1a6e07b5ef 🐛 fix: sanitize sensitive comments and examples from production JS bundle (#14557)
* 🐛 fix: sanitize sensitive comments and examples from production JS bundle

- Replace app.example.com with RFC 2606 example.com in agent-browser skill content
- Replace password-stdin examples with interactive auth prompts
- Remove hardcoded password-like strings from code examples
- Reword flagged code comments in page-agent system role

Addresses TAC Security CASA Tier 2 DAST Info findings:
Information Disclosure - Suspicious Comments (CWE-615)

The flagged strings appeared in SPA production bundles:
- /_spa/assets/chat-*.js
- /_spa/assets/index-*.js

* 🐛 fix: revert --interactive to --password-stdin in auth vault examples

The --interactive flag does not exist in agent-browser CLI (only --password
and --password-stdin are supported). Using --interactive would cause auth
save to fail and block login workflows.

Reverted both auth vault examples to use echo | --password-stdin pattern,
which pipes the password via stdin — the recommended secure approach.
2026-05-13 02:57:06 +08:00
Arvin Xu a7cc553212 💄 style(task): activity card stop run + register /tasks in SPA proxy (#14559)
*  feat(task): add stop run action to activity card menu

Surface the existing cancelTopic flow in the task detail activity card so
users can interrupt a running topic without opening the chat drawer.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

*  feat(task): confirm before stopping a running topic

Wrap the new Stop run action in a confirmModal so an accidental click can't
silently abort an in-flight run.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* 🐛 fix(spa): register /tasks and /task in SPA proxy matcher

Without these matcher entries, the Next.js middleware never rewrote /tasks
and /task/:taskId to the SPA catch-all, so the activity feed entries 404'd
in production builds even though the routes were wired in the SPA router.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-13 02:57:06 +08:00
YuTengjing c208723904 💄 style: update auth captcha retry copy (#14561) 2026-05-13 02:57:06 +08:00
Rdmclin2 760a342557 🐛 fix: multiple account link (#14562)
* feat: avoid rebind link same account

* chore: update i18n locales

* feat: avoid discord account misslink

* feat: support slack account mis match

* fix: avoid claim conflict
2026-05-13 02:57:06 +08:00
lobehubbot 0516184b45 🔖 chore(release): release version v2.1.57 [skip ci] 2026-05-09 13:36:15 +00:00
228 changed files with 2780 additions and 2192 deletions
+37
View File
@@ -2,6 +2,43 @@
# Changelog
## [Version 2.1.57](https://github.com/lobehub/lobe-chat/compare/v2.1.57-canary.33...v2.1.57)
<sup>Released on **2026-05-09**</sup>
#### 🐛 Bug Fixes
- **docker**: replace pnpm init with static package.json in /deps.
- **onboarding**: guard skip/mode-switch footer with feature flag, desktop & init checks.
- **misc**: hide runtime-only model aliases.
#### ✨ Features
- **misc**: set OSS default model to DeepSeek V4 Pro.
<br/>
<details>
<summary><kbd>Improvements and Fixes</kbd></summary>
#### What's fixed
- **docker**: replace pnpm init with static package.json in /deps, closes [#14576](https://github.com/lobehub/lobe-chat/issues/14576) ([8ed31df](https://github.com/lobehub/lobe-chat/commit/8ed31df))
- **onboarding**: guard skip/mode-switch footer with feature flag, desktop & init checks, closes [#14560](https://github.com/lobehub/lobe-chat/issues/14560) ([9756dab](https://github.com/lobehub/lobe-chat/commit/9756dab))
- **misc**: hide runtime-only model aliases, closes [#14552](https://github.com/lobehub/lobe-chat/issues/14552) ([2d33322](https://github.com/lobehub/lobe-chat/commit/2d33322))
#### What's improved
- **misc**: set OSS default model to DeepSeek V4 Pro, closes [#14555](https://github.com/lobehub/lobe-chat/issues/14555) ([8105fc0](https://github.com/lobehub/lobe-chat/commit/8105fc0))
</details>
<div align="right">
[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
</div>
### [Version 2.1.56](https://github.com/lobehub/lobe-chat/compare/v2.1.55...v2.1.56)
<sup>Released on **2026-05-01**</sup>
+1 -1
View File
@@ -318,7 +318,7 @@ export function registerAgentCommand(program: Command) {
}
// 1. Exec agent to get operationId
const input: Record<string, any> = { prompt: options.prompt };
const input: Record<string, any> = { prompt: options.prompt, trigger: 'cli' };
if (options.agentId) input.agentId = options.agentId;
if (deviceId) input.deviceId = deviceId;
if (options.slug) input.slug = options.slug;
+8
View File
@@ -1,4 +1,12 @@
[
{
"children": {
"fixes": ["hide runtime-only model aliases."],
"features": ["set OSS default model to DeepSeek V4 Pro."]
},
"date": "2026-05-09",
"version": "2.1.57"
},
{
"children": {},
"date": "2026-05-01",
+4
View File
@@ -115,6 +115,10 @@
"channel.line.fetchBotInfoMissingToken": "أدخل رمز الوصول للقناة أولاً، ثم انقر على \"Fetch from LINE\".",
"channel.line.fetchBotInfoSuccess": "تم جلب معرّف المستخدم الوجهة",
"channel.line.webhookManualSetup": "لا يسمح LINE بالتسجيل البرمجي للويب هوك. انسخ هذا الرابط إلى وحدة تحكم مطوري LINE (واجهة برمجة تطبيقات المراسلة → رابط الويب هوك)، انقر على \"تحقق\"، وقم بتمكين \"استخدام الويب هوك\".",
"channel.messengerPromo.action": "جرّب Messenger",
"channel.messengerPromo.desc": "لا حاجة لإعداد الروبوت. تحدث مع LobeHub على Slack، Discord، Telegram.",
"channel.messengerPromo.dismiss": "تجاهل",
"channel.messengerPromo.title": "تجاوز الإعداد",
"channel.openPlatform": "منصة مفتوحة",
"channel.platforms": "المنصات",
"channel.publicKey": "المفتاح العام",
+4 -3
View File
@@ -314,7 +314,7 @@
"openInNewWindow": "فتح في نافذة جديدة",
"operation.contextCompression": "السياق طويل جدًا، يتم ضغط السجل...",
"operation.execAgentRuntime": "جارٍ تحضير الرد",
"operation.execClientTask": نفيذ المهمة",
"operation.execClientSubAgent": شغيل الوكيل الفرعي",
"operation.execHeterogeneousAgent": "{{name}} قيد التشغيل",
"operation.execServerAgentRuntime": "جاري التشغيل… يمكنك تبديل المهام أو إغلاق الصفحة — ستستمر المهمة بالعمل.",
"operation.heterogeneousAgentFallback": "وكيل خارجي",
@@ -567,6 +567,7 @@
"taskList.contextMenu.copyLink": "نسخ الرابط",
"taskList.contextMenu.copyLinkSuccess": "تم نسخ الرابط",
"taskList.contextMenu.priority": "الأولوية",
"taskList.contextMenu.runNow": "تشغيل الآن",
"taskList.contextMenu.status": "الحالة",
"taskList.empty": "لا توجد مهام بعد",
"taskList.emptyHero.greeting": "ما الذي يجب أن نتعامل معه اليوم؟",
@@ -771,6 +772,8 @@
"workflow.toolDisplayName.addPreferenceMemory": "الذاكرة المحفوظة",
"workflow.toolDisplayName.calculate": "محسوب",
"workflow.toolDisplayName.callAgent": "تم استدعاء وكيل",
"workflow.toolDisplayName.callSubAgent": "تم إرسال وكيل فرعي",
"workflow.toolDisplayName.callSubAgents": "تم إرسال وكلاء فرعيين",
"workflow.toolDisplayName.clearTodos": "تم مسح المهام",
"workflow.toolDisplayName.copyDocument": "تم نسخ مستند",
"workflow.toolDisplayName.crawlMultiPages": "الصفحات التي تم الزحف إليها",
@@ -785,8 +788,6 @@
"workflow.toolDisplayName.editTitle": "العنوان المُعدَّل",
"workflow.toolDisplayName.evaluate": "التعبير المُقيَّم",
"workflow.toolDisplayName.execScript": "تم تنفيذ برنامج نصي",
"workflow.toolDisplayName.execTask": "تم تنفيذ مهمة",
"workflow.toolDisplayName.execTasks": "المهام المنفذة",
"workflow.toolDisplayName.execute": "تم تنفيذ العملية الحسابية",
"workflow.toolDisplayName.executeCode": "تم تنفيذ الشيفرة",
"workflow.toolDisplayName.finishOnboarding": "إنهاء الإعداد التعريفي",
+2
View File
@@ -349,6 +349,8 @@
"loading": "جارٍ التحميل...",
"mail.business": "تعاون تجاري",
"mail.support": "دعم عبر البريد الإلكتروني",
"messengerBanner.dismiss": "رفض",
"messengerBanner.title": "تحدث إلى Lobe AI عبر تطبيقات المراسلة المفضلة لديك",
"more": "المزيد",
"navPanel.agent": "الوكيل",
"navPanel.customizeSidebar": "تخصيص الشريط الجانبي",
-1
View File
@@ -35,7 +35,6 @@
"messenger.linkModal.notConfigured": "هذا الاتصال غير متاح حاليًا. يرجى المحاولة مرة أخرى لاحقًا.",
"messenger.linkModal.openCta": "افتح في {{platform}}",
"messenger.linkModal.scanHint": "أو امسح باستخدام هاتفك لفتح {{platform}}.",
"messenger.linkModal.title": "ربط المراسلة",
"messenger.list.discord.description": "تحدث مع وكلاء LobeHub الخاصين بك من أي خادم Discord عبر الرسائل الخاصة مع بوت LobeHub.",
"messenger.list.slack.description": "تحدث مع وكلاء LobeHub الخاصين بك من أي مساحة عمل Slack عبر الرسائل الخاصة أو @LobeHub.",
"messenger.list.telegram.description": "تحدث مع وكلاء LobeHub الخاصين بك في Telegram واختر من يجيب من أي مكان.",
+13 -20
View File
@@ -106,7 +106,6 @@
"MiniMax-Hailuo-2.3.description": "نموذج جديد لإنشاء الفيديو مع تحسينات شاملة في حركة الجسم، والواقعية الفيزيائية، واتباع التعليمات.",
"MiniMax-M1.description": "نموذج استدلال داخلي جديد بسلسلة تفكير تصل إلى 80K ومدخلات حتى 1M، يقدم أداءً مماثلاً لأفضل النماذج العالمية.",
"MiniMax-M2-Stable.description": "مصمم لتدفقات العمل البرمجية والوكلاء بكفاءة عالية، مع قدرة تزامن أعلى للاستخدام التجاري.",
"MiniMax-M2.1-Lightning.description": "قدرات برمجة متعددة اللغات قوية مع استنتاج أسرع وأكثر كفاءة.",
"MiniMax-M2.1-highspeed.description": "قدرات برمجة متعددة اللغات قوية، تجربة برمجة مطورة بشكل شامل. أسرع وأكثر كفاءة.",
"MiniMax-M2.1.description": "MiniMax-M2.1 هو نموذج مفتوح المصدر رائد من MiniMax، يركز على حل المهام الواقعية المعقدة. يتميز بقدرات برمجة متعددة اللغات والقدرة على أداء المهام المعقدة كوكلاء ذكي.",
"MiniMax-M2.5-highspeed.description": "MiniMax M2.5 Highspeed: نفس أداء M2.5 مع استدلال أسرع.",
@@ -315,13 +314,13 @@
"claude-3-haiku-20240307.description": "Claude 3 Haiku هو أسرع وأصغر نموذج من Anthropic، مصمم لتقديم استجابات شبه فورية بأداء سريع ودقيق.",
"claude-3-opus-20240229.description": "Claude 3 Opus هو أقوى نموذج من Anthropic للمهام المعقدة، يتميز بالأداء العالي، الذكاء، الطلاقة، والفهم.",
"claude-3-sonnet-20240229.description": "Claude 3 Sonnet يوازن بين الذكاء والسرعة لتلبية احتياجات المؤسسات، ويوفر فائدة عالية بتكلفة أقل ونشر موثوق على نطاق واسع.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 هو أسرع وأذكى نموذج Haiku من Anthropic، يتميز بسرعة البرق والتفكير الممتد.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 هو النموذج الأسرع والأذكى من Anthropic، يتميز بسرعة البرق وقدرات استدلال موسعة.",
"claude-haiku-4-5.description": "Claude Haiku 4.5 من Anthropic — نموذج Haiku من الجيل التالي مع تحسينات في التفكير والرؤية.",
"claude-haiku-4.5.description": "Claude Haiku 4.5 هو نموذج Haiku الأسرع والأذكى من Anthropic، يتميز بسرعة البرق وقدرات استدلال موسعة.",
"claude-opus-4-1-20250805-thinking.description": "Claude Opus 4.1 Thinking هو إصدار متقدم يمكنه عرض عملية تفكيره.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 هو أحدث وأقوى نموذج من Anthropic للمهام المعقدة للغاية، يتميز بالأداء والذكاء والطلاقة والفهم.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 هو أحدث وأقوى نموذج من Anthropic للمهام المعقدة للغاية، يتميز بالأداء العالي، الذكاء، الطلاقة، والفهم.",
"claude-opus-4-1.description": "Claude Opus 4.1 من Anthropic — نموذج تفكير متميز مع قدرات تحليل عميقة.",
"claude-opus-4-20250514.description": "Claude Opus 4 هو أقوى نموذج من Anthropic للمهام المعقدة للغاية، يتميز بالأداء والذكاء والطلاقة والفهم.",
"claude-opus-4-20250514.description": "Claude Opus 4 هو النموذج الأكثر قوة من Anthropic للمهام المعقدة للغاية، يتميز بالأداء العالي، الذكاء، الطلاقة، والاستيعاب.",
"claude-opus-4-5-20251101.description": "Claude Opus 4.5 هو النموذج الرائد من Anthropic، يجمع بين الذكاء الاستثنائي والأداء القابل للتوسع، مثالي للمهام المعقدة التي تتطلب استجابات عالية الجودة وتفكير متقدم.",
"claude-opus-4-5.description": "Claude Opus 4.5 من Anthropic — نموذج رئيسي مع تفكير وبرمجة من الدرجة الأولى.",
"claude-opus-4-6.description": "Claude Opus 4.6 من Anthropic — نافذة سياق 1M نموذج رئيسي مع تفكير متقدم.",
@@ -330,7 +329,7 @@
"claude-opus-4.6-fast.description": "Claude Opus 4.6 هو النموذج الأكثر ذكاءً من Anthropic لبناء الوكلاء والبرمجة.",
"claude-opus-4.6.description": "Claude Opus 4.6 هو النموذج الأكثر ذكاءً من Anthropic لبناء الوكلاء والبرمجة.",
"claude-sonnet-4-20250514-thinking.description": "Claude Sonnet 4 Thinking يمكنه تقديم استجابات شبه فورية أو تفكير متسلسل مرئي.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 هو النموذج الأكثر ذكاءً من Anthropic حتى الآن، يقدم استجابات شبه فورية أو تفكير ممتد خطوة بخطوة مع تحكم دقيق لمستخدمي API.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 يمكنه تقديم استجابات شبه فورية أو تفكير ممتد خطوة بخطوة مع عرض العملية.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5 هو النموذج الأكثر ذكاءً من Anthropic حتى الآن.",
"claude-sonnet-4-5.description": "Claude Sonnet 4.5 من Anthropic — نموذج Sonnet محسّن مع أداء برمجي معزز.",
"claude-sonnet-4-6.description": "Claude Sonnet 4.6 من Anthropic — أحدث نموذج Sonnet مع برمجة واستخدام أدوات متفوقة.",
@@ -404,7 +403,7 @@
"deepseek-ai/deepseek-llm-67b-chat.description": "DeepSeek LLM Chat (67B) هو نموذج مبتكر يوفر فهمًا عميقًا للغة وتفاعلًا ذكيًا.",
"deepseek-ai/deepseek-v3.1-terminus.description": "DeepSeek V3.1 هو نموذج تفكير من الجيل التالي يتمتع بقدرات أقوى في التفكير المعقد وسلسلة التفكير لمهام التحليل العميق.",
"deepseek-ai/deepseek-v3.2.description": "DeepSeek V3.2 هو نموذج استدلال من الجيل التالي يتميز بقدرات استدلال معقدة وسلسلة التفكير.",
"deepseek-chat.description": "اسم مستعار متوافق لوضع عدم التفكير في DeepSeek V4 Flash. مقرر إيقافه — استخدم DeepSeek V4 Flash بدلاً منه.",
"deepseek-chat.description": "نموذج مفتوح المصدر جديد يجمع بين القدرات العامة والبرمجية. يحافظ على حوار النموذج العام وقوة البرمجة للنموذج البرمجي، مع تحسين توافق التفضيلات. كما يحسن DeepSeek-V2.5 الكتابة واتباع التعليمات.",
"deepseek-coder-33B-instruct.description": "DeepSeek Coder 33B هو نموذج لغة برمجية تم تدريبه على 2 تريليون رمز (87٪ كود، 13٪ نص صيني/إنجليزي). يقدم نافذة سياق 16K ومهام الإكمال في المنتصف، ويوفر إكمال كود على مستوى المشاريع وملء مقاطع الكود.",
"deepseek-coder-v2.description": "DeepSeek Coder V2 هو نموذج كود MoE مفتوح المصدر يتميز بأداء قوي في مهام البرمجة، ويضاهي GPT-4 Turbo.",
"deepseek-coder-v2:236b.description": "DeepSeek Coder V2 هو نموذج كود MoE مفتوح المصدر يتميز بأداء قوي في مهام البرمجة، ويضاهي GPT-4 Turbo.",
@@ -426,7 +425,7 @@
"deepseek-r1-fast-online.description": "الإصدار الكامل السريع من DeepSeek R1 مع بحث ويب في الوقت الحقيقي، يجمع بين قدرات بحجم 671B واستجابة أسرع.",
"deepseek-r1-online.description": "الإصدار الكامل من DeepSeek R1 مع 671 مليار معلمة وبحث ويب في الوقت الحقيقي، يوفر فهمًا وتوليدًا أقوى.",
"deepseek-r1.description": "يستخدم DeepSeek-R1 بيانات البداية الباردة قبل التعلم المعزز ويؤدي أداءً مماثلًا لـ OpenAI-o1 في الرياضيات، والبرمجة، والتفكير.",
"deepseek-reasoner.description": "اسم مستعار متوافق لوضع التفكير في DeepSeek V4 Flash. مقرر إيقافه — استخدم DeepSeek V4 Flash بدلاً منه.",
"deepseek-reasoner.description": "نموذج DeepSeek مخصص لمهام الاستدلال المنطقي المعقدة.",
"deepseek-v2.description": "DeepSeek V2 هو نموذج MoE فعال لمعالجة منخفضة التكلفة.",
"deepseek-v2:236b.description": "DeepSeek V2 236B هو نموذج DeepSeek الموجه للبرمجة مع قدرات قوية في توليد الكود.",
"deepseek-v3-0324.description": "DeepSeek-V3-0324 هو نموذج MoE يحتوي على 671 مليار معلمة يتميز بقوة في البرمجة، والقدرات التقنية، وفهم السياق، والتعامل مع النصوص الطويلة.",
@@ -491,8 +490,6 @@
"doubao-seedream-4-0-250828.description": "Seedream 4.0 هو نموذج توليد صور من ByteDance Seed، يدعم إدخال النصوص والصور مع توليد صور عالية الجودة وقابلة للتحكم بدرجة كبيرة. يُولّد الصور من التعليمات النصية.",
"doubao-seedream-4-5-251128.description": "Seedream 4.5 هو أحدث نموذج متعدد الوسائط من ByteDance، يدمج قدرات تحويل النص إلى صورة، والصورة إلى صورة، وتوليد الصور بالجملة، مع دمج الفهم العام وقدرات الاستدلال. مقارنة بالإصدار السابق 4.0، يقدم جودة توليد محسّنة بشكل كبير، مع تحسين تناسق التحرير ودمج الصور المتعددة. يوفر تحكمًا أكثر دقة في التفاصيل البصرية، مما يجعل النصوص الصغيرة والوجوه الصغيرة أكثر طبيعية، ويحقق تخطيطًا وألوانًا أكثر انسجامًا، مما يعزز الجماليات العامة.",
"doubao-seedream-5-0-260128.description": "Doubao-Seedream-5.0-lite هو أحدث نموذج لتوليد الصور من ByteDance. لأول مرة، يدمج قدرات الاسترجاع عبر الإنترنت، مما يسمح له بتضمين معلومات الويب في الوقت الفعلي وتعزيز حداثة الصور المولدة. كما تم ترقية ذكاء النموذج، مما يمكنه من تفسير التعليمات المعقدة والمحتوى البصري بدقة. بالإضافة إلى ذلك، يقدم تغطية محسّنة للمعرفة العالمية، وتناسقًا مرجعيًا، وجودة توليد في السيناريوهات المهنية، مما يلبي بشكل أفضل احتياجات الإبداع البصري على مستوى المؤسسات.",
"dreamina-seedance-2-0-260128.description": "Seedance 2.0 من ByteDance هو النموذج الأكثر قوة لتوليد الفيديو، يدعم توليد الفيديو المرجعي متعدد الوسائط، تحرير الفيديو، تمديد الفيديو، تحويل النص إلى فيديو، وتحويل الصورة إلى فيديو مع صوت متزامن.",
"dreamina-seedance-2-0-fast-260128.description": "Seedance 2.0 Fast من ByteDance يقدم نفس القدرات مثل Seedance 2.0 مع سرعات توليد أسرع وسعر أكثر تنافسية.",
"emohaa.description": "Emohaa هو نموذج للصحة النفسية يتمتع بقدرات استشارية احترافية لمساعدة المستخدمين على فهم المشكلات العاطفية.",
"ernie-4.5-0.3b.description": "ERNIE 4.5 0.3B هو نموذج مفتوح المصدر وخفيف الوزن، مصمم للنشر المحلي والمخصص.",
"ernie-4.5-8k-preview.description": "ERNIE 4.5 8K Preview هو نموذج معاينة بسياق 8K لتقييم أداء ERNIE 4.5.",
@@ -517,8 +514,7 @@
"ernie-x1-turbo-32k.description": "ERNIE X1 Turbo 32K هو نموذج تفكير سريع بسياق 32K للاستدلال المعقد والدردشة متعددة الأدوار.",
"ernie-x1.1-preview.description": "معاينة ERNIE X1.1 هو نموذج تفكير مخصص للتقييم والاختبار.",
"ernie-x1.1.description": "ERNIE X1.1 هو نموذج تفكير تجريبي للتقييم والاختبار.",
"fal-ai/bytedance/seedream/v4.5.description": "Seedream 4.5، الذي تم تطويره بواسطة فريق ByteDance Seed، يدعم تحرير الصور المتعددة والتكوين. يتميز بتناسق الموضوع المحسن، اتباع التعليمات بدقة، فهم المنطق المكاني، التعبير الجمالي، تصميم الملصقات والشعارات مع تقديم النصوص والصور بدقة عالية.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0، الذي تم تطويره بواسطة ByteDance Seed، يدعم إدخال النصوص والصور لتوليد صور عالية الجودة وقابلة للتحكم بناءً على التعليمات.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0 هو نموذج توليد الصور من ByteDance Seed، يدعم إدخال النصوص والصور مع توليد صور عالية الجودة وقابلة للتحكم بشكل كبير. يقوم بتوليد الصور من التعليمات النصية.",
"fal-ai/flux-kontext/dev.description": "نموذج FLUX.1 يركز على تحرير الصور، ويدعم إدخال النصوص والصور.",
"fal-ai/flux-pro/kontext.description": "FLUX.1 Kontext [pro] يقبل النصوص وصور مرجعية كمدخلات، مما يتيح تعديلات محلية مستهدفة وتحولات معقدة في المشهد العام.",
"fal-ai/flux/krea.description": "Flux Krea [dev] هو نموذج لتوليد الصور يتميز بميول جمالية نحو صور أكثر واقعية وطبيعية.",
@@ -526,8 +522,8 @@
"fal-ai/hunyuan-image/v3.description": "نموذج قوي لتوليد الصور متعدد الوسائط أصلي.",
"fal-ai/imagen4/preview.description": "نموذج عالي الجودة لتوليد الصور من Google.",
"fal-ai/nano-banana.description": "Nano Banana هو أحدث وأسرع وأكثر نماذج Google كفاءةً لتوليد وتحرير الصور من خلال المحادثة.",
"fal-ai/qwen-image-edit.description": "نموذج تحرير الصور الاحترافي من فريق Qwen، يدعم التعديلات الدلالية والمظهر، تحرير النصوص الدقيقة باللغتين الصينية والإنجليزية، نقل الأسلوب، الدوران، والمزيد.",
"fal-ai/qwen-image.description": "نموذج قوي لتوليد الصور من فريق Qwen يتميز بتقديم نصوص صينية قوية وأنماط بصرية متنوعة.",
"fal-ai/qwen-image-edit.description": "نموذج تحرير الصور الاحترافي من فريق Qwen يدعم التعديلات الدلالية والمظهرية، ويحرر النصوص الصينية والإنجليزية بدقة، ويمكّن من تعديلات عالية الجودة مثل نقل الأنماط وتدوير الكائنات.",
"fal-ai/qwen-image.description": "نموذج توليد الصور القوي من فريق Qwen يتميز بعرض نصوص صينية مذهلة وأنماط بصرية متنوعة.",
"flux-1-schnell.description": "نموذج تحويل النص إلى صورة يحتوي على 12 مليار معلمة من Black Forest Labs يستخدم تقنيات تقطير الانتشار العدائي الكامن لتوليد صور عالية الجودة في 1-4 خطوات. ينافس البدائل المغلقة ومتاح بموجب ترخيص Apache-2.0 للاستخدام الشخصي والبحثي والتجاري.",
"flux-dev.description": "نموذج مفتوح المصدر مخصص لتوليد الصور لأغراض البحث والابتكار غير التجاري، مع تحسينات فعالة.",
"flux-kontext-max.description": "توليد وتحرير صور سياقية متقدمة، تجمع بين النصوص والصور لتحقيق نتائج دقيقة ومتسقة.",
@@ -569,7 +565,7 @@
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro) هو نموذج توليد الصور من Google ويدعم أيضًا الدردشة متعددة الوسائط.",
"gemini-3-pro-preview.description": "Gemini 3 Pro هو أقوى نموذج من Google للوكيل الذكي والبرمجة الإبداعية، يقدم تفاعلاً أعمق وصورًا أغنى مع استدلال متقدم.",
"gemini-3.1-flash-image-preview.description": "Gemini 3.1 Flash Image (Nano Banana 2) يقدم جودة صور احترافية بسرعة فائقة مع دعم الدردشة متعددة الوسائط.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) يقدم جودة صور بمستوى احترافي بسرعة Flash مع دعم الدردشة متعددة الوسائط.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) هو أسرع نموذج توليد صور أصلي من Google مع دعم التفكير، وتوليد الصور الحواري وتحريرها.",
"gemini-3.1-flash-lite-preview.description": "Gemini 3.1 Flash-Lite Preview هو النموذج الأكثر كفاءة من حيث التكلفة من Google، مُحسّن للمهام الوكيلة ذات الحجم الكبير، الترجمة، ومعالجة البيانات.",
"gemini-3.1-flash-lite.description": "Gemini 3.1 Flash-Lite هو النموذج متعدد الوسائط الأكثر كفاءة من Google، مُحسّن للمهام الوكيلية ذات الحجم الكبير، الترجمة، ومعالجة البيانات.",
"gemini-3.1-pro-preview.description": "Gemini 3.1 Pro Preview يحسن من Gemini 3 Pro مع قدرات استدلال محسّنة ويضيف دعم مستوى التفكير المتوسط.",
@@ -734,8 +730,6 @@
"grok-4-fast-reasoning.description": "يسعدنا إطلاق Grok 4 Fast، أحدث تقدم في نماذج الاستدلال منخفضة التكلفة.",
"grok-4.20-0309-non-reasoning.description": "نموذج غير تفكير للاستخدامات البسيطة.",
"grok-4.20-0309-reasoning.description": "نموذج ذكي وسريع للغاية يفكر قبل الرد.",
"grok-4.20-beta-0309-non-reasoning.description": "نسخة غير تفكيرية للاستخدامات البسيطة.",
"grok-4.20-beta-0309-reasoning.description": "نموذج ذكي وسريع للغاية يفكر قبل الرد.",
"grok-4.20-multi-agent-0309.description": "فريق من 4 أو 16 وكيلًا، يتفوق في حالات الاستخدام البحثية، لا يدعم حاليًا الأدوات على جانب العميل. يدعم فقط أدوات xAI على جانب الخادم (مثل X Search، أدوات البحث على الويب) وأدوات MCP البعيدة.",
"grok-4.3.description": "أكثر نموذج لغة كبير يسعى للحقيقة في العالم.",
"grok-4.description": "أحدث نموذج Grok الرائد بأداء لا مثيل له في اللغة، الرياضيات، والاستدلال — نموذج شامل حقيقي. يشير حاليًا إلى grok-4-0709؛ نظرًا للموارد المحدودة، فإن سعره مؤقتًا أعلى بنسبة 10% من السعر الرسمي ومن المتوقع أن يعود إلى السعر الرسمي لاحقًا.",
@@ -1220,8 +1214,6 @@
"qwq.description": "QwQ هو نموذج استدلال من عائلة Qwen. مقارنة بالنماذج المضبوطة على التعليمات، يقدم قدرات تفكير واستدلال تعزز الأداء بشكل كبير، خاصة في المشكلات الصعبة. QwQ-32B هو نموذج متوسط الحجم ينافس أفضل نماذج الاستدلال مثل DeepSeek-R1 و o1-mini.",
"qwq_32b.description": "نموذج استدلال متوسط الحجم من عائلة Qwen. مقارنة بالنماذج المضبوطة على التعليمات، تعزز قدرات التفكير والاستدلال في QwQ الأداء بشكل كبير، خاصة في المشكلات الصعبة.",
"r1-1776.description": "R1-1776 هو إصدار ما بعد التدريب من DeepSeek R1 مصمم لتقديم معلومات واقعية غير خاضعة للرقابة أو التحيز.",
"seedance-1-5-pro-251215.description": "Seedance 1.5 Pro من ByteDance يدعم تحويل النص إلى فيديو، تحويل الصورة إلى فيديو (الإطار الأول، الإطار الأول + الأخير)، وتوليد الصوت المتزامن مع المرئيات.",
"seedream-5-0-260128.description": "ByteDance-Seedream-5.0-lite من BytePlus يتميز بتوليد معزز بالاسترجاع عبر الويب للحصول على معلومات في الوقت الفعلي، تفسير معقد للتعليمات، وتحسين تناسق المرجع لإنشاء مرئيات احترافية.",
"solar-mini-ja.description": "Solar Mini (Ja) يوسع Solar Mini مع تركيز على اللغة اليابانية مع الحفاظ على الأداء القوي والكفاءة في الإنجليزية والكورية.",
"solar-mini.description": "Solar Mini هو نموذج لغة مدمج يتفوق على GPT-3.5، يتميز بقدرات متعددة اللغات قوية تدعم الإنجليزية والكورية، ويقدم حلاً فعالاً بصمة صغيرة.",
"solar-pro.description": "Solar Pro هو نموذج لغة عالي الذكاء من Upstage، يركز على اتباع التعليمات باستخدام وحدة معالجة رسومات واحدة، مع درجات IFEval تتجاوز 80. حالياً يدعم اللغة الإنجليزية؛ وكان من المقرر إصدار النسخة الكاملة في نوفمبر 2024 مع دعم لغات موسع وسياق أطول.",
@@ -1233,7 +1225,9 @@
"sophnet/deepseek-v3.2.description": "DeepSeek V3.2 هو نموذج يوازن بين الكفاءة الحسابية العالية وأداء الاستدلال والوكيل الممتاز.",
"sora-2-pro.description": "Sora 2 Pro هو نموذجنا الأكثر تقدمًا لتوليد الوسائط، يولد فيديوهات مع صوت متزامن. يمكنه إنشاء مقاطع غنية بالتفاصيل وديناميكية من اللغة الطبيعية أو الصور.",
"sora-2.description": "Sora 2 هو نموذجنا الجديد القوي لتوليد الوسائط، يولد فيديوهات مع صوت متزامن. يمكنه إنشاء مقاطع غنية بالتفاصيل وديناميكية من اللغة الطبيعية أو الصور.",
"spark-x.description": "نظرة عامة على قدرات X2: 1. يقدم تعديل ديناميكي لوضع الاستدلال، يتم التحكم فيه عبر الحقل `thinking`. 2. طول سياق موسع: 64K رموز إدخال و128K رموز إخراج. 3. يدعم وظيفة استدعاء الأدوات.",
"spark-x1.5.description": "تحديثات X1.5: (1) يضيف وضع التفكير الديناميكي الذي يتم التحكم فيه عبر حقل `thinking`; (2) طول سياق أكبر مع 64 ألف إدخال و64 ألف إخراج; (3) يدعم FunctionCall.",
"spark-x2-flash.description": "Spark X2-Flash يعتمد على بنية MoE (خليط الخبراء) مع 30 مليار معلمة إجمالية ويدعم نافذة سياق تصل إلى 256 ألف. يدعي تحسينات كبيرة في القدرات الوكالية والبرمجية، وتم تدريبه على مجموعة من معالجات Ascend 910B AI.",
"spark-x2.description": "نظرة عامة على قدرات X2: 1. يقدم تعديلًا ديناميكيًا لوضع الاستدلال، يتم التحكم فيه عبر حقل `thinking`. 2. طول سياق موسع: 64 ألف رمز إدخال و128 ألف رمز إخراج. 3. يدعم وظيفة Function Call.",
"stable-diffusion-3-medium.description": "أحدث نموذج تحويل النص إلى صورة من Stability AI. هذا الإصدار يحسن جودة الصور، وفهم النص، وتنوع الأساليب بشكل كبير، ويفسر التعليمات الطبيعية المعقدة بدقة أكبر وينتج صورًا أكثر دقة وتنوعًا.",
"stable-diffusion-3.5-large-turbo.description": "Stable Diffusion 3.5 Large Turbo يركز على توليد صور عالية الجودة مع قوة ممتازة في إظهار التفاصيل وواقعية المشاهد.",
"stable-diffusion-xl-base-1.0.description": "نموذج تحويل نص إلى صورة مفتوح المصدر من Stability AI يتميز بإبداع رائد في توليد الصور. يتمتع بفهم قوي للتعليمات ويدعم تعريف التعليمات العكسية لتوليد دقيق.",
@@ -1355,7 +1349,6 @@
"x-ai/grok-4.1-fast.description": "Grok 4.1 Fast هو نموذج عالي الإنتاجية ومنخفض التكلفة من xAI (يدعم نافذة سياق 2 مليون)، مثالي لحالات الاستخدام ذات التزامن العالي والسياق الطويل.",
"x-ai/grok-4.description": "Grok 4 هو النموذج الرائد من xAI بقدرات استدلال قوية ودعم متعدد الوسائط.",
"x-ai/grok-code-fast-1.description": "Grok Code Fast 1 هو نموذج سريع للبرمجة من xAI بإخراج قابل للقراءة ومناسب للهندسة.",
"x1.description": "تحديثات X1.5: (1) يضيف وضع التفكير الديناميكي الذي يتم التحكم فيه عبر الحقل `thinking`; (2) طول سياق أكبر مع 64K إدخال و64K إخراج; (3) يدعم وظيفة استدعاء الأدوات.",
"xai/grok-2-vision.description": "Grok 2 Vision يتفوّق في المهام البصرية، ويقدّم أداءً رائدًا في استدلال الرياضيات البصرية (MathVista) وأسئلة المستندات (DocVQA). يتعامل مع المستندات، والمخططات، والرسوم البيانية، ولقطات الشاشة، والصور.",
"xai/grok-2.description": "Grok 2 هو نموذج متقدم بأداء رائد في الاستدلال، والدردشة، والبرمجة، ويتفوّق على Claude 3.5 Sonnet وGPT-4 Turbo في تصنيفات LMSYS.",
"xai/grok-3-fast.description": "نموذج xAI الرائد يتفوّق في حالات الاستخدام المؤسسية مثل استخراج البيانات، والبرمجة، والتلخيص، مع معرفة عميقة في مجالات مثل المالية، والرعاية الصحية، والقانون، والعلوم. الإصدار السريع يعمل على بنية تحتية أسرع لتقديم استجابات أسرع بتكلفة أعلى لكل رمز.",
+21 -21
View File
@@ -69,9 +69,22 @@
"builtins.lobe-agent-management.render.installPlugin.plugin": "الملحق",
"builtins.lobe-agent-management.render.installPlugin.success": "تم التثبيت بنجاح",
"builtins.lobe-agent-management.title": "مدير الوكلاء",
"builtins.lobe-agent-marketplace.apiName.showAgentMarketplace": "افتح سوق الوكلاء",
"builtins.lobe-agent-marketplace.apiName.submitAgentPick": "إرسال اختيارات الوكلاء",
"builtins.lobe-agent-marketplace.title": "سوق الوكلاء",
"builtins.lobe-agent.apiName.callSubAgent": "استدعاء الوكيل الفرعي",
"builtins.lobe-agent.apiName.callSubAgent.completed": "تم إرسال الوكيل الفرعي: ",
"builtins.lobe-agent.apiName.callSubAgent.loading": "جارٍ إرسال الوكيل الفرعي: ",
"builtins.lobe-agent.apiName.callSubAgents": "استدعاء الوكلاء الفرعيين",
"builtins.lobe-agent.apiName.clearTodos": "مسح المهام",
"builtins.lobe-agent.apiName.clearTodos.modeAll": "الكل",
"builtins.lobe-agent.apiName.clearTodos.modeCompleted": "المكتملة",
"builtins.lobe-agent.apiName.clearTodos.result": "مسح <mode>{{mode}}</mode> المهام",
"builtins.lobe-agent.apiName.createPlan": "إنشاء خطة",
"builtins.lobe-agent.apiName.createPlan.result": "إنشاء خطة: <goal>{{goal}}</goal>",
"builtins.lobe-agent.apiName.createTodos": "إنشاء مهام",
"builtins.lobe-agent.apiName.updatePlan": "تحديث الخطة",
"builtins.lobe-agent.apiName.updatePlan.completed": "مكتمل",
"builtins.lobe-agent.apiName.updatePlan.modified": "تم التعديل",
"builtins.lobe-agent.apiName.updateTodos": "تحديث المهام",
"builtins.lobe-agent.title": "وكيل لوب",
"builtins.lobe-claude-code.agent.instruction": "تعليمات",
"builtins.lobe-claude-code.agent.result": "النتيجة",
"builtins.lobe-claude-code.todoWrite.allDone": "جميع المهام مكتملة",
@@ -139,24 +152,6 @@
"builtins.lobe-group-management.inspector.executeAgentTasks.title": "تعيين المهام إلى:",
"builtins.lobe-group-management.inspector.speak.title": "المتحدث المحدد:",
"builtins.lobe-group-management.title": "منسق المجموعة",
"builtins.lobe-gtd.apiName.clearTodos": "مسح المهام",
"builtins.lobe-gtd.apiName.clearTodos.modeAll": "الكل",
"builtins.lobe-gtd.apiName.clearTodos.modeCompleted": "المكتملة",
"builtins.lobe-gtd.apiName.clearTodos.result": "تم مسح المهام <mode>{{mode}}</mode>",
"builtins.lobe-gtd.apiName.completeTodos": "إكمال المهام",
"builtins.lobe-gtd.apiName.createPlan": "إنشاء خطة",
"builtins.lobe-gtd.apiName.createPlan.result": "تم إنشاء الخطة: <goal>{{goal}}</goal>",
"builtins.lobe-gtd.apiName.createTodos": "إنشاء مهام",
"builtins.lobe-gtd.apiName.execTask": "تنفيذ المهمة",
"builtins.lobe-gtd.apiName.execTask.completed": "تم إنشاء المهمة: ",
"builtins.lobe-gtd.apiName.execTask.loading": "جارٍ إنشاء المهمة: ",
"builtins.lobe-gtd.apiName.execTasks": "تنفيذ المهام",
"builtins.lobe-gtd.apiName.removeTodos": "حذف المهام",
"builtins.lobe-gtd.apiName.updatePlan": "تحديث الخطة",
"builtins.lobe-gtd.apiName.updatePlan.completed": "مكتملة",
"builtins.lobe-gtd.apiName.updatePlan.modified": "تم التعديل",
"builtins.lobe-gtd.apiName.updateTodos": "تحديث المهام",
"builtins.lobe-gtd.title": "أدوات المهام",
"builtins.lobe-knowledge-base.apiName.readKnowledge": "قراءة محتوى المكتبة",
"builtins.lobe-knowledge-base.apiName.searchKnowledgeBase": "البحث في المكتبة",
"builtins.lobe-knowledge-base.inspector.andMoreFiles": "و{{count}} ملفًا آخر",
@@ -317,6 +312,8 @@
"builtins.lobe-web-onboarding.apiName.finishOnboarding": "إنهاء الإعداد",
"builtins.lobe-web-onboarding.apiName.readDocument": "قراءة المستند",
"builtins.lobe-web-onboarding.apiName.saveUserQuestion": "حفظ سؤال المستخدم",
"builtins.lobe-web-onboarding.apiName.showAgentMarketplace": "تجميع فريق الوكلاء",
"builtins.lobe-web-onboarding.apiName.submitAgentPick": "إرسال اختيارات الوكلاء",
"builtins.lobe-web-onboarding.apiName.updateDocument": "تحديث المستند",
"builtins.lobe-web-onboarding.apiName.writeDocument": "كتابة المستند",
"builtins.lobe-web-onboarding.docType.persona": "شخصية المستخدم",
@@ -327,6 +324,9 @@
"builtins.lobe-web-onboarding.inspector.hunkCount_other": "{{count}} تغييرات",
"builtins.lobe-web-onboarding.inspector.interests_one": "{{count}} اهتمام",
"builtins.lobe-web-onboarding.inspector.interests_other": "{{count}} اهتمامات",
"builtins.lobe-web-onboarding.render.agent": "وكيل",
"builtins.lobe-web-onboarding.render.fullName": "الاسم الكامل",
"builtins.lobe-web-onboarding.render.interests": "الاهتمامات",
"builtins.lobe-web-onboarding.title": "إعداد المستخدم",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.delete": "حذف",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.deleteLines": "حذف الأسطر",
-1
View File
@@ -33,7 +33,6 @@
"jina.description": "تأسست Jina AI في عام 2020، وهي شركة رائدة في مجال البحث الذكي. تشمل تقنياتها نماذج المتجهات، ومعيدو الترتيب، ونماذج لغوية صغيرة لبناء تطبيقات بحث توليدية ومتعددة الوسائط عالية الجودة.",
"kimicodingplan.description": "كود Kimi من Moonshot AI يوفر الوصول إلى نماذج Kimi بما في ذلك K2.5 لأداء مهام الترميز.",
"lmstudio.description": "LM Studio هو تطبيق سطح مكتب لتطوير وتجربة النماذج اللغوية الكبيرة على جهازك.",
"lobehub.description": "يستخدم LobeHub Cloud واجهات برمجة التطبيقات الرسمية للوصول إلى نماذج الذكاء الاصطناعي ويقيس الاستخدام باستخدام أرصدة مرتبطة برموز النماذج.",
"longcat.description": "LongCat هو سلسلة من نماذج الذكاء الاصطناعي التوليدية الكبيرة التي تم تطويرها بشكل مستقل بواسطة Meituan. تم تصميمه لتعزيز إنتاجية المؤسسة الداخلية وتمكين التطبيقات المبتكرة من خلال بنية حسابية فعالة وقدرات متعددة الوسائط قوية.",
"minimax.description": "تأسست MiniMax في عام 2021، وتبني نماذج ذكاء اصطناعي متعددة الوسائط للأغراض العامة، بما في ذلك نماذج نصية بمليارات المعلمات، ونماذج صوتية وبصرية، بالإضافة إلى تطبيقات مثل Hailuo AI.",
"minimaxcodingplan.description": "خطة الرموز MiniMax توفر الوصول إلى نماذج MiniMax بما في ذلك M2.7 لأداء مهام الترميز عبر اشتراك ثابت الرسوم.",
-2
View File
@@ -913,8 +913,6 @@
"tools.builtins.lobe-agent-documents.title": "المستندات",
"tools.builtins.lobe-agent-management.description": "إنشاء الوكلاء وإدارتهم وتنظيم عملهم",
"tools.builtins.lobe-agent-management.title": "إدارة الوكلاء",
"tools.builtins.lobe-agent-marketplace.description": "عرض بطاقة سوق الوكلاء المختارة للمستخدمين وتسجيل القوالب التي يختارونها.",
"tools.builtins.lobe-agent-marketplace.title": "سوق الوكلاء",
"tools.builtins.lobe-artifacts.description": "إنشاء ومعاينة مكونات واجهة المستخدم التفاعلية، وتصوير البيانات، والمخططات، والرسومات بصيغة SVG، وتطبيقات الويب بشكل مباشر. أنشئ محتوى بصريًا غنيًا يمكن للمستخدمين التفاعل معه مباشرة.",
"tools.builtins.lobe-artifacts.readme": "أنشئ معاينات حية وتفاعلية لمكونات واجهة المستخدم، وتصوير البيانات، والمخططات، والرسومات بصيغة SVG، وتطبيقات الويب. أنشئ محتوى بصريًا غنيًا يمكن للمستخدمين التفاعل معه مباشرة.",
"tools.builtins.lobe-artifacts.title": "القطع الفنية",
+45 -45
View File
@@ -56,51 +56,51 @@
"dalle.generating": "جارٍ التوليد...",
"dalle.images": "الصور:",
"dalle.prompt": "الموجه",
"lobe-gtd.actions.add": "إضافة",
"lobe-gtd.actions.clearCompleted": "مسح المكتملة",
"lobe-gtd.actions.placeholder": "أدخل مهمة...",
"lobe-gtd.addTodo.placeholder": "أضف مهمة...",
"lobe-gtd.clearTodos.cleared": "تم مسح {{count}} عنصر(عناصر)",
"lobe-gtd.clearTodos.clearedCompleted": "تم مسح {{count}} عنصر(عناصر) مكتملة",
"lobe-gtd.clearTodos.clearedCompleted_one": "تم مسح عنصر مكتمل واحد",
"lobe-gtd.clearTodos.clearedCompleted_other": "تم مسح {{count}} عناصر مكتملة",
"lobe-gtd.clearTodos.cleared_one": "تم مسح عنصر واحد",
"lobe-gtd.clearTodos.cleared_other": "تم مسح {{count}} عناصر",
"lobe-gtd.clearTodos.header": "مسح المهام",
"lobe-gtd.clearTodos.label": "اختر ما تريد مسحه:",
"lobe-gtd.clearTodos.noItems": "لا توجد عناصر للمسح",
"lobe-gtd.clearTodos.option.all": "مسح جميع العناصر (بما في ذلك المعلقة)",
"lobe-gtd.clearTodos.option.completed": "مسح العناصر المكتملة فقط",
"lobe-gtd.clearTodos.remaining": "{{count}} عنصر(عناصر) متبقية",
"lobe-gtd.clearTodos.remaining_one": "عنصر واحد متبقٍ",
"lobe-gtd.clearTodos.remaining_other": "{{count}} عناصر متبقية",
"lobe-gtd.completeTodos.completed": "تم إكمال {{count}} عنصر(عناصر)",
"lobe-gtd.completeTodos.completed_one": "تم إكمال عنصر واحد",
"lobe-gtd.completeTodos.completed_other": "تم إكمال {{count}} عناصر",
"lobe-gtd.createPlan.context.label": "السياق (اختياري)",
"lobe-gtd.createPlan.context.placeholder": "الخلفية، القيود، الاعتبارات...",
"lobe-gtd.createPlan.description.label": "الوصف",
"lobe-gtd.createPlan.description.placeholder": "ملخص مختصر للخطة",
"lobe-gtd.createPlan.goal.label": "الهدف",
"lobe-gtd.createPlan.goal.placeholder": "ما الذي تريد تحقيقه؟",
"lobe-gtd.createTodos.created": "تم إنشاء {{count}} مهمة",
"lobe-gtd.createTodos.created_one": "تم إنشاء مهمة واحدة",
"lobe-gtd.createTodos.created_other": "تم إنشاء {{count}} مهام",
"lobe-gtd.createTodos.total": "الإجمالي: {{count}} عنصر(عناصر)",
"lobe-gtd.createTodos.total_one": "الإجمالي: عنصر واحد",
"lobe-gtd.createTodos.total_other": "الإجمالي: {{count}} عناصر",
"lobe-gtd.removeTodos.removed": "تمت إزالة {{count}} عنصر(عناصر)",
"lobe-gtd.removeTodos.removed_one": "تمت إزالة عنصر واحد",
"lobe-gtd.removeTodos.removed_other": "تمت إزالة {{count}} عناصر",
"lobe-gtd.status.done": "{{count}} مكتملة",
"lobe-gtd.status.pending": "{{count}} معلقة",
"lobe-gtd.todoItem.placeholder": "أدخل مهمة...",
"lobe-gtd.todoList.empty": "قائمة المهام فارغة",
"lobe-gtd.todoList.items": "{{count}} عنصر(عناصر)",
"lobe-gtd.todoList.items_one": "عنصر واحد",
"lobe-gtd.todoList.items_other": "{{count}} عناصر",
"lobe-gtd.todoList.title": "قائمة المهام",
"lobe-gtd.updateTodos.updated": "تم تحديث قائمة المهام",
"lobe-agent.actions.add": "إضافة",
"lobe-agent.actions.clearCompleted": "مسح المكتملة",
"lobe-agent.actions.placeholder": "أدخل مهمة للقيام بها...",
"lobe-agent.addTodo.placeholder": "أضف مهمة للقيام بها...",
"lobe-agent.clearTodos.cleared": "{{count}} عنصر(عناصر) تم مسحها",
"lobe-agent.clearTodos.clearedCompleted": "{{count}} عنصر(عناصر) مكتملة تم مسحها",
"lobe-agent.clearTodos.clearedCompleted_one": "{{count}} عنصر مكتمل تم مسحه",
"lobe-agent.clearTodos.clearedCompleted_other": "{{count}} عناصر مكتملة تم مسحها",
"lobe-agent.clearTodos.cleared_one": "{{count}} عنصر تم مسحه",
"lobe-agent.clearTodos.cleared_other": "{{count}} عناصر تم مسحها",
"lobe-agent.clearTodos.header": "مسح عناصر المهام",
"lobe-agent.clearTodos.label": "اختر ما تريد مسحه:",
"lobe-agent.clearTodos.noItems": "لا توجد عناصر للمسح",
"lobe-agent.clearTodos.option.all": "مسح جميع العناصر (بما في ذلك المعلقة)",
"lobe-agent.clearTodos.option.completed": "مسح العناصر المكتملة فقط",
"lobe-agent.clearTodos.remaining": "{{count}} عنصر(عناصر) متبقية",
"lobe-agent.clearTodos.remaining_one": "{{count}} عنصر متبقي",
"lobe-agent.clearTodos.remaining_other": "{{count}} عناصر متبقية",
"lobe-agent.completeTodos.completed": "{{count}} عنصر(عناصر) مكتملة",
"lobe-agent.completeTodos.completed_one": "{{count}} عنصر مكتمل",
"lobe-agent.completeTodos.completed_other": "{{count}} عناصر مكتملة",
"lobe-agent.createPlan.context.label": "السياق (اختياري)",
"lobe-agent.createPlan.context.placeholder": "الخلفية، القيود، الاعتبارات...",
"lobe-agent.createPlan.description.label": "الوصف",
"lobe-agent.createPlan.description.placeholder": "ملخص موجز للخطة",
"lobe-agent.createPlan.goal.label": "الهدف",
"lobe-agent.createPlan.goal.placeholder": "ما الذي تريد تحقيقه؟",
"lobe-agent.createTodos.created": "{{count}} عنصر(عناصر) للقيام بها تم إنشاؤها",
"lobe-agent.createTodos.created_one": "{{count}} عنصر للقيام به تم إنشاؤه",
"lobe-agent.createTodos.created_other": "{{count}} عناصر للقيام بها تم إنشاؤها",
"lobe-agent.createTodos.total": "الإجمالي: {{count}} عنصر(عناصر)",
"lobe-agent.createTodos.total_one": "الإجمالي: {{count}} عنصر",
"lobe-agent.createTodos.total_other": "الإجمالي: {{count}} عناصر",
"lobe-agent.removeTodos.removed": "{{count}} عنصر(عناصر) تم إزالتها",
"lobe-agent.removeTodos.removed_one": "{{count}} عنصر تم إزالته",
"lobe-agent.removeTodos.removed_other": "{{count}} عناصر تم إزالتها",
"lobe-agent.status.done": "{{count}} مكتملة",
"lobe-agent.status.pending": "{{count}} معلقة",
"lobe-agent.todoItem.placeholder": "أدخل مهمة للقيام بها...",
"lobe-agent.todoList.empty": "قائمة المهام فارغة",
"lobe-agent.todoList.items": "{{count}} عنصر(عناصر)",
"lobe-agent.todoList.items_one": "{{count}} عنصر",
"lobe-agent.todoList.items_other": "{{count}} عناصر",
"lobe-agent.todoList.title": "قائمة المهام",
"lobe-agent.updateTodos.updated": "تم تحديث قائمة المهام",
"lobe-knowledge-base.readKnowledge.meta.chars": "عدد الأحرف",
"lobe-knowledge-base.readKnowledge.meta.lines": "عدد الأسطر",
"localFiles.editFile.newString": "استبدال بـ",
+4
View File
@@ -115,6 +115,10 @@
"channel.line.fetchBotInfoMissingToken": "Първо въведете токена за достъп до канала, след това кликнете \"Извличане от LINE\".",
"channel.line.fetchBotInfoSuccess": "Потребителското ID на дестинацията е извлечено",
"channel.line.webhookManualSetup": "LINE не позволява програмно регистриране на уебхукове. Копирайте този URL в Конзолата за разработчици на LINE (Messaging API → Webhook URL), кликнете \"Проверка\" и активирайте \"Използване на уебхук\".",
"channel.messengerPromo.action": "Опитайте Messenger",
"channel.messengerPromo.desc": "Без настройка на бот. Чатете с LobeHub в Slack, Discord, Telegram.",
"channel.messengerPromo.dismiss": "Отхвърли",
"channel.messengerPromo.title": "Пропуснете настройката",
"channel.openPlatform": "Отворена платформа",
"channel.platforms": "Платформи",
"channel.publicKey": "Публичен ключ",
+4 -3
View File
@@ -314,7 +314,7 @@
"openInNewWindow": "Отвори в нов прозорец",
"operation.contextCompression": "Контекстът е твърде дълъг, компресиране на историята...",
"operation.execAgentRuntime": "Подготвяне на отговор",
"operation.execClientTask": "Изпълнение на задача",
"operation.execClientSubAgent": "Изпълнение на под-агент",
"operation.execHeterogeneousAgent": "{{name}} работи",
"operation.execServerAgentRuntime": "Изпълнява се… Можете да превключите задачи или да затворите страницата — задачата ще продължи.",
"operation.heterogeneousAgentFallback": "Външен агент",
@@ -567,6 +567,7 @@
"taskList.contextMenu.copyLink": "Копирай линк",
"taskList.contextMenu.copyLinkSuccess": "Линкът е копиран",
"taskList.contextMenu.priority": "Приоритет",
"taskList.contextMenu.runNow": "Изпълни сега",
"taskList.contextMenu.status": "Статус",
"taskList.empty": "Все още няма задачи",
"taskList.emptyHero.greeting": "С какво да се заемем днес?",
@@ -771,6 +772,8 @@
"workflow.toolDisplayName.addPreferenceMemory": "Запазена памет",
"workflow.toolDisplayName.calculate": "Изчислено",
"workflow.toolDisplayName.callAgent": "Извикан агент",
"workflow.toolDisplayName.callSubAgent": "Изпратен под-агент",
"workflow.toolDisplayName.callSubAgents": "Изпратени под-агенти",
"workflow.toolDisplayName.clearTodos": "Изчистени задачи",
"workflow.toolDisplayName.copyDocument": "Копиран документ",
"workflow.toolDisplayName.crawlMultiPages": "Обходени страници",
@@ -785,8 +788,6 @@
"workflow.toolDisplayName.editTitle": "Редактирано заглавие",
"workflow.toolDisplayName.evaluate": "Изчислен израз",
"workflow.toolDisplayName.execScript": "Изпълнен скрипт",
"workflow.toolDisplayName.execTask": "Изпълнена задача",
"workflow.toolDisplayName.execTasks": "Изпълнени задачи",
"workflow.toolDisplayName.execute": "Изпълнено изчисление",
"workflow.toolDisplayName.executeCode": "Изпълнен код",
"workflow.toolDisplayName.finishOnboarding": "Завършване на въвеждането",
+2
View File
@@ -349,6 +349,8 @@
"loading": "Зареждане...",
"mail.business": "Бизнес сътрудничество",
"mail.support": "Имейл поддръжка",
"messengerBanner.dismiss": "Затвори",
"messengerBanner.title": "Говорете с Lobe AI в любимите си приложения за съобщения",
"more": "Още",
"navPanel.agent": "Агент",
"navPanel.customizeSidebar": "Персонализиране на страничната лента",
-1
View File
@@ -35,7 +35,6 @@
"messenger.linkModal.notConfigured": "Тази връзка не е налична в момента. Моля, опитайте отново по-късно.",
"messenger.linkModal.openCta": "Отворете в {{platform}}",
"messenger.linkModal.scanHint": "Или сканирайте с телефона си, за да отворите {{platform}}.",
"messenger.linkModal.title": "Свързване на Messenger",
"messenger.list.discord.description": "Чатете с вашите агенти на LobeHub от всеки Discord сървър чрез лично съобщение с бота LobeHub.",
"messenger.list.slack.description": "Чатете с вашите агенти на LobeHub от всяко работно пространство в Slack чрез лично съобщение или @LobeHub.",
"messenger.list.telegram.description": "Чатете с вашите агенти на LobeHub в Telegram и изберете кой да отговаря от всяко място.",
+15 -22
View File
@@ -106,7 +106,6 @@
"MiniMax-Hailuo-2.3.description": "Чисто нов модел за видео генериране с цялостни подобрения в движенията на тялото, физическата реалистичност и следването на инструкции.",
"MiniMax-M1.description": "Нов вътрешен модел за разсъждение с 80K верига на мисълта и 1M вход, предлагащ производителност, сравнима с водещите глобални модели.",
"MiniMax-M2-Stable.description": "Създаден за ефективно програмиране и агентски работни потоци, с по-висока едновременност за търговска употреба.",
"MiniMax-M2.1-Lightning.description": "Мощни многоезични програмни възможности с по-бързо и ефективно извеждане.",
"MiniMax-M2.1-highspeed.description": "Мощни многоезични програмни възможности, цялостно подобрено програмиране. По-бързо и по-ефективно.",
"MiniMax-M2.1.description": "MiniMax-M2.1 е водеща отворена голяма езикова система от MiniMax, фокусирана върху решаването на сложни реални задачи. Основните ѝ предимства са възможностите за програмиране на множество езици и способността да действа като агент за решаване на сложни задачи.",
"MiniMax-M2.5-highspeed.description": "MiniMax M2.5 Highspeed: Същата производителност като M2.5, но с по-бързо извеждане.",
@@ -315,13 +314,13 @@
"claude-3-haiku-20240307.description": "Claude 3 Haiku е най-бързият и най-компактен модел на Anthropic, проектиран за почти мигновени отговори с бърза и точна производителност.",
"claude-3-opus-20240229.description": "Claude 3 Opus е най-мощният модел на Anthropic за силно сложни задачи, отличаващ се с производителност, интелигентност, плавност и разбиране.",
"claude-3-sonnet-20240229.description": "Claude 3 Sonnet балансира интелигентност и скорост за корпоративни натоварвания, осигурявайки висока полезност на по-ниска цена и надеждно мащабно внедряване.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 е най-бързият и интелигентен Haiku модел на Anthropic, с мълниеносна скорост и разширено мислене.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 е най-бързият и интелигентен Haiku модел на Anthropic, с мълниеносна скорост и разширено разсъждение.",
"claude-haiku-4-5.description": "Claude Haiku 4.5 от Anthropic — ново поколение Haiku с подобрено разсъждение и визия.",
"claude-haiku-4.5.description": "Claude Haiku 4.5 е най-бързият и най-умен Haiku модел на Anthropic, с мълниеносна скорост и разширено разсъждение.",
"claude-opus-4-1-20250805-thinking.description": "Claude Opus 4.1 Thinking е усъвършенстван вариант, който може да разкрие процеса си на разсъждение.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 е най-новият и най-способен модел на Anthropic за силно сложни задачи, превъзхождащ в производителност, интелигентност, плавност и разбиране.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 е най-новият и най-способен модел на Anthropic за изключително сложни задачи, отличаващ се с производителност, интелигентност, плавност и разбиране.",
"claude-opus-4-1.description": "Claude Opus 4.1 от Anthropic — премиум модел за дълбок анализ и разсъждение.",
"claude-opus-4-20250514.description": "Claude Opus 4 е най-мощният модел на Anthropic за силно сложни задачи, превъзхождащ в производителност, интелигентност, плавност и разбиране.",
"claude-opus-4-20250514.description": "Claude Opus 4 е най-мощният модел на Anthropic за изключително сложни задачи, отличаващ се с производителност, интелигентност, плавност и разбиране.",
"claude-opus-4-5-20251101.description": "Claude Opus 4.5 е флагманският модел на Anthropic, комбиниращ изключителна интелигентност с мащабируема производителност, идеален за сложни задачи, изискващи най-висококачествени отговори и разсъждение.",
"claude-opus-4-5.description": "Claude Opus 4.5 от Anthropic — флагмански модел с върхово разсъждение и кодови умения.",
"claude-opus-4-6.description": "Claude Opus 4.6 от Anthropic — флагман с 1M контекст и усъвършенствано разсъждение.",
@@ -330,8 +329,8 @@
"claude-opus-4.6-fast.description": "Claude Opus 4.6 е най-интелигентният модел на Anthropic за създаване на агенти и програмиране.",
"claude-opus-4.6.description": "Claude Opus 4.6 е най-интелигентният модел на Anthropic за създаване на агенти и програмиране.",
"claude-sonnet-4-20250514-thinking.description": "Claude Sonnet 4 Thinking може да генерира почти мигновени отговори или разширено стъпково мислене с видим процес.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 е най-интелигентният модел на Anthropic досега, предлагащ почти моментални отговори или разширено стъпка-по-стъпка мислене с фино управление за API потребители.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5 е най-интелигентният модел на Anthropic досега.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 може да генерира почти мигновени отговори или разширено стъпка по стъпка мислене с видим процес.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5 е най-интелигентният модел на Anthropic до момента.",
"claude-sonnet-4-5.description": "Claude Sonnet 4.5 от Anthropic — подобрен Sonnet с по‑силни кодови способности.",
"claude-sonnet-4-6.description": "Claude Sonnet 4.6 от Anthropic — последният Sonnet с превъзходно кодиране и работа с инструменти.",
"claude-sonnet-4.5.description": "Claude Sonnet 4.5 е най-интелигентният модел на Anthropic до момента.",
@@ -404,7 +403,7 @@
"deepseek-ai/deepseek-llm-67b-chat.description": "DeepSeek LLM Chat (67B) е иновативен модел, предлагащ дълбоко езиково разбиране и интеракция.",
"deepseek-ai/deepseek-v3.1-terminus.description": "DeepSeek V3.1 е модел за разсъждение от ново поколение с по-силни способности за сложни разсъждения и верига от мисли за задълбочени аналитични задачи.",
"deepseek-ai/deepseek-v3.2.description": "DeepSeek V3.2 е модел за разсъждение от следващо поколение с по-силни способности за сложни разсъждения и верига на мисълта.",
"deepseek-chat.description": "Съвместимостен псевдоним за режим без мислене на DeepSeek V4 Flash. Предстои да бъде премахнат — използвайте DeepSeek V4 Flash вместо него.",
"deepseek-chat.description": "Нов модел с отворен код, който комбинира общи и кодови способности. Той запазва общия диалогов модел и силното кодиране на кодовия модел, с по-добро съответствие на предпочитанията. DeepSeek-V2.5 също така подобрява писането и следването на инструкции.",
"deepseek-coder-33B-instruct.description": "DeepSeek Coder 33B е езиков модел за програмиране, обучен върху 2 трилиона токени (87% код, 13% китайски/английски текст). Въвежда 16K контекстен прозорец и задачи за попълване в средата, осигурявайки допълване на код на ниво проект и попълване на фрагменти.",
"deepseek-coder-v2.description": "DeepSeek Coder V2 е отворен MoE модел за програмиране, който се представя на ниво GPT-4 Turbo.",
"deepseek-coder-v2:236b.description": "DeepSeek Coder V2 е отворен MoE модел за програмиране, който се представя на ниво GPT-4 Turbo.",
@@ -426,7 +425,7 @@
"deepseek-r1-fast-online.description": "Пълна бърза версия на DeepSeek R1 с търсене в реално време в уеб, комбинираща възможности от мащаб 671B и по-бърз отговор.",
"deepseek-r1-online.description": "Пълна версия на DeepSeek R1 с 671 милиарда параметъра и търсене в реално време в уеб, предлагаща по-силно разбиране и генериране.",
"deepseek-r1.description": "DeepSeek-R1 използва данни от студен старт преди подсиленото обучение и се представя наравно с OpenAI-o1 в математика, програмиране и разсъждение.",
"deepseek-reasoner.description": "Съвместимостен псевдоним за режим с мислене на DeepSeek V4 Flash. Предстои да бъде премахнат — използвайте DeepSeek V4 Flash вместо него.",
"deepseek-reasoner.description": "Модел за разсъждение DeepSeek, фокусиран върху сложни логически задачи.",
"deepseek-v2.description": "DeepSeek V2 е ефективен MoE модел за икономична обработка.",
"deepseek-v2:236b.description": "DeepSeek V2 236B е модел на DeepSeek, фокусиран върху програмиране, с висока производителност при генериране на код.",
"deepseek-v3-0324.description": "DeepSeek-V3-0324 е MoE модел с 671 милиарда параметъра, с изключителни способности в програмиране, технически задачи, разбиране на контекст и обработка на дълги текстове.",
@@ -491,8 +490,6 @@
"doubao-seedream-4-0-250828.description": "Seedream 4.0 е модел за генериране на изображения от ByteDance Seed, поддържащ вход от текст и изображения с високо контролируемо, висококачествено генериране на изображения. Генерира изображения от текстови подсказки.",
"doubao-seedream-4-5-251128.description": "Seedream 4.5 е най-новият мултимодален модел за изображения на ByteDance, интегриращ текст-към-изображение, изображение-към-изображение и групово генериране на изображения, като включва обща логика и способности за разсъждение. В сравнение с предишната версия 4.0, той предлага значително подобрено качество на генериране, с по-добра консистентност при редактиране и мулти-изображение сливане. Осигурява по-прецизен контрол върху визуалните детайли, като произвежда малък текст и малки лица по-естествено, и постига по-хармонично оформление и цветове, подобрявайки цялостната естетика.",
"doubao-seedream-5-0-260128.description": "Doubao-Seedream-5.0-lite е най-новият модел за генериране на изображения на ByteDance. За първи път интегрира възможности за онлайн извличане, позволявайки му да включва информация в реално време от уеб и да подобрява актуалността на генерираните изображения. Интелигентността на модела също е подобрена, позволявайки прецизно интерпретиране на сложни инструкции и визуално съдържание. Освен това предлага подобрено глобално покритие на знания, консистентност на референциите и качество на генериране в професионални сценарии, по-добре отговаряйки на нуждите за визуално създаване на корпоративно ниво.",
"dreamina-seedance-2-0-260128.description": "Seedance 2.0 от ByteDance е най-мощният модел за генериране на видео, поддържащ мултимодално генериране на референтни видеа, редактиране на видео, разширение на видео, текст-към-видео и изображение-към-видео със синхронизиран аудио.",
"dreamina-seedance-2-0-fast-260128.description": "Seedance 2.0 Fast от ByteDance предлага същите възможности като Seedance 2.0 с по-бързи скорости на генериране на по-конкурентна цена.",
"emohaa.description": "Emohaa е модел за психично здраве с професионални консултантски способности, който помага на потребителите да разберат емоционални проблеми.",
"ernie-4.5-0.3b.description": "ERNIE 4.5 0.3B е лек модел с отворен код за локално и персонализирано внедряване.",
"ernie-4.5-8k-preview.description": "ERNIE 4.5 8K Preview е модел за предварителен преглед с 8K контекст за оценка на ERNIE 4.5.",
@@ -517,8 +514,7 @@
"ernie-x1-turbo-32k.description": "ERNIE X1 Turbo 32K е бърз мислещ модел с 32K контекст за сложни разсъждения и многозавойни разговори.",
"ernie-x1.1-preview.description": "ERNIE X1.1 Preview е предварителен модел за мислене, предназначен за оценка и тестване.",
"ernie-x1.1.description": "ERNIE X1.1 е мисловен модел за предварителен преглед за оценка и тестване.",
"fal-ai/bytedance/seedream/v4.5.description": "Seedream 4.5, създаден от екипа Seed на ByteDance, поддържа редактиране и композиция на множество изображения. Характеризира се с подобрена консистентност на обектите, прецизно следване на инструкции, разбиране на пространствена логика, естетично изразяване, оформление на плакати и дизайн на лого с високопрецизно рендиране на текст-изображение.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0, създаден от ByteDance Seed, поддържа текстови и визуални входове за силно контролируемо, висококачествено генериране на изображения от подсказки.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0 е модел за генериране на изображения от ByteDance Seed, който поддържа текстови и визуални входове с високо контролируемо и висококачествено генериране на изображения. Той генерира изображения от текстови подсказки.",
"fal-ai/flux-kontext/dev.description": "FLUX.1 модел, фокусиран върху редактиране на изображения, поддържащ вход от текст и изображения.",
"fal-ai/flux-pro/kontext.description": "FLUX.1 Kontext [pro] приема текст и референтни изображения като вход, позволявайки целенасочени локални редакции и сложни глобални трансформации на сцени.",
"fal-ai/flux/krea.description": "Flux Krea [dev] е модел за генериране на изображения с естетично предпочитание към по-реалистични и естествени изображения.",
@@ -526,8 +522,8 @@
"fal-ai/hunyuan-image/v3.description": "Мощен роден мултимодален модел за генериране на изображения.",
"fal-ai/imagen4/preview.description": "Модел за висококачествено генериране на изображения от Google.",
"fal-ai/nano-banana.description": "Nano Banana е най-новият, най-бърз и най-ефективен роден мултимодален модел на Google, позволяващ генериране и редактиране на изображения чрез разговор.",
"fal-ai/qwen-image-edit.description": "Професионален модел за редактиране на изображения от екипа Qwen, поддържащ семантични и визуални редакции, прецизно редактиране на текст на китайски/английски, трансфер на стил, ротация и други.",
"fal-ai/qwen-image.description": "Мощен модел за генериране на изображения от екипа Qwen със силно рендиране на текст на китайски и разнообразни визуални стилове.",
"fal-ai/qwen-image-edit.description": "Професионален модел за редактиране на изображения от екипа на Qwen, който поддържа семантични и визуални редакции, прецизно редактира китайски и английски текст и позволява висококачествени редакции като прехвърляне на стил и завъртане на обекти.",
"fal-ai/qwen-image.description": "Мощен модел за генериране на изображения от екипа на Qwen с впечатляващо рендиране на китайски текст и разнообразни визуални стилове.",
"flux-1-schnell.description": "Модел за преобразуване на текст в изображение с 12 милиарда параметъра от Black Forest Labs, използващ латентна дифузионна дестилация за генериране на висококачествени изображения в 1–4 стъпки. Съперничи на затворени алтернативи и е пуснат под лиценз Apache-2.0 за лична, изследователска и търговска употреба.",
"flux-dev.description": "Модел за генериране на изображения с отворен код, оптимизиран за неконкурентни изследвания и иновации.",
"flux-kontext-max.description": "Съвременно генериране и редактиране на изображения с контекст, комбиниращо текст и изображения за прецизни и последователни резултати.",
@@ -566,10 +562,10 @@
"gemini-3-flash-preview.description": "Gemini 3 Flash е най-интелигентният модел, създаден за скорост, съчетаващ авангардна интелигентност с отлично търсене и обоснованост.",
"gemini-3-flash.description": "Gemini 3 Flash от Google — ултрабърз модел с мултимодална поддръжка.",
"gemini-3-pro-image-preview.description": "Gemini 3 Pro Image (Nano Banana Pro) е модел за генериране на изображения на Google, който също поддържа мултимодален диалог.",
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro) е модел на Google за генериране на изображения и поддържа мултимодален чат.",
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro) е моделът на Google за генериране на изображения и също така поддържа мултимодален чат.",
"gemini-3-pro-preview.description": "Gemini 3 Pro е най-мощният агентен и „vibe-coding“ модел на Google, който предлага по-богати визуализации и по-дълбоко взаимодействие, базирано на съвременно логическо мислене.",
"gemini-3.1-flash-image-preview.description": "Gemini 3.1 Flash Image (Nano Banana 2) е най-бързият модел на Google за генериране на изображения с поддръжка на мислене, разговорно генериране и редактиране на изображения.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) предоставя качество на изображения от професионално ниво с Flash скорост и поддръжка на мултимодален чат.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) е най-бързият собствен модел на Google за генериране на изображения с поддръжка на мислене, разговорно генериране и редактиране на изображения.",
"gemini-3.1-flash-lite-preview.description": "Gemini 3.1 Flash-Lite Preview е най-икономичният мултимодален модел на Google, оптимизиран за задачи с голям обем, превод и обработка на данни.",
"gemini-3.1-flash-lite.description": "Gemini 3.1 Flash-Lite е най-икономичният мултимодален модел на Google, оптимизиран за задачи с голям обем, превод и обработка на данни.",
"gemini-3.1-pro-preview.description": "Gemini 3.1 Pro Preview подобрява Gemini 3 Pro с усъвършенствани способности за разсъждение и добавя поддръжка за средно ниво на мислене.",
@@ -734,8 +730,6 @@
"grok-4-fast-reasoning.description": "С гордост представяме Grok 4 Fast – нашият най-нов напредък в икономичните логически модели.",
"grok-4.20-0309-non-reasoning.description": "Неразсъждаващ вариант за прости случаи.",
"grok-4.20-0309-reasoning.description": "Интелигентен, изключително бърз модел с разсъждение.",
"grok-4.20-beta-0309-non-reasoning.description": "Вариант без разсъждения за прости случаи на употреба.",
"grok-4.20-beta-0309-reasoning.description": "Интелигентен, изключително бърз модел, който разсъждава преди да отговори.",
"grok-4.20-multi-agent-0309.description": "Екип от 4 или 16 агента — отличен за проучвания; поддържа само xAI сървърни инструменти.",
"grok-4.3.description": "Най-истинно търсещият голям езиков модел в света",
"grok-4.description": "Най-новият флагман Grok с ненадмината производителност в езика, математиката и разсъжденията — истински универсален модел. В момента сочи към grok-4-0709; поради ограничени ресурси временно е с 10% по-висока цена от официалната и се очаква да се върне към официалната цена по-късно.",
@@ -1220,8 +1214,6 @@
"qwq.description": "QwQ е модел за аргументация от семейството на Qwen. В сравнение със стандартните модели, обучени с инструкции, предлага мисловни и логически способности, които значително подобряват ефективността при трудни задачи. QwQ-32B е среден по размер модел, който се конкурира с водещи модели като DeepSeek-R1 и o1-mini.",
"qwq_32b.description": "Среден по размер модел за аргументация от семейството на Qwen. В сравнение със стандартните модели, обучени с инструкции, мисловните и логическите способности на QwQ значително подобряват ефективността при трудни задачи.",
"r1-1776.description": "R1-1776 е дообучен вариант на DeepSeek R1, създаден да предоставя неконфронтирана, обективна и фактическа информация.",
"seedance-1-5-pro-251215.description": "Seedance 1.5 Pro от ByteDance поддържа текст-към-видео, изображение-към-видео (първи кадър, първи+последен кадър) и генериране на аудио, синхронизирано с визуализации.",
"seedream-5-0-260128.description": "ByteDance-Seedream-5.0-lite от BytePlus предлага генериране, обогатено с уеб извличане за реална информация, подобрена интерпретация на сложни подсказки и подобрена консистентност на референциите за професионално визуално създаване.",
"solar-mini-ja.description": "Solar Mini (Ja) разширява Solar Mini с фокус върху японски език, като запазва ефективността и силната производителност на английски и корейски.",
"solar-mini.description": "Solar Mini е компактен LLM, който превъзхожда GPT-3.5, с мощни многоезични възможности, поддържащ английски и корейски, и предлага ефективно решение с малък отпечатък.",
"solar-pro.description": "Solar Pro е интелигентен LLM от Upstage, фокусиран върху следване на инструкции на един GPU, с IFEval резултати над 80. Понастоящем поддържа английски; пълното издание е планирано за ноември 2024 с разширена езикова поддръжка и по-дълъг контекст.",
@@ -1233,7 +1225,9 @@
"sophnet/deepseek-v3.2.description": "DeepSeek V3.2 е модел, който балансира висока изчислителна ефективност и отлична производителност за разсъждение и агенти.",
"sora-2-pro.description": "Sora 2 Pro е нашият най-съвременен, най-напреднал модел за генериране на медии, генериращ видеа със синхронизиран звук. Той може да създава богато детайлизирани, динамични клипове от естествен език или изображения.",
"sora-2.description": "Sora 2 е нашият нов мощен модел за генериране на медии, генериращ видеа със синхронизиран звук. Той може да създава богато детайлизирани, динамични клипове от естествен език или изображения.",
"spark-x.description": "Преглед на възможностите на X2: 1. Въвежда динамично регулиране на режима на разсъждение, контролирано чрез полето `thinking`. 2. Разширена дължина на контекста: 64K входни токени и 128K изходни токени. 3. Поддържа функционалност за извикване на функции.",
"spark-x1.5.description": "Актуализации на X1.5: (1) добавя динамичен режим на мислене, контролиран чрез полето `thinking`; (2) по-голяма дължина на контекста с 64K вход и 64K изход; (3) поддържа FunctionCall.",
"spark-x2-flash.description": "Spark X2-Flash използва архитектура MoE (Mixture of Experts) с общо 30 милиарда параметри и поддържа до 256K контекстен прозорец. Твърди се, че предлага значителни подобрения в агентните и кодиращите способности и е обучен на клъстер от AI процесори Ascend 910B.",
"spark-x2.description": "Преглед на възможностите на X2: 1. Въвежда динамично регулиране на режима на разсъждение, контролиран чрез полето `thinking`. 2. Разширена дължина на контекста: 64K входни токени и 128K изходни токени. 3. Поддържа функционалност за извикване на функции (Function Call).",
"stable-diffusion-3-medium.description": "Най-новият модел за преобразуване на текст в изображение от Stability AI. Тази версия значително подобрява качеството на изображенията, разбирането на текст и стиловото разнообразие, като по-точно интерпретира сложни естественоезикови заявки и генерира по-прецизни и разнообразни изображения.",
"stable-diffusion-3.5-large-turbo.description": "Stable Diffusion 3.5 Large Turbo е фокусиран върху висококачествено генериране на изображения с отлична детайлност и вярност на сцените.",
"stable-diffusion-xl-base-1.0.description": "Модел с отворен код за генериране на изображения от текст от Stability AI, предлагащ водещо в индустрията творческо качество. Притежава силно разбиране на инструкции и поддържа обратни дефиниции на подканите за прецизно генериране.",
@@ -1355,7 +1349,6 @@
"x-ai/grok-4.1-fast.description": "Grok 4 Fast е високопроизводителен, нискобюджетен модел на xAI (поддържа 2M контекст), идеален за случаи с висока едновременност и дълъг контекст.",
"x-ai/grok-4.description": "Grok 4 е водещ логически модел на xAI с мощни логически и мултимодални възможности.",
"x-ai/grok-code-fast-1.description": "Grok Code Fast 1 е бърз кодов модел на xAI с четим и удобен за инженеринг изход.",
"x1.description": "Актуализации на X1.5: (1) добавя динамичен режим на мислене, контролиран чрез полето `thinking`; (2) по-голяма дължина на контекста с 64K вход и 64K изход; (3) поддържа FunctionCall.",
"xai/grok-2-vision.description": "Grok 2 Vision се отличава във визуални задачи, постигайки водещи резултати във визуална математическа логика (MathVista) и въпроси и отговори по документи (DocVQA). Обработва документи, диаграми, графики, екранни снимки и снимки.",
"xai/grok-2.description": "Grok 2 е авангарден модел с водеща логика, силен чат, кодиране и логическа ефективност, надминаващ Claude 3.5 Sonnet и GPT-4 Turbo в LMSYS.",
"xai/grok-3-fast.description": "Водещият модел на xAI се отличава в корпоративни приложения като извличане на данни, кодиране и обобщаване, с дълбоки познания в области като финанси, здравеопазване, право и наука. Бързият вариант работи върху по-бърза инфраструктура за значително по-бързи отговори при по-висока цена на токен.",
+21 -21
View File
@@ -69,9 +69,22 @@
"builtins.lobe-agent-management.render.installPlugin.plugin": "Плъгин",
"builtins.lobe-agent-management.render.installPlugin.success": "Успешно инсталиран",
"builtins.lobe-agent-management.title": "Мениджър на агенти",
"builtins.lobe-agent-marketplace.apiName.showAgentMarketplace": "Отворете пазара за агенти",
"builtins.lobe-agent-marketplace.apiName.submitAgentPick": "Изпратете избора на агент",
"builtins.lobe-agent-marketplace.title": "Пазар за агенти",
"builtins.lobe-agent.apiName.callSubAgent": "Извикай под-агент",
"builtins.lobe-agent.apiName.callSubAgent.completed": "Под-агент изпратен: ",
"builtins.lobe-agent.apiName.callSubAgent.loading": "Изпращане на под-агент: ",
"builtins.lobe-agent.apiName.callSubAgents": "Извикай под-агенти",
"builtins.lobe-agent.apiName.clearTodos": "Изчисти задачи",
"builtins.lobe-agent.apiName.clearTodos.modeAll": "всички",
"builtins.lobe-agent.apiName.clearTodos.modeCompleted": "завършени",
"builtins.lobe-agent.apiName.clearTodos.result": "Изчисти <mode>{{mode}}</mode> задачи",
"builtins.lobe-agent.apiName.createPlan": "Създай план",
"builtins.lobe-agent.apiName.createPlan.result": "Създай план: <goal>{{goal}}</goal>",
"builtins.lobe-agent.apiName.createTodos": "Създай задачи",
"builtins.lobe-agent.apiName.updatePlan": "Актуализирай план",
"builtins.lobe-agent.apiName.updatePlan.completed": "Завършен",
"builtins.lobe-agent.apiName.updatePlan.modified": "Модифициран",
"builtins.lobe-agent.apiName.updateTodos": "Актуализирай задачи",
"builtins.lobe-agent.title": "Lobe Агент",
"builtins.lobe-claude-code.agent.instruction": "Инструкция",
"builtins.lobe-claude-code.agent.result": "Резултат",
"builtins.lobe-claude-code.todoWrite.allDone": "Всички задачи са изпълнени",
@@ -139,24 +152,6 @@
"builtins.lobe-group-management.inspector.executeAgentTasks.title": "Възлагане на задачи на:",
"builtins.lobe-group-management.inspector.speak.title": "Назначен агент говори:",
"builtins.lobe-group-management.title": "Координатор на група",
"builtins.lobe-gtd.apiName.clearTodos": "Изчистване на задачи",
"builtins.lobe-gtd.apiName.clearTodos.modeAll": "всички",
"builtins.lobe-gtd.apiName.clearTodos.modeCompleted": "завършени",
"builtins.lobe-gtd.apiName.clearTodos.result": "Изчистени <mode>{{mode}}</mode> задачи",
"builtins.lobe-gtd.apiName.completeTodos": "Завършване на задачи",
"builtins.lobe-gtd.apiName.createPlan": "Създаване на план",
"builtins.lobe-gtd.apiName.createPlan.result": "Създаден план: <goal>{{goal}}</goal>",
"builtins.lobe-gtd.apiName.createTodos": "Създаване на задачи",
"builtins.lobe-gtd.apiName.execTask": "Изпълнение на задача",
"builtins.lobe-gtd.apiName.execTask.completed": "Задачата е създадена: ",
"builtins.lobe-gtd.apiName.execTask.loading": "Създаване на задача: ",
"builtins.lobe-gtd.apiName.execTasks": "Изпълнение на задачи",
"builtins.lobe-gtd.apiName.removeTodos": "Изтриване на задачи",
"builtins.lobe-gtd.apiName.updatePlan": "Актуализиране на план",
"builtins.lobe-gtd.apiName.updatePlan.completed": "Завършен",
"builtins.lobe-gtd.apiName.updatePlan.modified": "Променен",
"builtins.lobe-gtd.apiName.updateTodos": "Актуализиране на задачи",
"builtins.lobe-gtd.title": "Инструменти за задачи",
"builtins.lobe-knowledge-base.apiName.readKnowledge": "Прочитане на съдържание от библиотеката",
"builtins.lobe-knowledge-base.apiName.searchKnowledgeBase": "Търсене в библиотеката",
"builtins.lobe-knowledge-base.inspector.andMoreFiles": "и още {{count}}",
@@ -317,6 +312,8 @@
"builtins.lobe-web-onboarding.apiName.finishOnboarding": "Завършване на въвеждането",
"builtins.lobe-web-onboarding.apiName.readDocument": "Прочетете документа",
"builtins.lobe-web-onboarding.apiName.saveUserQuestion": "Запазете въпроса на потребителя",
"builtins.lobe-web-onboarding.apiName.showAgentMarketplace": "Събери екип от агенти",
"builtins.lobe-web-onboarding.apiName.submitAgentPick": "Изпрати избора на агенти",
"builtins.lobe-web-onboarding.apiName.updateDocument": "Актуализирайте документа",
"builtins.lobe-web-onboarding.apiName.writeDocument": "Създаване на документ",
"builtins.lobe-web-onboarding.docType.persona": "Потребителски профил",
@@ -327,6 +324,9 @@
"builtins.lobe-web-onboarding.inspector.hunkCount_other": "{{count}} промени",
"builtins.lobe-web-onboarding.inspector.interests_one": "{{count}} интерес",
"builtins.lobe-web-onboarding.inspector.interests_other": "{{count}} интереса",
"builtins.lobe-web-onboarding.render.agent": "Агент",
"builtins.lobe-web-onboarding.render.fullName": "Пълно име",
"builtins.lobe-web-onboarding.render.interests": "Интереси",
"builtins.lobe-web-onboarding.title": "Въвеждане на потребител",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.delete": "Изтриване",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.deleteLines": "Изтриване на редове",
-1
View File
@@ -33,7 +33,6 @@
"jina.description": "Основана през 2020 г., Jina AI е водеща компания в областта на търсещия AI. Технологичният ѝ стек включва векторни модели, преоценители и малки езикови модели за създаване на надеждни генеративни и мултимодални търсещи приложения.",
"kimicodingplan.description": "Kimi Code от Moonshot AI предоставя достъп до модели Kimi, включително K2.5, за задачи, свързани с програмиране.",
"lmstudio.description": "LM Studio е десктоп приложение за разработка и експериментиране с LLM на вашия компютър.",
"lobehub.description": "LobeHub Cloud използва официални API, за да осъществява достъп до AI модели и измерва използването чрез Кредити, свързани с токените на модела.",
"longcat.description": "LongCat е серия от големи модели за генеративен AI, независимо разработени от Meituan. Той е създаден да подобри вътрешната продуктивност на предприятието и да позволи иновативни приложения чрез ефективна изчислителна архитектура и силни мултимодални възможности.",
"minimax.description": "Основана през 2021 г., MiniMax създава универсален AI с мултимодални базови модели, включително текстови модели с трилиони параметри, речеви и визуални модели, както и приложения като Hailuo AI.",
"minimaxcodingplan.description": "MiniMax Token Plan предоставя достъп до модели MiniMax, включително M2.7, за задачи, свързани с програмиране, чрез абонамент с фиксирана такса.",
-2
View File
@@ -913,8 +913,6 @@
"tools.builtins.lobe-agent-documents.title": "Документи",
"tools.builtins.lobe-agent-management.description": "Създаване, управление и оркестриране на AI агенти",
"tools.builtins.lobe-agent-management.title": "Управление на агенти",
"tools.builtins.lobe-agent-marketplace.description": "Показване на потребителите на подбрана карта на Пазара на агенти и записване на избраните от тях шаблони.",
"tools.builtins.lobe-agent-marketplace.title": "Пазар на агенти",
"tools.builtins.lobe-artifacts.description": "Генерирайте и визуализирайте интерактивни UI компоненти, визуализации на данни, диаграми, SVG графики и уеб приложения в реално време. Създавайте богато визуално съдържание, с което потребителите могат директно да взаимодействат.",
"tools.builtins.lobe-artifacts.readme": "Генерирайте и визуализирайте интерактивни UI компоненти, визуализации на данни, диаграми, SVG графики и уеб приложения в реално време. Създавайте богато визуално съдържание, с което потребителите могат директно да взаимодействат.",
"tools.builtins.lobe-artifacts.title": "Артефакти",
+45 -45
View File
@@ -56,51 +56,51 @@
"dalle.generating": "Генериране...",
"dalle.images": "Изображения:",
"dalle.prompt": "Подсказка",
"lobe-gtd.actions.add": "Добави",
"lobe-gtd.actions.clearCompleted": "Изчисти завършените",
"lobe-gtd.actions.placeholder": "Въведете задача...",
"lobe-gtd.addTodo.placeholder": "Добави задача...",
"lobe-gtd.clearTodos.cleared": "{{count}} елемент(а) изчистени",
"lobe-gtd.clearTodos.clearedCompleted": "{{count}} завършени елемент(а) изчистени",
"lobe-gtd.clearTodos.clearedCompleted_one": "{{count}} завършен елемент изчистен",
"lobe-gtd.clearTodos.clearedCompleted_other": "{{count}} завършени елемента изчистени",
"lobe-gtd.clearTodos.cleared_one": "{{count}} елемент изчистен",
"lobe-gtd.clearTodos.cleared_other": "{{count}} елемента изчистени",
"lobe-gtd.clearTodos.header": "Изчистване на задачи",
"lobe-gtd.clearTodos.label": "Изберете какво да се изчисти:",
"lobe-gtd.clearTodos.noItems": "Няма елементи за изчистване",
"lobe-gtd.clearTodos.option.all": "Изчисти всички елементи (включително чакащи)",
"lobe-gtd.clearTodos.option.completed": "Изчисти само завършените елементи",
"lobe-gtd.clearTodos.remaining": "{{count}} оставащ(и) елемент(а)",
"lobe-gtd.clearTodos.remaining_one": "{{count}} оставащ елемент",
"lobe-gtd.clearTodos.remaining_other": "{{count}} оставащи елемента",
"lobe-gtd.completeTodos.completed": "{{count}} елемент(а) завършени",
"lobe-gtd.completeTodos.completed_one": "{{count}} елемент завършен",
"lobe-gtd.completeTodos.completed_other": "{{count}} елемента завършени",
"lobe-gtd.createPlan.context.label": "Контекст (по избор)",
"lobe-gtd.createPlan.context.placeholder": "Фон, ограничения, съображения...",
"lobe-gtd.createPlan.description.label": "Описание",
"lobe-gtd.createPlan.description.placeholder": "Кратко обобщение на плана",
"lobe-gtd.createPlan.goal.label": "Цел",
"lobe-gtd.createPlan.goal.placeholder": "Какво искате да постигнете?",
"lobe-gtd.createTodos.created": "{{count}} задача(и) създадени",
"lobe-gtd.createTodos.created_one": "{{count}} задача създадена",
"lobe-gtd.createTodos.created_other": "{{count}} задачи създадени",
"lobe-gtd.createTodos.total": "Общо: {{count}} елемент(а)",
"lobe-gtd.createTodos.total_one": "Общо: {{count}} елемент",
"lobe-gtd.createTodos.total_other": "Общо: {{count}} елемента",
"lobe-gtd.removeTodos.removed": "{{count}} елемент(а) премахнати",
"lobe-gtd.removeTodos.removed_one": "{{count}} елемент премахнат",
"lobe-gtd.removeTodos.removed_other": "{{count}} елемента премахнати",
"lobe-gtd.status.done": "{{count}} завършени",
"lobe-gtd.status.pending": "{{count}} чакащи",
"lobe-gtd.todoItem.placeholder": "Въведете задача...",
"lobe-gtd.todoList.empty": "Списъкът със задачи е празен",
"lobe-gtd.todoList.items": "{{count}} елемент(а)",
"lobe-gtd.todoList.items_one": "{{count}} елемент",
"lobe-gtd.todoList.items_other": "{{count}} елемента",
"lobe-gtd.todoList.title": "Списък със задачи",
"lobe-gtd.updateTodos.updated": "Списъкът със задачи е обновен",
"lobe-agent.actions.add": "Добави",
"lobe-agent.actions.clearCompleted": "Изчисти завършените",
"lobe-agent.actions.placeholder": "Въведете задача...",
"lobe-agent.addTodo.placeholder": "Добавете задача...",
"lobe-agent.clearTodos.cleared": "{{count}} елемент(а) изчистен(и)",
"lobe-agent.clearTodos.clearedCompleted": "{{count}} завършен(и) елемент(а) изчистен(и)",
"lobe-agent.clearTodos.clearedCompleted_one": "{{count}} завършен елемент изчистен",
"lobe-agent.clearTodos.clearedCompleted_other": "{{count}} завършени елемента изчистени",
"lobe-agent.clearTodos.cleared_one": "{{count}} елемент изчистен",
"lobe-agent.clearTodos.cleared_other": "{{count}} елемента изчистени",
"lobe-agent.clearTodos.header": "Изчистване на задачи",
"lobe-agent.clearTodos.label": "Изберете какво да изчистите:",
"lobe-agent.clearTodos.noItems": "Няма елементи за изчистване",
"lobe-agent.clearTodos.option.all": "Изчисти всички елементи (включително чакащите)",
"lobe-agent.clearTodos.option.completed": "Изчисти само завършените елементи",
"lobe-agent.clearTodos.remaining": "{{count}} оставащ(и) елемент(а)",
"lobe-agent.clearTodos.remaining_one": "{{count}} оставащ елемент",
"lobe-agent.clearTodos.remaining_other": "{{count}} оставащи елемента",
"lobe-agent.completeTodos.completed": "{{count}} завършен(и) елемент(а)",
"lobe-agent.completeTodos.completed_one": "{{count}} завършен елемент",
"lobe-agent.completeTodos.completed_other": "{{count}} завършени елемента",
"lobe-agent.createPlan.context.label": "Контекст (по избор)",
"lobe-agent.createPlan.context.placeholder": "Фон, ограничения, съображения...",
"lobe-agent.createPlan.description.label": "Описание",
"lobe-agent.createPlan.description.placeholder": "Кратко резюме на плана",
"lobe-agent.createPlan.goal.label": "Цел",
"lobe-agent.createPlan.goal.placeholder": "Какво искате да постигнете?",
"lobe-agent.createTodos.created": "{{count}} задача(и) създадена(и)",
"lobe-agent.createTodos.created_one": "{{count}} задача създадена",
"lobe-agent.createTodos.created_other": "{{count}} задачи създадени",
"lobe-agent.createTodos.total": "Общо: {{count}} елемент(а)",
"lobe-agent.createTodos.total_one": "Общо: {{count}} елемент",
"lobe-agent.createTodos.total_other": "Общо: {{count}} елемента",
"lobe-agent.removeTodos.removed": "{{count}} елемент(а) премахнат(и)",
"lobe-agent.removeTodos.removed_one": "{{count}} елемент премахнат",
"lobe-agent.removeTodos.removed_other": "{{count}} елемента премахнати",
"lobe-agent.status.done": "{{count}} завършен(и)",
"lobe-agent.status.pending": "{{count}} чакащ(и)",
"lobe-agent.todoItem.placeholder": "Въведете задача...",
"lobe-agent.todoList.empty": "Списъкът със задачи е празен",
"lobe-agent.todoList.items": "{{count}} елемент(а)",
"lobe-agent.todoList.items_one": "{{count}} елемент",
"lobe-agent.todoList.items_other": "{{count}} елемента",
"lobe-agent.todoList.title": "Списък със задачи",
"lobe-agent.updateTodos.updated": "Списъкът със задачи е актуализиран",
"lobe-knowledge-base.readKnowledge.meta.chars": "Брой знаци",
"lobe-knowledge-base.readKnowledge.meta.lines": "Брой редове",
"localFiles.editFile.newString": "Замени с",
+4
View File
@@ -115,6 +115,10 @@
"channel.line.fetchBotInfoMissingToken": "Geben Sie zuerst das Kanalzugriffstoken ein und klicken Sie dann auf „Von LINE abrufen“.",
"channel.line.fetchBotInfoSuccess": "Ziel-Benutzer-ID abgerufen",
"channel.line.webhookManualSetup": "LINE erlaubt keine programmgesteuerte Webhook-Registrierung. Kopieren Sie diese URL in die LINE Developers Console (Messaging API → Webhook-URL), klicken Sie auf „Überprüfen“ und aktivieren Sie „Webhook verwenden“.",
"channel.messengerPromo.action": "Messenger ausprobieren",
"channel.messengerPromo.desc": "Keine Bot-Einrichtung. Chatten Sie mit LobeHub auf Slack, Discord, Telegram.",
"channel.messengerPromo.dismiss": "Schließen",
"channel.messengerPromo.title": "Überspringen Sie die Einrichtung",
"channel.openPlatform": "Offene Plattform",
"channel.platforms": "Plattformen",
"channel.publicKey": "Öffentlicher Schlüssel",
+4 -3
View File
@@ -314,7 +314,7 @@
"openInNewWindow": "In neuem Fenster öffnen",
"operation.contextCompression": "Kontext zu lang, komprimiere Verlauf...",
"operation.execAgentRuntime": "Antwort wird vorbereitet",
"operation.execClientTask": "Aufgabe wird ausgeführt",
"operation.execClientSubAgent": "Sub-Agent wird ausgeführt",
"operation.execHeterogeneousAgent": "{{name}} wird ausgeführt",
"operation.execServerAgentRuntime": "Wird ausgeführt… Sie können die Aufgabe wechseln oder die Seite schließen — die Aufgabe läuft weiter.",
"operation.heterogeneousAgentFallback": "Externer Agent",
@@ -567,6 +567,7 @@
"taskList.contextMenu.copyLink": "Link kopieren",
"taskList.contextMenu.copyLinkSuccess": "Link kopiert",
"taskList.contextMenu.priority": "Priorität",
"taskList.contextMenu.runNow": "Jetzt ausführen",
"taskList.contextMenu.status": "Status",
"taskList.empty": "Noch keine Aufgaben",
"taskList.emptyHero.greeting": "Woran sollen wir heute arbeiten?",
@@ -771,6 +772,8 @@
"workflow.toolDisplayName.addPreferenceMemory": "Gespeicherte Erinnerung",
"workflow.toolDisplayName.calculate": "Berechnet",
"workflow.toolDisplayName.callAgent": "Agent wurde aufgerufen",
"workflow.toolDisplayName.callSubAgent": "Ein Sub-Agent wurde gestartet",
"workflow.toolDisplayName.callSubAgents": "Sub-Agenten wurden gestartet",
"workflow.toolDisplayName.clearTodos": "Todos gelöscht",
"workflow.toolDisplayName.copyDocument": "Ein Dokument wurde kopiert",
"workflow.toolDisplayName.crawlMultiPages": "Gecrawlte Seiten",
@@ -785,8 +788,6 @@
"workflow.toolDisplayName.editTitle": "Bearbeiteter Titel",
"workflow.toolDisplayName.evaluate": "Ausgewerteter Ausdruck",
"workflow.toolDisplayName.execScript": "Skript wurde ausgeführt",
"workflow.toolDisplayName.execTask": "Eine Aufgabe ausgeführt",
"workflow.toolDisplayName.execTasks": "Ausgeführte Aufgaben",
"workflow.toolDisplayName.execute": "Berechnung ausgeführt",
"workflow.toolDisplayName.executeCode": "Code ausgeführt",
"workflow.toolDisplayName.finishOnboarding": "Onboarding abgeschlossen",
+2
View File
@@ -349,6 +349,8 @@
"loading": "Wird geladen...",
"mail.business": "Geschäftliche Anfragen",
"mail.support": "E-Mail-Support",
"messengerBanner.dismiss": "Schließen",
"messengerBanner.title": "Sprechen Sie mit Lobe AI über Ihre bevorzugten Messaging-Apps",
"more": "Mehr",
"navPanel.agent": "Agent",
"navPanel.customizeSidebar": "Seitenleiste anpassen",
-1
View File
@@ -35,7 +35,6 @@
"messenger.linkModal.notConfigured": "Diese Verbindung ist derzeit nicht verfügbar. Bitte versuchen Sie es später erneut.",
"messenger.linkModal.openCta": "In {{platform}} öffnen",
"messenger.linkModal.scanHint": "Oder scannen Sie mit Ihrem Telefon, um {{platform}} zu öffnen.",
"messenger.linkModal.title": "Messenger verbinden",
"messenger.list.discord.description": "Chatten Sie mit Ihren LobeHub-Agenten von jedem Discord-Server aus per DM mit dem LobeHub-Bot.",
"messenger.list.slack.description": "Chatten Sie mit Ihren LobeHub-Agenten von jedem Slack-Arbeitsbereich aus per DM oder @LobeHub.",
"messenger.list.telegram.description": "Chatten Sie mit Ihren LobeHub-Agenten in Telegram und wählen Sie, wer von überall antwortet.",
+13 -20
View File
@@ -106,7 +106,6 @@
"MiniMax-Hailuo-2.3.description": "Brandneues Videoerzeugungsmodell mit umfassenden Verbesserungen in Körperbewegung, physikalischem Realismus und Befolgung von Anweisungen.",
"MiniMax-M1.description": "Ein neues Inhouse-Argumentationsmodell mit 80K Chain-of-Thought und 1M Eingabe, vergleichbar mit führenden globalen Modellen.",
"MiniMax-M2-Stable.description": "Entwickelt für effizientes Coden und Agenten-Workflows mit höherer Parallelität für den kommerziellen Einsatz.",
"MiniMax-M2.1-Lightning.description": "Leistungsstarke mehrsprachige Programmierfähigkeiten mit schnellerer und effizienterer Inferenz.",
"MiniMax-M2.1-highspeed.description": "Leistungsstarke mehrsprachige Programmierfähigkeiten, umfassend verbesserte Programmiererfahrung. Schneller und effizienter.",
"MiniMax-M2.1.description": "MiniMax-M2.1 ist das Flaggschiff unter den Open-Source-Großmodellen von MiniMax und konzentriert sich auf die Lösung komplexer Aufgaben aus der realen Welt. Seine zentralen Stärken liegen in der mehrsprachigen Programmierfähigkeit und der Fähigkeit, als Agent komplexe Aufgaben zu bewältigen.",
"MiniMax-M2.5-highspeed.description": "MiniMax M2.5 Highspeed: Gleiche Leistung wie M2.5 mit schnellerer Inferenz.",
@@ -315,13 +314,13 @@
"claude-3-haiku-20240307.description": "Claude 3 Haiku ist das schnellste und kompakteste Modell von Anthropic, entwickelt für nahezu sofortige Antworten mit schneller, präziser Leistung.",
"claude-3-opus-20240229.description": "Claude 3 Opus ist das leistungsstärkste Modell von Anthropic für hochkomplexe Aufgaben. Es überzeugt in Leistung, Intelligenz, Sprachfluss und Verständnis.",
"claude-3-sonnet-20240229.description": "Claude 3 Sonnet bietet eine ausgewogene Kombination aus Intelligenz und Geschwindigkeit für Unternehmensanwendungen. Es liefert hohe Nutzbarkeit bei geringeren Kosten und zuverlässiger Skalierbarkeit.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 ist das schnellste und intelligenteste Haiku-Modell von Anthropic, mit blitzschneller Geschwindigkeit und erweitertem Denken.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 ist das schnellste und intelligenteste Haiku-Modell von Anthropic, mit blitzschneller Geschwindigkeit und erweitertem logischen Denken.",
"claude-haiku-4-5.description": "Claude Haiku 4.5 von Anthropic — Next-Gen-Haiku mit verbessertem Reasoning und Vision.",
"claude-haiku-4.5.description": "Claude Haiku 4.5 ist das schnellste und intelligenteste Haiku-Modell von Anthropic, mit blitzschneller Geschwindigkeit und erweiterten Denkfähigkeiten.",
"claude-opus-4-1-20250805-thinking.description": "Claude Opus 4.1 Thinking ist eine erweiterte Variante, die ihren Denkprozess offenlegen kann.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 ist das neueste und leistungsfähigste Modell von Anthropic für hochkomplexe Aufgaben, das in Leistung, Intelligenz, Sprachgewandtheit und Verständnis herausragt.",
"claude-opus-4-1.description": "Claude Opus 4.1 von Anthropic — Premium-Reasoning-Modell mit tiefgehender Analysefähigkeit.",
"claude-opus-4-20250514.description": "Claude Opus 4 ist das leistungsstärkste Modell von Anthropic für hochkomplexe Aufgaben, das in Leistung, Intelligenz, Sprachgewandtheit und Verständnis herausragt.",
"claude-opus-4-20250514.description": "Claude Opus 4 ist das leistungsstärkste Modell von Anthropic für hochkomplexe Aufgaben, das in Leistung, Intelligenz, Sprachgewandtheit und Verständnis überzeugt.",
"claude-opus-4-5-20251101.description": "Claude Opus 4.5 ist das Flaggschiffmodell von Anthropic. Es kombiniert herausragende Intelligenz mit skalierbarer Leistung und ist ideal für komplexe Aufgaben, die höchste Qualität bei Antworten und logischem Denken erfordern.",
"claude-opus-4-5.description": "Claude Opus 4.5 von Anthropic — Flaggschiffmodell mit erstklassigem Reasoning und Coding.",
"claude-opus-4-6.description": "Claude Opus 4.6 von Anthropic — Flaggschiffmodell mit 1M Kontextfenster und erweitertem Reasoning.",
@@ -330,7 +329,7 @@
"claude-opus-4.6-fast.description": "Claude Opus 4.6 ist das intelligenteste Modell von Anthropic für die Entwicklung von Agenten und Programmierung.",
"claude-opus-4.6.description": "Claude Opus 4.6 ist das intelligenteste Modell von Anthropic für die Entwicklung von Agenten und Programmierung.",
"claude-sonnet-4-20250514-thinking.description": "Claude Sonnet 4 Thinking kann nahezu sofortige Antworten oder schrittweises Denken mit sichtbarem Prozess erzeugen.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 ist das bisher intelligenteste Modell von Anthropic, das nahezu sofortige Antworten oder erweitertes schrittweises Denken mit fein abgestimmter Kontrolle für API-Nutzer bietet.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 kann nahezu sofortige Antworten oder ausführliches schrittweises Denken mit sichtbarem Prozess erzeugen.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5 ist das bisher intelligenteste Modell von Anthropic.",
"claude-sonnet-4-5.description": "Claude Sonnet 4.5 von Anthropic — weiterentwickeltes Sonnet mit verbesserter Coding-Leistung.",
"claude-sonnet-4-6.description": "Claude Sonnet 4.6 von Anthropic — neuestes Sonnet mit überlegener Coding- und Tool-Nutzung.",
@@ -404,7 +403,7 @@
"deepseek-ai/deepseek-llm-67b-chat.description": "DeepSeek LLM Chat (67B) ist ein innovatives Modell mit tiefem Sprachverständnis und Interaktionsfähigkeit.",
"deepseek-ai/deepseek-v3.1-terminus.description": "DeepSeek V3.1 ist ein Next-Gen-Denkmodell mit stärkerem komplexem Denken und Chain-of-Thought für tiefgreifende Analyseaufgaben.",
"deepseek-ai/deepseek-v3.2.description": "DeepSeek V3.2 ist ein Next-Gen-Modell für logisches Denken mit stärkeren Fähigkeiten für komplexes Denken und Kettenlogik.",
"deepseek-chat.description": "Kompatibilitätsalias für den Nicht-Denken-Modus von DeepSeek V4 Flash. Zur Einstellung vorgesehen verwenden Sie stattdessen DeepSeek V4 Flash.",
"deepseek-chat.description": "Ein neues Open-Source-Modell, das allgemeine und Code-Fähigkeiten kombiniert. Es bewahrt den allgemeinen Dialog des Chat-Modells und die starken Codierungsfähigkeiten des Coder-Modells, mit besserer Präferenzabstimmung. DeepSeek-V2.5 verbessert auch das Schreiben und das Befolgen von Anweisungen.",
"deepseek-coder-33B-instruct.description": "DeepSeek Coder 33B ist ein Code-Sprachmodell, trainiert auf 2B Tokens (87% Code, 13% chinesisch/englischer Text). Es bietet ein 16K-Kontextfenster und Fill-in-the-Middle-Aufgaben für projektweite Codevervollständigung und Snippet-Ergänzung.",
"deepseek-coder-v2.description": "DeepSeek Coder V2 ist ein Open-Source-MoE-Code-Modell mit starker Leistung bei Programmieraufgaben, vergleichbar mit GPT-4 Turbo.",
"deepseek-coder-v2:236b.description": "DeepSeek Coder V2 ist ein Open-Source-MoE-Code-Modell mit starker Leistung bei Programmieraufgaben, vergleichbar mit GPT-4 Turbo.",
@@ -426,7 +425,7 @@
"deepseek-r1-fast-online.description": "DeepSeek R1 Schnellversion mit Echtzeit-Websuche kombiniert 671B-Fähigkeiten mit schneller Reaktion.",
"deepseek-r1-online.description": "DeepSeek R1 Vollversion mit 671B Parametern und Echtzeit-Websuche bietet stärkeres Verständnis und bessere Generierung.",
"deepseek-r1.description": "DeepSeek-R1 nutzt Cold-Start-Daten vor dem RL und erreicht vergleichbare Leistungen wie OpenAI-o1 bei Mathematik, Programmierung und logischem Denken.",
"deepseek-reasoner.description": "Kompatibilitätsalias für den Denken-Modus von DeepSeek V4 Flash. Zur Einstellung vorgesehen verwenden Sie stattdessen DeepSeek V4 Flash.",
"deepseek-reasoner.description": "Ein DeepSeek-Logikmodell, das sich auf komplexe logische Denkaufgaben konzentriert.",
"deepseek-v2.description": "DeepSeek V2 ist ein effizientes MoE-Modell für kostengünstige Verarbeitung.",
"deepseek-v2:236b.description": "DeepSeek V2 236B ist das codefokussierte Modell von DeepSeek mit starker Codegenerierung.",
"deepseek-v3-0324.description": "DeepSeek-V3-0324 ist ein MoE-Modell mit 671B Parametern und herausragenden Stärken in Programmierung, technischer Kompetenz, Kontextverständnis und Langtextverarbeitung.",
@@ -491,8 +490,6 @@
"doubao-seedream-4-0-250828.description": "Seedream 4.0 ist ein Bildgenerierungsmodell von ByteDance Seed, das Text- und Bildeingaben unterstützt und eine hochgradig kontrollierbare, hochwertige Bildgenerierung ermöglicht. Es erzeugt Bilder aus Texteingaben.",
"doubao-seedream-4-5-251128.description": "Seedream 4.5 ist das neueste multimodale Bildmodell von ByteDance, das Text-zu-Bild, Bild-zu-Bild und Batch-Bilderzeugung integriert und dabei Allgemeinwissen und logisches Denken einbezieht. Im Vergleich zur vorherigen Version 4.0 bietet es eine deutlich verbesserte Generierungsqualität, bessere Konsistenz bei der Bearbeitung und Multi-Bild-Fusion. Es ermöglicht eine präzisere Kontrolle über visuelle Details, erzeugt kleine Texte und kleine Gesichter natürlicher und erreicht harmonischere Layouts und Farben, wodurch die Gesamtästhetik verbessert wird.",
"doubao-seedream-5-0-260128.description": "Doubao-Seedream-5.0-lite ist das neueste Bildgenerierungsmodell von ByteDance. Erstmals integriert es Online-Retrieval-Funktionen, die es ermöglichen, Echtzeit-Webinformationen einzubeziehen und die Aktualität der generierten Bilder zu verbessern. Die Intelligenz des Modells wurde ebenfalls aufgerüstet, um komplexe Anweisungen und visuelle Inhalte präzise zu interpretieren. Darüber hinaus bietet es eine verbesserte globale Wissensabdeckung, Konsistenz bei Referenzen und Generierungsqualität in professionellen Szenarien, um den visuellen Erstellungsbedarf auf Unternehmensebene besser zu erfüllen.",
"dreamina-seedance-2-0-260128.description": "Seedance 2.0 von ByteDance ist das leistungsstärkste Videogenerierungsmodell, das multimodale Referenzvideogenerierung, Videobearbeitung, Videoerweiterung, Text-zu-Video und Bild-zu-Video mit synchronisiertem Audio unterstützt.",
"dreamina-seedance-2-0-fast-260128.description": "Seedance 2.0 Fast von ByteDance bietet die gleichen Funktionen wie Seedance 2.0 mit schnelleren Generierungsgeschwindigkeiten zu einem wettbewerbsfähigeren Preis.",
"emohaa.description": "Emohaa ist ein Modell für psychische Gesundheit mit professionellen Beratungsfähigkeiten, das Nutzern hilft, emotionale Probleme zu verstehen.",
"ernie-4.5-0.3b.description": "ERNIE 4.5 0.3B ist ein quelloffenes, leichtgewichtiges Modell für lokale und individuell angepasste Bereitstellungen.",
"ernie-4.5-8k-preview.description": "ERNIE 4.5 8K Preview ist ein Vorschau-Modell mit 8K Kontextlänge zur Bewertung von ERNIE 4.5.",
@@ -517,8 +514,7 @@
"ernie-x1-turbo-32k.description": "ERNIE X1 Turbo 32K ist ein schnelles Denkmodell mit 32K Kontext für komplexe Schlussfolgerungen und mehrstufige Gespräche.",
"ernie-x1.1-preview.description": "ERNIE X1.1 Preview ist ein Vorschau-Modell mit Denkfähigkeit zur Bewertung und zum Testen.",
"ernie-x1.1.description": "ERNIE X1.1 ist ein Vorschau-Denkmodell für Evaluierung und Tests.",
"fal-ai/bytedance/seedream/v4.5.description": "Seedream 4.5, entwickelt vom ByteDance Seed-Team, unterstützt Multi-Bild-Bearbeitung und -Komposition. Es bietet verbesserte Konsistenz von Subjekten, präzise Befolgung von Anweisungen, Verständnis räumlicher Logik, ästhetischen Ausdruck, Poster-Layout und Logo-Design mit hochpräziser Text-Bild-Rendering.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0, entwickelt von ByteDance Seed, unterstützt Text- und Bildeingaben für hochkontrollierbare, qualitativ hochwertige Bildgenerierung aus Eingabeaufforderungen.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0 ist ein Bildgenerierungsmodell von ByteDance Seed, das Text- und Bildeingaben unterstützt und hochkontrollierbare, qualitativ hochwertige Bilder generiert. Es erstellt Bilder basierend auf Textaufforderungen.",
"fal-ai/flux-kontext/dev.description": "FLUX.1-Modell mit Fokus auf Bildbearbeitung, unterstützt Text- und Bildeingaben.",
"fal-ai/flux-pro/kontext.description": "FLUX.1 Kontext [pro] akzeptiert Texte und Referenzbilder als Eingabe und ermöglicht gezielte lokale Bearbeitungen sowie komplexe globale Szenentransformationen.",
"fal-ai/flux/krea.description": "Flux Krea [dev] ist ein Bildgenerierungsmodell mit ästhetischer Ausrichtung auf realistischere, natürliche Bilder.",
@@ -526,8 +522,8 @@
"fal-ai/hunyuan-image/v3.description": "Ein leistungsstarkes natives multimodales Bildgenerierungsmodell.",
"fal-ai/imagen4/preview.description": "Hochwertiges Bildgenerierungsmodell von Google.",
"fal-ai/nano-banana.description": "Nano Banana ist das neueste, schnellste und effizienteste native multimodale Modell von Google. Es ermöglicht Bildgenerierung und -bearbeitung im Dialog.",
"fal-ai/qwen-image-edit.description": "Ein professionelles Bildbearbeitungsmodell vom Qwen-Team, das semantische und optische Bearbeitungen, präzise chinesische/englische Textbearbeitung, Stilübertragungen, Drehungen und mehr unterstützt.",
"fal-ai/qwen-image.description": "Ein leistungsstarkes Bildgenerierungsmodell vom Qwen-Team mit starker chinesischer Textrendering-Fähigkeit und vielfältigen visuellen Stilen.",
"fal-ai/qwen-image-edit.description": "Ein professionelles Bildbearbeitungsmodell des Qwen-Teams, das semantische und optische Bearbeitungen unterstützt, präzise chinesische und englische Texte bearbeitet und hochwertige Bearbeitungen wie Stilübertragungen und Objektrotation ermöglicht.",
"fal-ai/qwen-image.description": "Ein leistungsstarkes Bildgenerierungsmodell des Qwen-Teams mit beeindruckender chinesischer Textdarstellung und vielfältigen visuellen Stilen.",
"flux-1-schnell.description": "Ein Text-zu-Bild-Modell mit 12 Milliarden Parametern von Black Forest Labs, das latente adversariale Diffusionsdistillation nutzt, um hochwertige Bilder in 14 Schritten zu erzeugen. Es konkurriert mit geschlossenen Alternativen und ist unter Apache-2.0 für persönliche, Forschungs- und kommerzielle Nutzung verfügbar.",
"flux-dev.description": "Open-SourceBildgenerierungsmodell für Forschung und Entwicklung, effizient optimiert für nichtkommerzielle Innovationsforschung.",
"flux-kontext-max.description": "Modernste kontextuelle Bildgenerierung und -bearbeitung, kombiniert Text und Bilder für präzise, kohärente Ergebnisse.",
@@ -566,10 +562,10 @@
"gemini-3-flash-preview.description": "Gemini 3 Flash ist das intelligenteste Modell, das auf Geschwindigkeit ausgelegt ist es vereint modernste Intelligenz mit exzellenter Suchverankerung.",
"gemini-3-flash.description": "Gemini 3 Flash von Google — ultraschnelles Modell mit Unterstützung für multimodale Eingaben.",
"gemini-3-pro-image-preview.description": "Gemini 3 Pro Image (Nano Banana Pro) ist Googles Bildgenerierungsmodell, das auch multimodale Dialoge unterstützt.",
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro) ist Googles Bildgenerierungsmodell und unterstützt auch multimodalen Chat.",
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro) ist Googles Bildgenerierungsmodell und unterstützt auch multimodale Chats.",
"gemini-3-pro-preview.description": "Gemini 3 Pro ist Googles leistungsstärkstes Agenten- und Vibe-Coding-Modell. Es bietet reichhaltigere visuelle Inhalte und tiefere Interaktionen auf Basis modernster logischer Fähigkeiten.",
"gemini-3.1-flash-image-preview.description": "Gemini 3.1 Flash Image (Nano Banana 2) ist Googles schnellstes natives Bildgenerierungsmodell mit Denkunterstützung, konversationaler Bildgenerierung und -bearbeitung.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) liefert Pro-Bildqualität mit Flash-Geschwindigkeit und unterstützt multimodalen Chat.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) ist Googles schnellstes natives Bildgenerierungsmodell mit Unterstützung für Denken, konversationelle Bildgenerierung und -bearbeitung.",
"gemini-3.1-flash-lite-preview.description": "Gemini 3.1 Flash-Lite Preview ist Googles kosteneffizientestes multimodales Modell, optimiert für hochvolumige agentische Aufgaben, Übersetzung und Datenverarbeitung.",
"gemini-3.1-flash-lite.description": "Gemini 3.1 Flash-Lite ist Googles kosteneffizientestes multimodales Modell, optimiert für hochvolumige agentenbasierte Aufgaben, Übersetzungen und Datenverarbeitung.",
"gemini-3.1-pro-preview.description": "Gemini 3.1 Pro Preview verbessert Gemini 3 Pro mit erweiterten Fähigkeiten für logisches Denken und unterstützt mittleres Denklevel.",
@@ -734,8 +730,6 @@
"grok-4-fast-reasoning.description": "Wir freuen uns, Grok 4 Fast vorzustellen unser neuester Fortschritt bei kosteneffizienten Denkmodellen.",
"grok-4.20-0309-non-reasoning.description": "Eine Non-Reasoning-Variante für einfache Anwendungsfälle.",
"grok-4.20-0309-reasoning.description": "Intelligentes, extrem schnelles Modell, das vor der Antwort aktiv denkt.",
"grok-4.20-beta-0309-non-reasoning.description": "Eine Nicht-Denken-Variante für einfache Anwendungsfälle.",
"grok-4.20-beta-0309-reasoning.description": "Intelligentes, blitzschnelles Modell, das vor der Antwort überlegt.",
"grok-4.20-multi-agent-0309.description": "Ein Team aus 4 oder 16 Agenten, hervorragend für Rechercheaufgaben. Unterstützt derzeit keine clientseitigen Tools. Unterstützt ausschließlich serverseitige xAI-Tools (z. B. X Search, Web Search Tools) und Remote-MCP-Tools.",
"grok-4.3.description": "Das wahrheitssuchendste große Sprachmodell der Welt",
"grok-4.description": "Das neueste Grok-Flaggschiff mit unvergleichlicher Leistung in Sprache, Mathematik und Logik — ein wahrer Alleskönner. Derzeit verweist es auf grok-4-0709; aufgrund begrenzter Ressourcen ist der Preis vorübergehend 10 % höher als der offizielle Preis und wird voraussichtlich später wieder auf den offiziellen Preis zurückkehren.",
@@ -1220,8 +1214,6 @@
"qwq.description": "QwQ ist ein Schlussfolgerungsmodell aus der Qwen-Familie. Im Vergleich zu standardmäßig instruktionstunierten Modellen bietet es überlegene Denk- und Schlussfolgerungsfähigkeiten, die die Leistung bei nachgelagerten Aufgaben deutlich verbessern insbesondere bei schwierigen Problemen. QwQ-32B ist ein mittelgroßes Modell, das mit führenden Schlussfolgerungsmodellen wie DeepSeek-R1 und o1-mini mithalten kann.",
"qwq_32b.description": "Mittelgroßes Schlussfolgerungsmodell aus der Qwen-Familie. Im Vergleich zu standardmäßig instruktionstunierten Modellen steigern QwQs Denk- und Schlussfolgerungsfähigkeiten die Leistung bei nachgelagerten Aufgaben deutlich insbesondere bei schwierigen Problemen.",
"r1-1776.description": "R1-1776 ist eine nachtrainierte Variante von DeepSeek R1, die darauf ausgelegt ist, unzensierte, objektive und faktenbasierte Informationen bereitzustellen.",
"seedance-1-5-pro-251215.description": "Seedance 1.5 Pro von ByteDance unterstützt Text-zu-Video, Bild-zu-Video (erstes Bild, erstes+letztes Bild) und Audioerzeugung synchron mit visuellen Inhalten.",
"seedream-5-0-260128.description": "ByteDance-Seedream-5.0-lite von BytePlus bietet webgestützte Generierung für Echtzeitinformationen, verbesserte Interpretation komplexer Eingabeaufforderungen und verbesserte Konsistenz von Referenzen für professionelle visuelle Kreationen.",
"solar-mini-ja.description": "Solar Mini (Ja) erweitert Solar Mini mit einem Fokus auf Japanisch und behält dabei eine effiziente und starke Leistung in Englisch und Koreanisch bei.",
"solar-mini.description": "Solar Mini ist ein kompaktes LLM, das GPT-3.5 übertrifft. Es bietet starke mehrsprachige Fähigkeiten in Englisch und Koreanisch und ist eine effiziente Lösung mit kleinem Ressourcenbedarf.",
"solar-pro.description": "Solar Pro ist ein hochintelligentes LLM von Upstage, das auf Befolgen von Anweisungen auf einer einzelnen GPU ausgelegt ist und IFEval-Werte über 80 erreicht. Derzeit wird Englisch unterstützt; die vollständige Veröffentlichung mit erweitertem Sprachsupport und längeren Kontexten war für November 2024 geplant.",
@@ -1233,7 +1225,9 @@
"sophnet/deepseek-v3.2.description": "DeepSeek V3.2 ist ein Modell, das ein Gleichgewicht zwischen hoher Recheneffizienz und hervorragender Leistung in logischem Denken und Agentenfähigkeiten bietet.",
"sora-2-pro.description": "Sora 2 Pro ist unser hochmodernes, fortschrittlichstes Medienerzeugungsmodell, das Videos mit synchronisiertem Audio erzeugt. Es kann reich detaillierte, dynamische Clips aus natürlicher Sprache oder Bildern erstellen.",
"sora-2.description": "Sora 2 ist unser neues leistungsstarkes Medienerzeugungsmodell, das Videos mit synchronisiertem Audio erzeugt. Es kann reich detaillierte, dynamische Clips aus natürlicher Sprache oder Bildern erstellen.",
"spark-x.description": "X2-Fähigkeiten-Übersicht: 1. Führt dynamische Anpassung des Denkmodus ein, gesteuert über das `thinking`-Feld. 2. Erweiterte Kontextlänge: 64K Eingabetokens und 128K Ausgabetokens. 3. Unterstützt Funktionaufruf-Funktionalität.",
"spark-x1.5.description": "X1.5-Updates: (1) fügt einen dynamischen Denkmodus hinzu, der über das Feld `thinking` gesteuert wird; (2) größere Kontextlänge mit 64K Eingabe- und 64K Ausgabetokens; (3) unterstützt FunctionCall.",
"spark-x2-flash.description": "Spark X2-Flash verwendet eine MoE-Architektur (Mixture of Experts) mit insgesamt 30 Milliarden Parametern und unterstützt ein Kontextfenster von bis zu 256K. Es bietet signifikante Verbesserungen in agentischen und Codierungsfähigkeiten und wurde auf einem Cluster von Ascend 910B AI-Prozessoren trainiert.",
"spark-x2.description": "X2-Fähigkeiten im Überblick: 1. Führt eine dynamische Anpassung des Denkmodus ein, gesteuert über das Feld `thinking`. 2. Erweiterte Kontextlänge: 64K Eingabetokens und 128K Ausgabetokens. 3. Unterstützt die Funktionalität Function Call.",
"stable-diffusion-3-medium.description": "Das neueste Text-zu-Bild-Modell von Stability AI. Diese Version verbessert die Bildqualität, das Textverständnis und die Stilvielfalt erheblich, interpretiert komplexe Spracheingaben präziser und erzeugt genauere, vielfältigere Bilder.",
"stable-diffusion-3.5-large-turbo.description": "Stable Diffusion 3.5 Large Turbo konzentriert sich auf hochwertige Bildgenerierung mit starker Detaildarstellung und hoher Szenentreue.",
"stable-diffusion-xl-base-1.0.description": "Ein Open-Source-Text-zu-Bild-Modell von Stability AI mit branchenführender kreativer Bildgenerierung. Es versteht Anweisungen sehr gut und unterstützt umgekehrte Prompt-Definitionen für präzise Generierung.",
@@ -1355,7 +1349,6 @@
"x-ai/grok-4.1-fast.description": "Grok 4 Fast ist xAIs hochdurchsatzfähiges, kostengünstiges Modell (unterstützt 2M Kontextfenster), ideal für hochparallele und langkontextuelle Anwendungsfälle.",
"x-ai/grok-4.description": "Grok 4 ist xAIs Flaggschiff-Reasoning-Modell mit starker Denk- und Multimodal-Fähigkeit.",
"x-ai/grok-code-fast-1.description": "Grok Code Fast 1 ist xAIs schnelles Codemodell mit lesbaren, entwicklerfreundlichen Ausgaben.",
"x1.description": "X1.5 Updates: (1) fügt dynamischen Denkmodus hinzu, gesteuert durch das `thinking`-Feld; (2) größere Kontextlänge mit 64K Eingabe und 64K Ausgabe; (3) unterstützt FunctionCall.",
"xai/grok-2-vision.description": "Grok 2 Vision überzeugt bei visuellen Aufgaben mit SOTA-Leistung in visuellem Mathematik-Reasoning (MathVista) und Dokumenten-QA (DocVQA). Es verarbeitet Dokumente, Diagramme, Grafiken, Screenshots und Fotos.",
"xai/grok-2.description": "Grok 2 ist ein Spitzenmodell mit modernstem Reasoning, starker Chat-, Coding- und Denkleistung und übertrifft Claude 3.5 Sonnet und GPT-4 Turbo auf LMSYS.",
"xai/grok-3-fast.description": "xAIs Flaggschiffmodell überzeugt in Unternehmensanwendungen wie Datenextraktion, Codierung und Zusammenfassung mit tiefem Fachwissen in Finanzen, Gesundheitswesen, Recht und Wissenschaft. Die schnelle Variante läuft auf schnellerer Infrastruktur für deutlich schnellere Antworten bei höheren Tokenkosten.",
+21 -21
View File
@@ -69,9 +69,22 @@
"builtins.lobe-agent-management.render.installPlugin.plugin": "Plugin",
"builtins.lobe-agent-management.render.installPlugin.success": "Erfolgreich installiert",
"builtins.lobe-agent-management.title": "Agenten-Manager",
"builtins.lobe-agent-marketplace.apiName.showAgentMarketplace": "Agenten-Marktplatz öffnen",
"builtins.lobe-agent-marketplace.apiName.submitAgentPick": "Agenten-Auswahl einreichen",
"builtins.lobe-agent-marketplace.title": "Agenten-Marktplatz",
"builtins.lobe-agent.apiName.callSubAgent": "Sub-Agent aufrufen",
"builtins.lobe-agent.apiName.callSubAgent.completed": "Sub-Agent entsendet: ",
"builtins.lobe-agent.apiName.callSubAgent.loading": "Sub-Agent wird entsendet: ",
"builtins.lobe-agent.apiName.callSubAgents": "Sub-Agents aufrufen",
"builtins.lobe-agent.apiName.clearTodos": "Todos löschen",
"builtins.lobe-agent.apiName.clearTodos.modeAll": "alle",
"builtins.lobe-agent.apiName.clearTodos.modeCompleted": "abgeschlossen",
"builtins.lobe-agent.apiName.clearTodos.result": "<mode>{{mode}}</mode> Todos löschen",
"builtins.lobe-agent.apiName.createPlan": "Plan erstellen",
"builtins.lobe-agent.apiName.createPlan.result": "Plan erstellen: <goal>{{goal}}</goal>",
"builtins.lobe-agent.apiName.createTodos": "Todos erstellen",
"builtins.lobe-agent.apiName.updatePlan": "Plan aktualisieren",
"builtins.lobe-agent.apiName.updatePlan.completed": "Abgeschlossen",
"builtins.lobe-agent.apiName.updatePlan.modified": "Geändert",
"builtins.lobe-agent.apiName.updateTodos": "Todos aktualisieren",
"builtins.lobe-agent.title": "Lobe-Agent",
"builtins.lobe-claude-code.agent.instruction": "Anweisung",
"builtins.lobe-claude-code.agent.result": "Ergebnis",
"builtins.lobe-claude-code.todoWrite.allDone": "Alle Aufgaben abgeschlossen",
@@ -139,24 +152,6 @@
"builtins.lobe-group-management.inspector.executeAgentTasks.title": "Aufgaben zuweisen an:",
"builtins.lobe-group-management.inspector.speak.title": "Zugewiesener Agent spricht:",
"builtins.lobe-group-management.title": "Gruppenkoordinator",
"builtins.lobe-gtd.apiName.clearTodos": "To-dos löschen",
"builtins.lobe-gtd.apiName.clearTodos.modeAll": "alle",
"builtins.lobe-gtd.apiName.clearTodos.modeCompleted": "abgeschlossen",
"builtins.lobe-gtd.apiName.clearTodos.result": "<mode>{{mode}}</mode> To-dos gelöscht",
"builtins.lobe-gtd.apiName.completeTodos": "To-dos abschließen",
"builtins.lobe-gtd.apiName.createPlan": "Plan erstellen",
"builtins.lobe-gtd.apiName.createPlan.result": "Plan erstellt: <goal>{{goal}}</goal>",
"builtins.lobe-gtd.apiName.createTodos": "To-dos erstellen",
"builtins.lobe-gtd.apiName.execTask": "Aufgabe ausführen",
"builtins.lobe-gtd.apiName.execTask.completed": "Aufgabe erstellt: ",
"builtins.lobe-gtd.apiName.execTask.loading": "Aufgabe wird erstellt: ",
"builtins.lobe-gtd.apiName.execTasks": "Aufgaben ausführen",
"builtins.lobe-gtd.apiName.removeTodos": "To-dos löschen",
"builtins.lobe-gtd.apiName.updatePlan": "Plan aktualisieren",
"builtins.lobe-gtd.apiName.updatePlan.completed": "Abgeschlossen",
"builtins.lobe-gtd.apiName.updatePlan.modified": "Geändert",
"builtins.lobe-gtd.apiName.updateTodos": "To-dos aktualisieren",
"builtins.lobe-gtd.title": "Aufgaben-Tools",
"builtins.lobe-knowledge-base.apiName.readKnowledge": "Bibliotheksinhalte lesen",
"builtins.lobe-knowledge-base.apiName.searchKnowledgeBase": "Bibliothek durchsuchen",
"builtins.lobe-knowledge-base.inspector.andMoreFiles": "und {{count}} weitere",
@@ -317,6 +312,8 @@
"builtins.lobe-web-onboarding.apiName.finishOnboarding": "Onboarding abschließen",
"builtins.lobe-web-onboarding.apiName.readDocument": "Dokument lesen",
"builtins.lobe-web-onboarding.apiName.saveUserQuestion": "Benutzerfrage speichern",
"builtins.lobe-web-onboarding.apiName.showAgentMarketplace": "Agenten-Team zusammenstellen",
"builtins.lobe-web-onboarding.apiName.submitAgentPick": "Agenten-Auswahl einreichen",
"builtins.lobe-web-onboarding.apiName.updateDocument": "Dokument aktualisieren",
"builtins.lobe-web-onboarding.apiName.writeDocument": "Dokument schreiben",
"builtins.lobe-web-onboarding.docType.persona": "Benutzerpersona",
@@ -327,6 +324,9 @@
"builtins.lobe-web-onboarding.inspector.hunkCount_other": "{{count}} Änderungen",
"builtins.lobe-web-onboarding.inspector.interests_one": "{{count}} Interesse",
"builtins.lobe-web-onboarding.inspector.interests_other": "{{count}} Interessen",
"builtins.lobe-web-onboarding.render.agent": "Agent",
"builtins.lobe-web-onboarding.render.fullName": "Vollständiger Name",
"builtins.lobe-web-onboarding.render.interests": "Interessen",
"builtins.lobe-web-onboarding.title": "Benutzer-Onboarding",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.delete": "Löschen",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.deleteLines": "Zeilen löschen",
-1
View File
@@ -33,7 +33,6 @@
"jina.description": "Jina AI wurde 2020 gegründet und ist ein führendes Unternehmen im Bereich Such-KI. Der Such-Stack umfasst Vektormodelle, Reranker und kleine Sprachmodelle für zuverlässige, hochwertige generative und multimodale Suchanwendungen.",
"kimicodingplan.description": "Kimi Code von Moonshot AI bietet Zugriff auf Kimi-Modelle, darunter K2.5, für Coding-Aufgaben.",
"lmstudio.description": "LM Studio ist eine Desktop-App zur Entwicklung und zum Experimentieren mit LLMs auf dem eigenen Computer.",
"lobehub.description": "LobeHub Cloud verwendet offizielle APIs, um auf KI-Modelle zuzugreifen, und misst die Nutzung mit Credits, die an Modell-Token gebunden sind.",
"longcat.description": "LongCat ist eine Reihe von generativen KI-Großmodellen, die unabhängig von Meituan entwickelt wurden. Sie sind darauf ausgelegt, die Produktivität innerhalb des Unternehmens zu steigern und innovative Anwendungen durch eine effiziente Rechenarchitektur und starke multimodale Fähigkeiten zu ermöglichen.",
"minimax.description": "MiniMax wurde 2021 gegründet und entwickelt allgemeine KI mit multimodalen Foundation-Modellen, darunter Textmodelle mit Billionen Parametern, Sprach- und Bildmodelle sowie Apps wie Hailuo AI.",
"minimaxcodingplan.description": "Der MiniMax Token Plan bietet Zugriff auf MiniMax-Modelle, darunter M2.7, für Coding-Aufgaben im Rahmen eines Festpreis-Abonnements.",
-2
View File
@@ -913,8 +913,6 @@
"tools.builtins.lobe-agent-documents.title": "Dokumente",
"tools.builtins.lobe-agent-management.description": "KIAgenten erstellen, verwalten und orchestrieren",
"tools.builtins.lobe-agent-management.title": "Agentenverwaltung",
"tools.builtins.lobe-agent-marketplace.description": "Zeigen Sie den Benutzern eine kuratierte Agenten-Marktplatzkarte und zeichnen Sie auf, welche Vorlagen sie auswählen.",
"tools.builtins.lobe-agent-marketplace.title": "Agenten-Marktplatz",
"tools.builtins.lobe-artifacts.description": "Interaktive UI-Komponenten, Datenvisualisierungen, Diagramme, SVG-Grafiken und Webanwendungen generieren und in Echtzeit anzeigen. Erstellen Sie reichhaltige visuelle Inhalte, mit denen Nutzer direkt interagieren können.",
"tools.builtins.lobe-artifacts.readme": "Erstellen und live-vorschauen interaktive UI-Komponenten, Datenvisualisierungen, Diagramme, SVG-Grafiken und Webanwendungen. Erzeugen Sie reichhaltige visuelle Inhalte, mit denen Nutzer direkt interagieren können.",
"tools.builtins.lobe-artifacts.title": "Artefakte",
+45 -45
View File
@@ -56,51 +56,51 @@
"dalle.generating": "Wird generiert...",
"dalle.images": "Bilder:",
"dalle.prompt": "Eingabeaufforderung",
"lobe-gtd.actions.add": "Hinzufügen",
"lobe-gtd.actions.clearCompleted": "Erledigte löschen",
"lobe-gtd.actions.placeholder": "Geben Sie eine Aufgabe ein...",
"lobe-gtd.addTodo.placeholder": "Eine Aufgabe hinzufügen...",
"lobe-gtd.clearTodos.cleared": "{{count}} Element(e) gelöscht",
"lobe-gtd.clearTodos.clearedCompleted": "{{count}} erledigte Element(e) gelöscht",
"lobe-gtd.clearTodos.clearedCompleted_one": "{{count}} erledigtes Element gelöscht",
"lobe-gtd.clearTodos.clearedCompleted_other": "{{count}} erledigte Elemente gelöscht",
"lobe-gtd.clearTodos.cleared_one": "{{count}} Element gelöscht",
"lobe-gtd.clearTodos.cleared_other": "{{count}} Elemente gelöscht",
"lobe-gtd.clearTodos.header": "Aufgaben löschen",
"lobe-gtd.clearTodos.label": "Wählen Sie aus, was gelöscht werden soll:",
"lobe-gtd.clearTodos.noItems": "Keine Elemente zum Löschen vorhanden",
"lobe-gtd.clearTodos.option.all": "Alle Elemente löschen (einschließlich offener)",
"lobe-gtd.clearTodos.option.completed": "Nur erledigte Elemente löschen",
"lobe-gtd.clearTodos.remaining": "{{count}} verbleibende(s) Element(e)",
"lobe-gtd.clearTodos.remaining_one": "{{count}} verbleibendes Element",
"lobe-gtd.clearTodos.remaining_other": "{{count}} verbleibende Elemente",
"lobe-gtd.completeTodos.completed": "{{count}} Element(e) erledigt",
"lobe-gtd.completeTodos.completed_one": "{{count}} Element erledigt",
"lobe-gtd.completeTodos.completed_other": "{{count}} Elemente erledigt",
"lobe-gtd.createPlan.context.label": "Kontext (optional)",
"lobe-gtd.createPlan.context.placeholder": "Hintergrund, Einschränkungen, Überlegungen...",
"lobe-gtd.createPlan.description.label": "Beschreibung",
"lobe-gtd.createPlan.description.placeholder": "Kurze Zusammenfassung des Plans",
"lobe-gtd.createPlan.goal.label": "Ziel",
"lobe-gtd.createPlan.goal.placeholder": "Was möchten Sie erreichen?",
"lobe-gtd.createTodos.created": "{{count}} Aufgabe(n) erstellt",
"lobe-gtd.createTodos.created_one": "{{count}} Aufgabe erstellt",
"lobe-gtd.createTodos.created_other": "{{count}} Aufgaben erstellt",
"lobe-gtd.createTodos.total": "Gesamt: {{count}} Element(e)",
"lobe-gtd.createTodos.total_one": "Gesamt: {{count}} Element",
"lobe-gtd.createTodos.total_other": "Gesamt: {{count}} Elemente",
"lobe-gtd.removeTodos.removed": "{{count}} Element(e) entfernt",
"lobe-gtd.removeTodos.removed_one": "{{count}} Element entfernt",
"lobe-gtd.removeTodos.removed_other": "{{count}} Elemente entfernt",
"lobe-gtd.status.done": "{{count}} erledigt",
"lobe-gtd.status.pending": "{{count}} offen",
"lobe-gtd.todoItem.placeholder": "Aufgabe eingeben...",
"lobe-gtd.todoList.empty": "Aufgabenliste ist leer",
"lobe-gtd.todoList.items": "{{count}} Element(e)",
"lobe-gtd.todoList.items_one": "{{count}} Element",
"lobe-gtd.todoList.items_other": "{{count}} Elemente",
"lobe-gtd.todoList.title": "Aufgabenliste",
"lobe-gtd.updateTodos.updated": "Aufgabenliste aktualisiert",
"lobe-agent.actions.add": "Hinzufügen",
"lobe-agent.actions.clearCompleted": "Abgeschlossenes löschen",
"lobe-agent.actions.placeholder": "Geben Sie einen To-Do-Punkt ein...",
"lobe-agent.addTodo.placeholder": "Fügen Sie einen To-Do-Punkt hinzu...",
"lobe-agent.clearTodos.cleared": "{{count}} Element(e) gelöscht",
"lobe-agent.clearTodos.clearedCompleted": "{{count}} abgeschlossene Element(e) gelöscht",
"lobe-agent.clearTodos.clearedCompleted_one": "{{count}} abgeschlossenes Element gelöscht",
"lobe-agent.clearTodos.clearedCompleted_other": "{{count}} abgeschlossene Elemente gelöscht",
"lobe-agent.clearTodos.cleared_one": "{{count}} Element gelöscht",
"lobe-agent.clearTodos.cleared_other": "{{count}} Elemente gelöscht",
"lobe-agent.clearTodos.header": "To-Do-Elemente löschen",
"lobe-agent.clearTodos.label": "Wählen Sie aus, was gelöscht werden soll:",
"lobe-agent.clearTodos.noItems": "Keine Elemente zum Löschen",
"lobe-agent.clearTodos.option.all": "Alle Elemente löschen (einschließlich ausstehender)",
"lobe-agent.clearTodos.option.completed": "Nur abgeschlossene Elemente löschen",
"lobe-agent.clearTodos.remaining": "{{count}} Element(e) verbleibend",
"lobe-agent.clearTodos.remaining_one": "{{count}} Element verbleibend",
"lobe-agent.clearTodos.remaining_other": "{{count}} Elemente verbleibend",
"lobe-agent.completeTodos.completed": "{{count}} Element(e) abgeschlossen",
"lobe-agent.completeTodos.completed_one": "{{count}} Element abgeschlossen",
"lobe-agent.completeTodos.completed_other": "{{count}} Elemente abgeschlossen",
"lobe-agent.createPlan.context.label": "Kontext (optional)",
"lobe-agent.createPlan.context.placeholder": "Hintergrund, Einschränkungen, Überlegungen...",
"lobe-agent.createPlan.description.label": "Beschreibung",
"lobe-agent.createPlan.description.placeholder": "Kurze Zusammenfassung des Plans",
"lobe-agent.createPlan.goal.label": "Ziel",
"lobe-agent.createPlan.goal.placeholder": "Was möchten Sie erreichen?",
"lobe-agent.createTodos.created": "{{count}} To-Do-Element(e) erstellt",
"lobe-agent.createTodos.created_one": "{{count}} To-Do-Element erstellt",
"lobe-agent.createTodos.created_other": "{{count}} To-Do-Elemente erstellt",
"lobe-agent.createTodos.total": "Gesamt: {{count}} Element(e)",
"lobe-agent.createTodos.total_one": "Gesamt: {{count}} Element",
"lobe-agent.createTodos.total_other": "Gesamt: {{count}} Elemente",
"lobe-agent.removeTodos.removed": "{{count}} Element(e) entfernt",
"lobe-agent.removeTodos.removed_one": "{{count}} Element entfernt",
"lobe-agent.removeTodos.removed_other": "{{count}} Elemente entfernt",
"lobe-agent.status.done": "{{count}} abgeschlossen",
"lobe-agent.status.pending": "{{count}} ausstehend",
"lobe-agent.todoItem.placeholder": "To-Do-Element eingeben...",
"lobe-agent.todoList.empty": "To-Do-Liste ist leer",
"lobe-agent.todoList.items": "{{count}} Element(e)",
"lobe-agent.todoList.items_one": "{{count}} Element",
"lobe-agent.todoList.items_other": "{{count}} Elemente",
"lobe-agent.todoList.title": "To-Do-Liste",
"lobe-agent.updateTodos.updated": "To-Do-Liste aktualisiert",
"lobe-knowledge-base.readKnowledge.meta.chars": "Anzahl Zeichen",
"lobe-knowledge-base.readKnowledge.meta.lines": "Anzahl Zeilen",
"localFiles.editFile.newString": "Ersetzen durch",
+4
View File
@@ -115,6 +115,10 @@
"channel.line.fetchBotInfoMissingToken": "Enter the Channel Access Token first, then click \"Fetch from LINE\".",
"channel.line.fetchBotInfoSuccess": "Destination User ID fetched",
"channel.line.webhookManualSetup": "LINE does not allow programmatic webhook registration. Copy this URL into the LINE Developers Console (Messaging API → Webhook URL), click \"Verify\", and enable \"Use webhook\".",
"channel.messengerPromo.action": "Try Messenger",
"channel.messengerPromo.desc": "No bot setup. Chat with LobeHub on Slack, Discord, Telegram.",
"channel.messengerPromo.dismiss": "Dismiss",
"channel.messengerPromo.title": "Skip the setup",
"channel.openPlatform": "Open Platform",
"channel.platforms": "Platforms",
"channel.publicKey": "Public Key",
+3 -1
View File
@@ -29,7 +29,7 @@
"batchDelete": "Batch Delete",
"blog": "Product Blog",
"botIntegrationBanner.dismiss": "Dismiss",
"botIntegrationBanner.title": "Talk to Lobe AI on your favorite messaging apps",
"botIntegrationBanner.title": "Create your own Bot Channel",
"branching": "Create Subtopic",
"branchingDisable": "The \"Sub-topic\" feature is unavailable in the current mode. To use this feature, please switch to Postgres/Pglite DB mode or use LobeHub Cloud.",
"branchingRequiresSavedTopic": "Current topic is not saved, please save it first to use subtopic feature",
@@ -349,6 +349,8 @@
"loading": "Loading...",
"mail.business": "Business Cooperation",
"mail.support": "Email Support",
"messengerBanner.dismiss": "Dismiss",
"messengerBanner.title": "Talk to Lobe AI on your favorite messaging apps",
"more": "More",
"navPanel.agent": "Agents",
"navPanel.customizeSidebar": "Customize Sidebar",
+1
View File
@@ -8,6 +8,7 @@
"brief.action.confirm": "Confirm",
"brief.action.confirmDone": "Confirm complete",
"brief.action.feedback": "Feedback",
"brief.action.ignore": "Ignore",
"brief.action.retry": "Retry",
"brief.addFeedback": "Share feedback",
"brief.collapse": "Show less",
-2
View File
@@ -9,7 +9,5 @@
"features.groupChat.title": "Group Chat (Multi-Agent)",
"features.inputMarkdown.desc": "Render Markdown in the input area in real time (bold text, code blocks, tables, etc.).",
"features.inputMarkdown.title": "Input Markdown Rendering",
"features.messenger.desc": "Talk to your agents from Telegram (and other messengers) via the shared LobeHub bot. Adds a Messenger tab in Settings for binding your account and choosing which agent receives messages.",
"features.messenger.title": "Messenger",
"title": "Labs"
}
-4
View File
@@ -35,7 +35,6 @@
"messenger.linkModal.notConfigured": "This connection isn't available right now. Please try again later.",
"messenger.linkModal.openCta": "Open in {{platform}}",
"messenger.linkModal.scanHint": "Or scan with your phone to open {{platform}}.",
"messenger.linkModal.title": "Connect Messenger",
"messenger.list.discord.description": "Chat with your LobeHub agents from any Discord server via DM with the LobeHub bot.",
"messenger.list.slack.description": "Chat with your LobeHub agents from any Slack workspace via DM or @LobeHub.",
"messenger.list.telegram.description": "Chat with your LobeHub agents in Telegram and pick which one answers from anywhere.",
@@ -97,9 +96,6 @@
"verify.error.missingToken": "Invalid link. Open this page from the bot.",
"verify.error.title": "Unable to confirm link",
"verify.error.unlinkBeforeRelink": "This LobeHub account is already linked to another account on this platform. Disconnect it in Settings → Messenger before linking a new one.",
"verify.labRequired.description": "Messenger is currently a Labs feature. Enable it in Settings → Advanced → Labs and reload this page.",
"verify.labRequired.openSettings": "Open Labs settings",
"verify.labRequired.title": "Enable Messenger to continue",
"verify.signInCta": "Sign in to continue",
"verify.signInRequired": "Please sign in to LobeHub to confirm the link.",
"verify.success.description": "Your account is now connected to {{platform}}. Open {{platform}} and send your first message.",
+15 -22
View File
@@ -106,7 +106,6 @@
"MiniMax-Hailuo-2.3.description": "Brand-new video generation model with comprehensive upgrades in body motion, physical realism, and instruction following.",
"MiniMax-M1.description": "A new in-house reasoning model with 80K chain-of-thought and 1M input, delivering performance comparable to top global models.",
"MiniMax-M2-Stable.description": "Built for efficient coding and agent workflows, with higher concurrency for commercial use.",
"MiniMax-M2.1-Lightning.description": "Powerful multilingual programming capabilities with faster and more efficient inference.",
"MiniMax-M2.1-highspeed.description": "Powerful multilingual programming capabilities, comprehensively upgraded programming experience. Faster and more efficient.",
"MiniMax-M2.1.description": "MiniMax-M2.1 is a flagship open-source large model from MiniMax, focusing on solving complex real-world tasks. Its core strengths are multi-language programming capabilities and the ability to solve complex tasks as an Agent.",
"MiniMax-M2.5-highspeed.description": "MiniMax M2.5 Highspeed: Same performance as M2.5 with faster inference.",
@@ -315,13 +314,13 @@
"claude-3-haiku-20240307.description": "Claude 3 Haiku is Anthropics fastest and most compact model, designed for near-instant responses with fast, accurate performance.",
"claude-3-opus-20240229.description": "Claude 3 Opus is Anthropics most powerful model for highly complex tasks, excelling in performance, intelligence, fluency, and comprehension.",
"claude-3-sonnet-20240229.description": "Claude 3 Sonnet balances intelligence and speed for enterprise workloads, delivering high utility at lower cost and reliable large-scale deployment.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 is Anthropic's fastest and most intelligent Haiku model, with lightning speed and extended thinking.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 is Anthropics fastest and smartest Haiku model, with lightning speed and extended reasoning.",
"claude-haiku-4-5.description": "Claude Haiku 4.5 by Anthropic — next-gen Haiku with enhanced reasoning and vision.",
"claude-haiku-4.5.description": "Claude Haiku 4.5 is Anthropics fastest and smartest Haiku model, with lightning speed and extended reasoning.",
"claude-opus-4-1-20250805-thinking.description": "Claude Opus 4.1 Thinking is an advanced variant that can reveal its reasoning process.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 is Anthropic's latest and most capable model for highly complex tasks, excelling in performance, intelligence, fluency, and understanding.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 is Anthropics latest and most capable model for highly complex tasks, excelling in performance, intelligence, fluency, and understanding.",
"claude-opus-4-1.description": "Claude Opus 4.1 by Anthropic — premium reasoning model with deep analysis capabilities.",
"claude-opus-4-20250514.description": "Claude Opus 4 is Anthropic's most powerful model for highly complex tasks, excelling in performance, intelligence, fluency, and understanding.",
"claude-opus-4-20250514.description": "Claude Opus 4 is Anthropics most powerful model for highly complex tasks, excelling in performance, intelligence, fluency, and comprehension.",
"claude-opus-4-5-20251101.description": "Claude Opus 4.5 is Anthropics flagship model, combining outstanding intelligence with scalable performance, ideal for complex tasks requiring the highest-quality responses and reasoning.",
"claude-opus-4-5.description": "Claude Opus 4.5 by Anthropic — flagship model with top-tier reasoning and coding.",
"claude-opus-4-6.description": "Claude Opus 4.6 by Anthropic — 1M context window flagship with advanced reasoning.",
@@ -330,8 +329,8 @@
"claude-opus-4.6-fast.description": "Claude Opus 4.6 is Anthropics most intelligent model for building agents and coding.",
"claude-opus-4.6.description": "Claude Opus 4.6 is Anthropics most intelligent model for building agents and coding.",
"claude-sonnet-4-20250514-thinking.description": "Claude Sonnet 4 Thinking can produce near-instant responses or extended step-by-step thinking with visible process.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 is Anthropic's most intelligent model to date, offering near-instant responses or extended step-by-step thinking with fine-grained control for API users.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5 is Anthropic's most intelligent model to date.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 can produce near-instant responses or extended step-by-step thinking with visible process.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5 is Anthropics most intelligent model to date.",
"claude-sonnet-4-5.description": "Claude Sonnet 4.5 by Anthropic — improved Sonnet with enhanced coding performance.",
"claude-sonnet-4-6.description": "Claude Sonnet 4.6 by Anthropic — latest Sonnet with superior coding and tool use.",
"claude-sonnet-4.5.description": "Claude Sonnet 4.5 is Anthropics most intelligent model to date.",
@@ -404,7 +403,7 @@
"deepseek-ai/deepseek-llm-67b-chat.description": "DeepSeek LLM Chat (67B) is an innovative model offering deep language understanding and interaction.",
"deepseek-ai/deepseek-v3.1-terminus.description": "DeepSeek V3.1 is a next-gen reasoning model with stronger complex reasoning and chain-of-thought for deep analysis tasks.",
"deepseek-ai/deepseek-v3.2.description": "DeepSeek V3.2 is a next-gen reasoning model with stronger complex reasoning and chain-of-thought capabilities.",
"deepseek-chat.description": "Compatibility alias for DeepSeek V4 Flash non-thinking mode. Slated for deprecation — use DeepSeek V4 Flash instead.",
"deepseek-chat.description": "A new open-source model combining general and code abilities. It preserves the chat models general dialogue and the coder models strong coding, with better preference alignment. DeepSeek-V2.5 also improves writing and instruction following.",
"deepseek-coder-33B-instruct.description": "DeepSeek Coder 33B is a code language model trained on 2T tokens (87% code, 13% Chinese/English text). It introduces a 16K context window and fill-in-the-middle tasks, providing project-level code completion and snippet infilling.",
"deepseek-coder-v2.description": "DeepSeek Coder V2 is an open-source MoE code model that performs strongly on coding tasks, comparable to GPT-4 Turbo.",
"deepseek-coder-v2:236b.description": "DeepSeek Coder V2 is an open-source MoE code model that performs strongly on coding tasks, comparable to GPT-4 Turbo.",
@@ -426,7 +425,7 @@
"deepseek-r1-fast-online.description": "DeepSeek R1 fast full version with real-time web search, combining 671B-scale capability and faster response.",
"deepseek-r1-online.description": "DeepSeek R1 full version with 671B parameters and real-time web search, offering stronger understanding and generation.",
"deepseek-r1.description": "DeepSeek-R1 uses cold-start data before RL and performs comparably to OpenAI-o1 on math, coding, and reasoning.",
"deepseek-reasoner.description": "Compatibility alias for DeepSeek V4 Flash thinking mode. Slated for deprecation — use DeepSeek V4 Flash instead.",
"deepseek-reasoner.description": "A DeepSeek reasoning model focused on complex logical reasoning tasks.",
"deepseek-v2.description": "DeepSeek V2 is an efficient MoE model for cost-effective processing.",
"deepseek-v2:236b.description": "DeepSeek V2 236B is DeepSeeks code-focused model with strong code generation.",
"deepseek-v3-0324.description": "DeepSeek-V3-0324 is a 671B-parameter MoE model with standout strengths in programming and technical capability, context understanding, and long-text handling.",
@@ -491,8 +490,6 @@
"doubao-seedream-4-0-250828.description": "Seedream 4.0 is an image generation model from ByteDance Seed, supporting text and image inputs with highly controllable, high-quality image generation. It generates images from text prompts.",
"doubao-seedream-4-5-251128.description": "Seedream 4.5 is ByteDances latest multimodal image model, integrating text-to-image, image-to-image, and batch image generation capabilities, while incorporating commonsense and reasoning abilities. Compared to the previous 4.0 version, it delivers significantly improved generation quality, with better editing consistency and multi-image fusion. It offers more precise control over visual details, producing small text and small faces more naturally, and achieves more harmonious layout and color, enhancing overall aesthetics.",
"doubao-seedream-5-0-260128.description": "Doubao-Seedream-5.0-lite is ByteDances latest image-generation model. For the first time, it integrates online retrieval capabilities, allowing it to incorporate real-time web information and enhance the timeliness of generated images. The models intelligence has also been upgraded, enabling precise interpretation of complex instructions and visual content. Additionally, it offers improved global knowledge coverage, reference consistency, and generation quality in professional scenarios, better meeting enterprise-level visual creation needs.",
"dreamina-seedance-2-0-260128.description": "Seedance 2.0 by ByteDance is the most powerful video generation model, supporting multimodal reference video generation, video editing, video extension, text-to-video, and image-to-video with synchronized audio.",
"dreamina-seedance-2-0-fast-260128.description": "Seedance 2.0 Fast by ByteDance offers the same capabilities as Seedance 2.0 with faster generation speeds at a more competitive price.",
"emohaa.description": "Emohaa is a mental health model with professional counseling abilities to help users understand emotional issues.",
"ernie-4.5-0.3b.description": "ERNIE 4.5 0.3B is an open-source lightweight model for local and customized deployment.",
"ernie-4.5-8k-preview.description": "ERNIE 4.5 8K Preview is an 8K context preview model for evaluating ERNIE 4.5.",
@@ -517,8 +514,7 @@
"ernie-x1-turbo-32k.description": "ERNIE X1 Turbo 32K is a fast thinking model with 32K context for complex reasoning and multi-turn chat.",
"ernie-x1.1-preview.description": "ERNIE X1.1 Preview is a thinking-model preview for evaluation and testing.",
"ernie-x1.1.description": "ERNIE X1.1 is a thinking-model preview for evaluation and testing.",
"fal-ai/bytedance/seedream/v4.5.description": "Seedream 4.5, built by ByteDance Seed team, supports multi-image editing and composition. Features enhanced subject consistency, precise instruction following, spatial logic understanding, aesthetic expression, poster layout and logo design with high-precision text-image rendering.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0, built by ByteDance Seed, supports text and image inputs for highly controllable, high-quality image generation from prompts.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0 is an image generation model from ByteDance Seed, supporting text and image inputs with highly controllable, high-quality image generation. It generates images from text prompts.",
"fal-ai/flux-kontext/dev.description": "FLUX.1 model focused on image editing, supporting text and image inputs.",
"fal-ai/flux-pro/kontext.description": "FLUX.1 Kontext [pro] accepts text and reference images as input, enabling targeted local edits and complex global scene transformations.",
"fal-ai/flux/krea.description": "Flux Krea [dev] is an image generation model with an aesthetic bias toward more realistic, natural images.",
@@ -526,8 +522,8 @@
"fal-ai/hunyuan-image/v3.description": "A powerful native multimodal image generation model.",
"fal-ai/imagen4/preview.description": "High-quality image generation model from Google.",
"fal-ai/nano-banana.description": "Nano Banana is Googles newest, fastest, and most efficient native multimodal model, enabling image generation and editing through conversation.",
"fal-ai/qwen-image-edit.description": "A professional image editing model from the Qwen team, supporting semantic and appearance edits, precise Chinese/English text editing, style transfer, rotation, and more.",
"fal-ai/qwen-image.description": "A powerful image generation model from the Qwen team with strong Chinese text rendering and diverse visual styles.",
"fal-ai/qwen-image-edit.description": "A professional image editing model from the Qwen team that supports semantic and appearance edits, precisely edits Chinese and English text, and enables high-quality edits such as style transfer and object rotation.",
"fal-ai/qwen-image.description": "A powerful image generation model from the Qwen team with impressive Chinese text rendering and diverse visual styles.",
"flux-1-schnell.description": "A 12B-parameter text-to-image model from Black Forest Labs using latent adversarial diffusion distillation to generate high-quality images in 1-4 steps. It rivals closed alternatives and is released under Apache-2.0 for personal, research, and commercial use.",
"flux-dev.description": "Open-source R&D image generation model, efficiently optimized for non-commercial innovation research.",
"flux-kontext-max.description": "State-of-the-art contextual image generation and editing, combining text and images for precise, coherent results.",
@@ -566,10 +562,10 @@
"gemini-3-flash-preview.description": "Gemini 3 Flash is the smartest model built for speed, combining cutting-edge intelligence with excellent search grounding.",
"gemini-3-flash.description": "Gemini 3 Flash by Google — ultra-fast model with multimodal input support.",
"gemini-3-pro-image-preview.description": "Gemini 3 Pro Image (Nano Banana Pro) is Google's image generation model that also supports multimodal dialogue.",
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro) is Google's image generation model and also supports multimodal chat.",
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro) is Googles image generation model and also supports multimodal chat.",
"gemini-3-pro-preview.description": "Gemini 3 Pro is Googles most powerful agent and vibe-coding model, delivering richer visuals and deeper interaction on top of state-of-the-art reasoning.",
"gemini-3.1-flash-image-preview.description": "Gemini 3.1 Flash Image (Nano Banana 2) is Google's fastest native image generation model with thinking support, conversational image generation and editing.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) delivers Pro-level image quality at Flash speed with multimodal chat support.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) is Google's fastest native image generation model with thinking support, conversational image generation and editing.",
"gemini-3.1-flash-lite-preview.description": "Gemini 3.1 Flash-Lite Preview is Google's most cost-efficient multimodal model, optimized for high-volume agentic tasks, translation, and data processing.",
"gemini-3.1-flash-lite.description": "Gemini 3.1 Flash-Lite is Google's most cost-efficient multimodal model, optimized for high-volume agentic tasks, translation, and data processing.",
"gemini-3.1-pro-preview.description": "Gemini 3.1 Pro Preview improves on Gemini 3 Pro with enhanced reasoning capabilities and adds medium thinking level support.",
@@ -734,8 +730,6 @@
"grok-4-fast-reasoning.description": "Were excited to release Grok 4 Fast, our latest progress in cost-effective reasoning models.",
"grok-4.20-0309-non-reasoning.description": "A non-reasoning variant for simple use cases",
"grok-4.20-0309-reasoning.description": "Intelligent, blazing-fast model that reasons before responding",
"grok-4.20-beta-0309-non-reasoning.description": "A non-reasoning variant for simple use cases",
"grok-4.20-beta-0309-reasoning.description": "Intelligent, blazing-fast model that reasons before responding",
"grok-4.20-multi-agent-0309.description": "A team of 4 or 16 agents, Excels at research use cases, Does not currently support client-side tools. Only supports xAI server side tools (eg X Search, Web Search tools) and remote MCP tools.",
"grok-4.3.description": "The most truth-seeking large language model in the world",
"grok-4.description": "Latest Grok flagship with unmatched performance in language, math, and reasoning — a true all-rounder. Currently points to grok-4-0709; due to limited resources it is temporarily 10% higher than official pricing and is expected to return to official price later.",
@@ -1220,8 +1214,6 @@
"qwq.description": "QwQ is a reasoning model in the Qwen family. Compared with standard instruction-tuned models, it brings thinking and reasoning abilities that significantly improve downstream performance, especially on hard problems. QwQ-32B is a mid-sized reasoning model that competes well with top reasoning models like DeepSeek-R1 and o1-mini.",
"qwq_32b.description": "Mid-sized reasoning model in the Qwen family. Compared with standard instruction-tuned models, QwQs thinking and reasoning abilities significantly boost downstream performance, especially on hard problems.",
"r1-1776.description": "R1-1776 is a post-trained variant of DeepSeek R1 designed to provide uncensored, unbiased factual information.",
"seedance-1-5-pro-251215.description": "Seedance 1.5 Pro by ByteDance supports text-to-video, image-to-video (first frame, first+last frame), and audio generation synchronized with visuals.",
"seedream-5-0-260128.description": "ByteDance-Seedream-5.0-lite by BytePlus features web-retrieval-augmented generation for real-time information, enhanced complex prompt interpretation, and improved reference consistency for professional visual creation.",
"solar-mini-ja.description": "Solar Mini (Ja) extends Solar Mini with a focus on Japanese while maintaining efficient, strong performance in English and Korean.",
"solar-mini.description": "Solar Mini is a compact LLM that outperforms GPT-3.5, with strong multilingual capability supporting English and Korean, offering an efficient small-footprint solution.",
"solar-pro.description": "Solar Pro is a high-intelligence LLM from Upstage, focused on instruction following on a single GPU, with IFEval scores above 80. It currently supports English; the full release was planned for November 2024 with expanded language support and longer context.",
@@ -1233,7 +1225,9 @@
"sophnet/deepseek-v3.2.description": "DeepSeek V3.2 is a model that strikes a balance between high computational efficiency and excellent reasoning and agent performance.",
"sora-2-pro.description": "Sora 2 Pro is our state-of-the-art, most advanced media generation model, generating videos with synced audio. It can create richly detailed, dynamic clips from natural language or images.",
"sora-2.description": "Sora 2 is our new powerful media generation model, generating videos with synced audio. It can create richly detailed, dynamic clips from natural language or images.",
"spark-x.description": "X2 Capabilities Overview: 1. Introduces dynamic adjustment of reasoning mode, controlled via the `thinking` field. 2. Expanded context length: 64K input tokens and 128K output tokens. 3. Supports Function Call functionality.",
"spark-x1.5.description": "X1.5 updates: (1) adds dynamic thinking mode controlled by the `thinking` field; (2) larger context length with 64K input and 64K output; (3) supports FunctionCall.",
"spark-x2-flash.description": "Spark X2-Flash adopts an MoE (Mixture of Experts) architecture with 30 billion total parameters and supports up to a 256K context window. It claims significant improvements in agentic and coding capabilities, and was trained on a cluster of Ascend 910B AI processors.",
"spark-x2.description": "X2 Capabilities Overview: 1. Introduces dynamic adjustment of reasoning mode, controlled via the `thinking` field. 2. Expanded context length: 64K input tokens and 128K output tokens. 3. Supports Function Call functionality.",
"stable-diffusion-3-medium.description": "The latest text-to-image model from Stability AI. This version significantly improves image quality, text understanding, and style diversity, interpreting complex natural-language prompts more accurately and generating more precise, diverse images.",
"stable-diffusion-3.5-large-turbo.description": "Stable Diffusion 3.5 Large Turbo focuses on high-quality image generation with strong detail rendering and scene fidelity.",
"stable-diffusion-xl-base-1.0.description": "An open-source text-to-image model from Stability AI with industry-leading creative image generation. It has strong instruction understanding and supports reverse prompt definitions for precise generation.",
@@ -1355,7 +1349,6 @@
"x-ai/grok-4.1-fast.description": "Grok 4 Fast is xAIs high-throughput, low-cost model (supports a 2M context window), ideal for high-concurrency and long-context use cases.",
"x-ai/grok-4.description": "Grok 4 is xAI's flagship reasoning model with strong reasoning and multimodal capability.",
"x-ai/grok-code-fast-1.description": "Grok Code Fast 1 is xAI's fast code model with readable, engineering-friendly output.",
"x1.description": "X1.5 updates: (1) adds dynamic thinking mode controlled by the `thinking` field; (2) larger context length with 64K input and 64K output; (3) supports FunctionCall.",
"xai/grok-2-vision.description": "Grok 2 Vision excels at visual tasks, delivering SOTA performance on visual math reasoning (MathVista) and document QA (DocVQA). It handles documents, charts, graphs, screenshots, and photos.",
"xai/grok-2.description": "Grok 2 is a frontier model with state-of-the-art reasoning, strong chat, coding, and reasoning performance, and ranks above Claude 3.5 Sonnet and GPT-4 Turbo on LMSYS.",
"xai/grok-3-fast.description": "xAIs flagship model excels in enterprise use cases like data extraction, coding, and summarization, with deep domain knowledge in finance, healthcare, law, and science. The fast variant runs on quicker infrastructure for much faster responses at higher per-token cost.",
+5 -3
View File
@@ -69,9 +69,6 @@
"builtins.lobe-agent-management.render.installPlugin.plugin": "Plugin",
"builtins.lobe-agent-management.render.installPlugin.success": "Installed successfully",
"builtins.lobe-agent-management.title": "Agent Manager",
"builtins.lobe-agent-marketplace.apiName.showAgentMarketplace": "Assemble agent team",
"builtins.lobe-agent-marketplace.apiName.submitAgentPick": "Submit agent picks",
"builtins.lobe-agent-marketplace.title": "Agent Marketplace",
"builtins.lobe-agent.apiName.callSubAgent": "Call sub-agent",
"builtins.lobe-agent.apiName.callSubAgent.completed": "Sub-agent dispatched: ",
"builtins.lobe-agent.apiName.callSubAgent.loading": "Dispatching sub-agent: ",
@@ -315,6 +312,8 @@
"builtins.lobe-web-onboarding.apiName.finishOnboarding": "Finish onboarding",
"builtins.lobe-web-onboarding.apiName.readDocument": "Read document",
"builtins.lobe-web-onboarding.apiName.saveUserQuestion": "Save",
"builtins.lobe-web-onboarding.apiName.showAgentMarketplace": "Assemble agent team",
"builtins.lobe-web-onboarding.apiName.submitAgentPick": "Submit agent picks",
"builtins.lobe-web-onboarding.apiName.updateDocument": "Update document",
"builtins.lobe-web-onboarding.apiName.writeDocument": "Write document",
"builtins.lobe-web-onboarding.docType.persona": "User Persona",
@@ -325,6 +324,9 @@
"builtins.lobe-web-onboarding.inspector.hunkCount_other": "{{count}} changes",
"builtins.lobe-web-onboarding.inspector.interests_one": "{{count}} interest",
"builtins.lobe-web-onboarding.inspector.interests_other": "{{count}} interests",
"builtins.lobe-web-onboarding.render.agent": "Agent",
"builtins.lobe-web-onboarding.render.fullName": "Full name",
"builtins.lobe-web-onboarding.render.interests": "Interests",
"builtins.lobe-web-onboarding.title": "User Onboarding",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.delete": "Delete",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.deleteLines": "Delete lines",
-1
View File
@@ -33,7 +33,6 @@
"jina.description": "Founded in 2020, Jina AI is a leading search AI company. Its search stack includes vector models, rerankers, and small language models to build reliable, high-quality generative and multimodal search apps.",
"kimicodingplan.description": "Kimi Code from Moonshot AI provides access to Kimi models including K2.5 for coding tasks.",
"lmstudio.description": "LM Studio is a desktop app for developing and experimenting with LLMs on your computer.",
"lobehub.description": "LobeHub Cloud uses official APIs to access AI models and measures usage with Credits tied to model tokens.",
"longcat.description": "LongCat is a series of generative AI large models independently developed by Meituan. It is designed to enhance internal enterprise productivity and enable innovative applications through an efficient computational architecture and strong multimodal capabilities.",
"minimax.description": "Founded in 2021, MiniMax builds general-purpose AI with multimodal foundation models, including trillion-parameter MoE text models, speech models, and vision models, along with apps like Hailuo AI.",
"minimaxcodingplan.description": "MiniMax Token Plan provides access to MiniMax models including M2.7 for coding tasks via a fixed-fee subscription.",
-2
View File
@@ -913,8 +913,6 @@
"tools.builtins.lobe-agent-documents.title": "Documents",
"tools.builtins.lobe-agent-management.description": "Create, manage, and orchestrate AI agents",
"tools.builtins.lobe-agent-management.title": "Agent Management",
"tools.builtins.lobe-agent-marketplace.description": "Show users a curated Agent Marketplace card and record which templates they pick.",
"tools.builtins.lobe-agent-marketplace.title": "Agent Marketplace",
"tools.builtins.lobe-artifacts.description": "Generate and preview interactive UI components and visualizations",
"tools.builtins.lobe-artifacts.readme": "Generate and live-preview interactive UI components, data visualizations, charts, SVG graphics, and web applications. Create rich visual content that users can interact with directly.",
"tools.builtins.lobe-artifacts.title": "Artifacts",
+4
View File
@@ -115,6 +115,10 @@
"channel.line.fetchBotInfoMissingToken": "Primero ingresa el Token de Acceso del Canal, luego haz clic en \"Obtener de LINE\".",
"channel.line.fetchBotInfoSuccess": "ID de Usuario de Destino obtenido",
"channel.line.webhookManualSetup": "LINE no permite el registro programático de webhooks. Copia esta URL en la Consola de Desarrolladores de LINE (API de Mensajería → URL del Webhook), haz clic en \"Verificar\" y habilita \"Usar webhook\".",
"channel.messengerPromo.action": "Prueba Messenger",
"channel.messengerPromo.desc": "Sin configuración de bot. Chatea con LobeHub en Slack, Discord, Telegram.",
"channel.messengerPromo.dismiss": "Descartar",
"channel.messengerPromo.title": "Omite la configuración",
"channel.openPlatform": "Plataforma Abierta",
"channel.platforms": "Plataformas",
"channel.publicKey": "Clave Pública",
+4 -3
View File
@@ -314,7 +314,7 @@
"openInNewWindow": "Abrir en una nueva ventana",
"operation.contextCompression": "Contexto demasiado largo, comprimiendo historial...",
"operation.execAgentRuntime": "Preparando respuesta",
"operation.execClientTask": "Ejecutando tarea",
"operation.execClientSubAgent": "Ejecutando subagente",
"operation.execHeterogeneousAgent": "{{name}} está en ejecución",
"operation.execServerAgentRuntime": "Ejecutando… Puedes cambiar de tarea o cerrar la página; la tarea seguirá en curso.",
"operation.heterogeneousAgentFallback": "Agente externo",
@@ -567,6 +567,7 @@
"taskList.contextMenu.copyLink": "Copiar enlace",
"taskList.contextMenu.copyLinkSuccess": "Enlace copiado",
"taskList.contextMenu.priority": "Prioridad",
"taskList.contextMenu.runNow": "Ejecutar ahora",
"taskList.contextMenu.status": "Estado",
"taskList.empty": "Aún no hay tareas",
"taskList.emptyHero.greeting": "¿Qué deberíamos abordar hoy?",
@@ -771,6 +772,8 @@
"workflow.toolDisplayName.addPreferenceMemory": "Memoria guardada",
"workflow.toolDisplayName.calculate": "Calculado",
"workflow.toolDisplayName.callAgent": "Agente llamado",
"workflow.toolDisplayName.callSubAgent": "Subagente despachado",
"workflow.toolDisplayName.callSubAgents": "Subagentes despachados",
"workflow.toolDisplayName.clearTodos": "Tareas borradas",
"workflow.toolDisplayName.copyDocument": "Copió un documento",
"workflow.toolDisplayName.crawlMultiPages": "Páginas rastreadas",
@@ -785,8 +788,6 @@
"workflow.toolDisplayName.editTitle": "Título editado",
"workflow.toolDisplayName.evaluate": "Expresión evaluada",
"workflow.toolDisplayName.execScript": "Ejecutó un script",
"workflow.toolDisplayName.execTask": "Ejecutó una tarea",
"workflow.toolDisplayName.execTasks": "Tareas ejecutadas",
"workflow.toolDisplayName.execute": "Cálculo ejecutado",
"workflow.toolDisplayName.executeCode": "Código ejecutado",
"workflow.toolDisplayName.finishOnboarding": "Incorporación finalizada",
+2
View File
@@ -349,6 +349,8 @@
"loading": "Cargando...",
"mail.business": "Cooperación empresarial",
"mail.support": "Soporte por correo",
"messengerBanner.dismiss": "Cerrar",
"messengerBanner.title": "Habla con Lobe AI en tus aplicaciones de mensajería favoritas",
"more": "Más",
"navPanel.agent": "Agente",
"navPanel.customizeSidebar": "Personalizar barra lateral",
-1
View File
@@ -35,7 +35,6 @@
"messenger.linkModal.notConfigured": "Esta conexión no está disponible en este momento. Por favor, inténtalo de nuevo más tarde.",
"messenger.linkModal.openCta": "Abrir en {{platform}}",
"messenger.linkModal.scanHint": "O escanea con tu teléfono para abrir {{platform}}.",
"messenger.linkModal.title": "Conectar Messenger",
"messenger.list.discord.description": "Chatea con tus agentes de LobeHub desde cualquier servidor de Discord mediante mensajes directos con el bot de LobeHub.",
"messenger.list.slack.description": "Chatea con tus agentes de LobeHub desde cualquier espacio de trabajo de Slack mediante mensajes directos o @LobeHub.",
"messenger.list.telegram.description": "Chatea con tus agentes de LobeHub en Telegram y elige quién responde desde cualquier lugar.",
+12 -19
View File
@@ -106,7 +106,6 @@
"MiniMax-Hailuo-2.3.description": "Nuevo modelo de generación de video con mejoras integrales en movimiento corporal, realismo físico y seguimiento de instrucciones.",
"MiniMax-M1.description": "Nuevo modelo de razonamiento interno con 80K de cadena de pensamiento y 1M de entrada, con rendimiento comparable a los mejores modelos globales.",
"MiniMax-M2-Stable.description": "Diseñado para codificación eficiente y flujos de trabajo de agentes, con mayor concurrencia para uso comercial.",
"MiniMax-M2.1-Lightning.description": "Potentes capacidades de programación multilingüe con inferencia más rápida y eficiente.",
"MiniMax-M2.1-highspeed.description": "Potentes capacidades de programación multilingüe, con una experiencia de programación completamente mejorada. Más rápido y eficiente.",
"MiniMax-M2.1.description": "MiniMax-M2.1 es un modelo insignia de código abierto de MiniMax, enfocado en resolver tareas complejas del mundo real. Sus principales fortalezas son sus capacidades de programación multilingüe y su habilidad para resolver tareas complejas como un Agente.",
"MiniMax-M2.5-highspeed.description": "MiniMax M2.5 Highspeed: Mismo rendimiento que M2.5 con inferencia más rápida.",
@@ -315,13 +314,13 @@
"claude-3-haiku-20240307.description": "Claude 3 Haiku es el modelo más rápido y compacto de Anthropic, diseñado para respuestas casi instantáneas con rendimiento rápido y preciso.",
"claude-3-opus-20240229.description": "Claude 3 Opus es el modelo más potente de Anthropic para tareas altamente complejas, destacando en rendimiento, inteligencia, fluidez y comprensión.",
"claude-3-sonnet-20240229.description": "Claude 3 Sonnet equilibra inteligencia y velocidad para cargas de trabajo empresariales, ofreciendo alta utilidad a menor costo y despliegue confiable a gran escala.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 es el modelo Haiku más rápido e inteligente de Anthropic, con velocidad relámpago y pensamiento extendido.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 es el modelo Haiku más rápido e inteligente de Anthropic, con velocidad relámpago y razonamiento extendido.",
"claude-haiku-4-5.description": "Claude Haiku 4.5 de Anthropic: Haiku de nueva generación con razonamiento y visión mejorados.",
"claude-haiku-4.5.description": "Claude Haiku 4.5 es el modelo Haiku más rápido e inteligente de Anthropic, con velocidad relámpago y razonamiento extendido.",
"claude-opus-4-1-20250805-thinking.description": "Claude Opus 4.1 Thinking es una variante avanzada que puede mostrar su proceso de razonamiento.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 es el modelo más reciente y capaz de Anthropic para tareas altamente complejas, destacando en rendimiento, inteligencia, fluidez y comprensión.",
"claude-opus-4-1.description": "Claude Opus 4.1 de Anthropic: modelo de razonamiento premium con profundas capacidades de análisis.",
"claude-opus-4-20250514.description": "Claude Opus 4 es el modelo más poderoso de Anthropic para tareas altamente complejas, destacando en rendimiento, inteligencia, fluidez y comprensión.",
"claude-opus-4-20250514.description": "Claude Opus 4 es el modelo más potente de Anthropic para tareas altamente complejas, sobresaliendo en rendimiento, inteligencia, fluidez y comprensión.",
"claude-opus-4-5-20251101.description": "Claude Opus 4.5 es el modelo insignia de Anthropic, combinando inteligencia excepcional con rendimiento escalable, ideal para tareas complejas que requieren respuestas y razonamiento de la más alta calidad.",
"claude-opus-4-5.description": "Claude Opus 4.5 de Anthropic: modelo insignia con razonamiento y programación de primer nivel.",
"claude-opus-4-6.description": "Claude Opus 4.6 de Anthropic: modelo insignia con ventana de contexto de 1M y razonamiento avanzado.",
@@ -330,7 +329,7 @@
"claude-opus-4.6-fast.description": "Claude Opus 4.6 es el modelo más inteligente de Anthropic para construir agentes y programar.",
"claude-opus-4.6.description": "Claude Opus 4.6 es el modelo más inteligente de Anthropic para construir agentes y programar.",
"claude-sonnet-4-20250514-thinking.description": "Claude Sonnet 4 Thinking puede generar respuestas casi instantáneas o pensamiento paso a paso extendido con proceso visible.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 es el modelo más inteligente de Anthropic hasta la fecha, ofreciendo respuestas casi instantáneas o pensamiento extendido paso a paso con control detallado para usuarios de API.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 puede generar respuestas casi instantáneas o razonamientos detallados paso a paso con un proceso visible.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5 es el modelo más inteligente de Anthropic hasta la fecha.",
"claude-sonnet-4-5.description": "Claude Sonnet 4.5 de Anthropic: versión mejorada de Sonnet con mayor rendimiento en programación.",
"claude-sonnet-4-6.description": "Claude Sonnet 4.6 de Anthropic: última versión de Sonnet con programación superior y uso avanzado de herramientas.",
@@ -404,7 +403,7 @@
"deepseek-ai/deepseek-llm-67b-chat.description": "DeepSeek LLM Chat (67B) es un modelo innovador que ofrece una comprensión profunda del lenguaje y una interacción avanzada.",
"deepseek-ai/deepseek-v3.1-terminus.description": "DeepSeek V3.1 es un modelo de razonamiento de nueva generación con capacidades mejoradas para razonamiento complejo y cadenas de pensamiento, ideal para tareas de análisis profundo.",
"deepseek-ai/deepseek-v3.2.description": "DeepSeek V3.2 es un modelo de razonamiento de próxima generación con capacidades mejoradas de razonamiento complejo y cadenas de pensamiento.",
"deepseek-chat.description": "Alias de compatibilidad para el modo sin pensamiento de DeepSeek V4 Flash. Programado para ser descontinuado — utiliza DeepSeek V4 Flash en su lugar.",
"deepseek-chat.description": "Un nuevo modelo de código abierto que combina habilidades generales y de programación. Preserva el diálogo general del modelo de chat y la sólida capacidad de codificación del modelo de programación, con mejor alineación de preferencias. DeepSeek-V2.5 también mejora la escritura y el seguimiento de instrucciones.",
"deepseek-coder-33B-instruct.description": "DeepSeek Coder 33B es un modelo de lenguaje para código entrenado con 2T de tokens (87% código, 13% texto en chino/inglés). Introduce una ventana de contexto de 16K y tareas de completado intermedio, ofreciendo completado de código a nivel de proyecto y relleno de fragmentos.",
"deepseek-coder-v2.description": "DeepSeek Coder V2 es un modelo de código MoE de código abierto que tiene un rendimiento sólido en tareas de programación, comparable a GPT-4 Turbo.",
"deepseek-coder-v2:236b.description": "DeepSeek Coder V2 es un modelo de código MoE de código abierto que tiene un rendimiento sólido en tareas de programación, comparable a GPT-4 Turbo.",
@@ -426,7 +425,7 @@
"deepseek-r1-fast-online.description": "Versión completa rápida de DeepSeek R1 con búsqueda web en tiempo real, combinando capacidad a escala 671B y respuesta ágil.",
"deepseek-r1-online.description": "Versión completa de DeepSeek R1 con 671B de parámetros y búsqueda web en tiempo real, ofreciendo mejor comprensión y generación.",
"deepseek-r1.description": "DeepSeek-R1 utiliza datos de arranque en frío antes del aprendizaje por refuerzo y tiene un rendimiento comparable a OpenAI-o1 en matemáticas, programación y razonamiento.",
"deepseek-reasoner.description": "Alias de compatibilidad para el modo de pensamiento de DeepSeek V4 Flash. Programado para ser descontinuado — utiliza DeepSeek V4 Flash en su lugar.",
"deepseek-reasoner.description": "Un modelo de razonamiento DeepSeek enfocado en tareas de razonamiento lógico complejo.",
"deepseek-v2.description": "DeepSeek V2 es un modelo MoE eficiente para procesamiento rentable.",
"deepseek-v2:236b.description": "DeepSeek V2 236B es el modelo de DeepSeek centrado en código con fuerte generación de código.",
"deepseek-v3-0324.description": "DeepSeek-V3-0324 es un modelo MoE con 671 mil millones de parámetros, con fortalezas destacadas en programación, capacidad técnica, comprensión de contexto y manejo de textos largos.",
@@ -491,8 +490,6 @@
"doubao-seedream-4-0-250828.description": "Seedream 4.0 es un modelo de generación de imágenes de ByteDance Seed que admite entradas de texto e imagen con generación de imágenes de alta calidad y altamente controlable. Genera imágenes a partir de indicaciones de texto.",
"doubao-seedream-4-5-251128.description": "Seedream 4.5 es el último modelo multimodal de imágenes de ByteDance, que integra capacidades de texto a imagen, imagen a imagen y generación de imágenes por lotes, mientras incorpora sentido común y habilidades de razonamiento. En comparación con la versión 4.0 anterior, ofrece una calidad de generación significativamente mejorada, con mayor consistencia en la edición y fusión de múltiples imágenes. Proporciona un control más preciso sobre los detalles visuales, produciendo texto y rostros pequeños de manera más natural, y logra una disposición y color más armoniosos, mejorando la estética general.",
"doubao-seedream-5-0-260128.description": "Doubao-Seedream-5.0-lite es el último modelo de generación de imágenes de ByteDance. Por primera vez, integra capacidades de recuperación en línea, permitiendo incorporar información web en tiempo real y mejorar la actualidad de las imágenes generadas. La inteligencia del modelo también ha sido mejorada, permitiendo una interpretación precisa de instrucciones complejas y contenido visual. Además, ofrece una mejor cobertura de conocimiento global, consistencia de referencia y calidad de generación en escenarios profesionales, satisfaciendo mejor las necesidades de creación visual a nivel empresarial.",
"dreamina-seedance-2-0-260128.description": "Seedance 2.0 de ByteDance es el modelo de generación de video más poderoso, compatible con generación de video multimodal de referencia, edición de video, extensión de video, texto a video e imagen a video con audio sincronizado.",
"dreamina-seedance-2-0-fast-260128.description": "Seedance 2.0 Fast de ByteDance ofrece las mismas capacidades que Seedance 2.0 con velocidades de generación más rápidas a un precio más competitivo.",
"emohaa.description": "Emohaa es un modelo de salud mental con capacidades profesionales de asesoramiento para ayudar a los usuarios a comprender problemas emocionales.",
"ernie-4.5-0.3b.description": "ERNIE 4.5 0.3B es un modelo ligero de código abierto para implementación local y personalizada.",
"ernie-4.5-8k-preview.description": "ERNIE 4.5 8K Preview es un modelo de vista previa con contexto de 8K para evaluar ERNIE 4.5.",
@@ -517,8 +514,7 @@
"ernie-x1-turbo-32k.description": "ERNIE X1 Turbo 32K es un modelo de pensamiento rápido con contexto de 32K para razonamiento complejo y chat de múltiples turnos.",
"ernie-x1.1-preview.description": "ERNIE X1.1 Preview es una vista previa del modelo de pensamiento para evaluación y pruebas.",
"ernie-x1.1.description": "ERNIE X1.1 es un modelo de pensamiento en vista previa para evaluación y pruebas.",
"fal-ai/bytedance/seedream/v4.5.description": "Seedream 4.5, desarrollado por el equipo Seed de ByteDance, admite edición y composición de múltiples imágenes. Presenta consistencia mejorada de sujetos, seguimiento preciso de instrucciones, comprensión de lógica espacial, expresión estética, diseño de carteles y logotipos con renderizado de texto e imagen de alta precisión.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0, desarrollado por ByteDance Seed, admite entradas de texto e imagen para generación de imágenes altamente controlable y de alta calidad a partir de indicaciones.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0 es un modelo de generación de imágenes de ByteDance Seed, que admite entradas de texto e imagen con generación de imágenes altamente controlable y de alta calidad. Genera imágenes a partir de indicaciones de texto.",
"fal-ai/flux-kontext/dev.description": "Modelo FLUX.1 centrado en la edición de imágenes, compatible con entradas de texto e imagen.",
"fal-ai/flux-pro/kontext.description": "FLUX.1 Kontext [pro] acepta texto e imágenes de referencia como entrada, permitiendo ediciones locales dirigidas y transformaciones globales complejas de escenas.",
"fal-ai/flux/krea.description": "Flux Krea [dev] es un modelo de generación de imágenes con una inclinación estética hacia imágenes más realistas y naturales.",
@@ -526,8 +522,8 @@
"fal-ai/hunyuan-image/v3.description": "Un potente modelo nativo multimodal de generación de imágenes.",
"fal-ai/imagen4/preview.description": "Modelo de generación de imágenes de alta calidad de Google.",
"fal-ai/nano-banana.description": "Nano Banana es el modelo multimodal nativo más nuevo, rápido y eficiente de Google, que permite generación y edición de imágenes mediante conversación.",
"fal-ai/qwen-image-edit.description": "Un modelo profesional de edición de imágenes del equipo Qwen, que admite ediciones semánticas y de apariencia, edición precisa de texto en chino/inglés, transferencia de estilo, rotación y más.",
"fal-ai/qwen-image.description": "Un modelo poderoso de generación de imágenes del equipo Qwen con fuerte renderizado de texto en chino y estilos visuales diversos.",
"fal-ai/qwen-image-edit.description": "Un modelo profesional de edición de imágenes del equipo Qwen que admite ediciones semánticas y de apariencia, edita con precisión texto en chino e inglés, y permite ediciones de alta calidad como transferencia de estilo y rotación de objetos.",
"fal-ai/qwen-image.description": "Un potente modelo de generación de imágenes del equipo Qwen con impresionante renderizado de texto en chino y estilos visuales diversos.",
"flux-1-schnell.description": "Modelo de texto a imagen con 12 mil millones de parámetros de Black Forest Labs que utiliza destilación difusiva adversarial latente para generar imágenes de alta calidad en 1 a 4 pasos. Compite con alternativas cerradas y se lanza bajo licencia Apache-2.0 para uso personal, de investigación y comercial.",
"flux-dev.description": "Modelo de generación de imágenes de I+D de código abierto, optimizado de forma eficiente para investigación innovadora no comercial.",
"flux-kontext-max.description": "Generación y edición de imágenes contextual de última generación, combinando texto e imágenes para resultados precisos y coherentes.",
@@ -569,7 +565,7 @@
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro) es el modelo de generación de imágenes de Google y también admite chat multimodal.",
"gemini-3-pro-preview.description": "Gemini 3 Pro es el agente más potente de Google y modelo de codificación emocional, que ofrece visuales más ricos e interacción más profunda sobre un razonamiento de última generación.",
"gemini-3.1-flash-image-preview.description": "Gemini 3.1 Flash Image (Nano Banana 2) es el modelo nativo de generación de imágenes más rápido de Google con soporte de pensamiento, generación conversacional de imágenes y edición.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) ofrece calidad de imagen a nivel Pro con velocidad Flash y soporte para chat multimodal.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) es el modelo nativo de generación de imágenes más rápido de Google con soporte de razonamiento, generación conversacional de imágenes y edición.",
"gemini-3.1-flash-lite-preview.description": "Gemini 3.1 Flash-Lite Preview es el modelo multimodal más rentable de Google, optimizado para tareas agentivas de alto volumen, traducción y procesamiento de datos.",
"gemini-3.1-flash-lite.description": "Gemini 3.1 Flash-Lite es el modelo multimodal más eficiente en costos de Google, optimizado para tareas agentivas de alto volumen, traducción y procesamiento de datos.",
"gemini-3.1-pro-preview.description": "Gemini 3.1 Pro Preview mejora las capacidades de razonamiento de Gemini 3 Pro y añade soporte para un nivel de pensamiento medio.",
@@ -734,8 +730,6 @@
"grok-4-fast-reasoning.description": "Nos complace lanzar Grok 4 Fast, nuestro último avance en modelos de razonamiento rentables.",
"grok-4.20-0309-non-reasoning.description": "Variante sin razonamiento para casos de uso simples.",
"grok-4.20-0309-reasoning.description": "Modelo inteligente y rapidísimo que razona antes de responder.",
"grok-4.20-beta-0309-non-reasoning.description": "Una variante sin razonamiento para casos de uso simples.",
"grok-4.20-beta-0309-reasoning.description": "Modelo inteligente y ultrarrápido que razona antes de responder.",
"grok-4.20-multi-agent-0309.description": "Equipo de 4 o 16 agentes. Destaca en casos de investigación. No admite herramientas del lado del cliente. Solo admite herramientas del lado del servidor de xAI (como X Search, Web Search) y herramientas MCP remotas.",
"grok-4.3.description": "El modelo de lenguaje grande más orientado a la verdad en el mundo.",
"grok-4.description": "Último modelo insignia de Grok con un rendimiento inigualable en lenguaje, matemáticas y razonamiento — un verdadero todoterreno. Actualmente apunta a grok-4-0709; debido a recursos limitados, tiene un precio temporalmente un 10% más alto que el oficial y se espera que regrese al precio oficial más adelante.",
@@ -1220,8 +1214,6 @@
"qwq.description": "QwQ es un modelo de razonamiento de la familia Qwen. En comparación con los modelos estándar ajustados por instrucciones, ofrece capacidades de pensamiento y razonamiento que mejoran significativamente el rendimiento en tareas difíciles. QwQ-32B es un modelo de razonamiento de tamaño medio que compite con los mejores modelos como DeepSeek-R1 y o1-mini.",
"qwq_32b.description": "Modelo de razonamiento de tamaño medio de la familia Qwen. En comparación con los modelos estándar ajustados por instrucciones, las capacidades de pensamiento y razonamiento de QwQ mejoran significativamente el rendimiento en tareas difíciles.",
"r1-1776.description": "R1-1776 es una variante postentrenada de DeepSeek R1 diseñada para proporcionar información factual sin censura ni sesgo.",
"seedance-1-5-pro-251215.description": "Seedance 1.5 Pro de ByteDance admite generación de texto a video, imagen a video (primer cuadro, primer+último cuadro) y generación de audio sincronizado con visuales.",
"seedream-5-0-260128.description": "ByteDance-Seedream-5.0-lite de BytePlus presenta generación aumentada con recuperación web para información en tiempo real, interpretación mejorada de indicaciones complejas y mayor consistencia de referencia para creación visual profesional.",
"solar-mini-ja.description": "Solar Mini (Ja) amplía Solar Mini con un enfoque en japonés, manteniendo un rendimiento eficiente y sólido en inglés y coreano.",
"solar-mini.description": "Solar Mini es un modelo LLM compacto que supera a GPT-3.5, con una sólida capacidad multilingüe compatible con inglés y coreano, ofreciendo una solución eficiente de bajo consumo.",
"solar-pro.description": "Solar Pro es un LLM de alta inteligencia de Upstage, enfocado en el seguimiento de instrucciones en una sola GPU, con puntuaciones IFEval superiores a 80. Actualmente admite inglés; el lanzamiento completo estaba previsto para noviembre de 2024 con soporte de idiomas ampliado y contexto más largo.",
@@ -1233,7 +1225,9 @@
"sophnet/deepseek-v3.2.description": "DeepSeek V3.2 es un modelo que equilibra alta eficiencia computacional con un excelente rendimiento en razonamiento y agentes.",
"sora-2-pro.description": "Sora 2 Pro es nuestro modelo de generación de medios más avanzado, generando videos con audio sincronizado. Puede crear clips dinámicos y detallados a partir de lenguaje natural o imágenes.",
"sora-2.description": "Sora 2 es nuestro nuevo modelo poderoso de generación de medios, generando videos con audio sincronizado. Puede crear clips dinámicos y detallados a partir de lenguaje natural o imágenes.",
"spark-x.description": "Resumen de capacidades de X2: 1. Introduce ajuste dinámico del modo de razonamiento, controlado a través del campo `thinking`. 2. Longitud de contexto expandida: 64K tokens de entrada y 128K tokens de salida. 3. Admite funcionalidad de llamada de funciones (Function Call).",
"spark-x1.5.description": "Actualizaciones de X1.5: (1) añade un modo de pensamiento dinámico controlado por el campo `thinking`; (2) mayor longitud de contexto con 64K de entrada y 64K de salida; (3) admite FunctionCall.",
"spark-x2-flash.description": "Spark X2-Flash adopta una arquitectura MoE (Mixture of Experts) con un total de 30 mil millones de parámetros y admite hasta una ventana de contexto de 256K. Ofrece mejoras significativas en capacidades de agencia y codificación, y fue entrenado en un clúster de procesadores Ascend 910B AI.",
"spark-x2.description": "Resumen de capacidades de X2: 1. Introduce un ajuste dinámico del modo de razonamiento, controlado mediante el campo `thinking`. 2. Longitud de contexto ampliada: 64K tokens de entrada y 128K tokens de salida. 3. Admite funcionalidad de Function Call.",
"stable-diffusion-3-medium.description": "El último modelo de texto a imagen de Stability AI. Esta versión mejora significativamente la calidad de imagen, la comprensión del texto y la diversidad de estilos, interpretando indicaciones en lenguaje natural complejas con mayor precisión y generando imágenes más precisas y variadas.",
"stable-diffusion-3.5-large-turbo.description": "Stable Diffusion 3.5 Large Turbo se centra en la generación de imágenes de alta calidad con un fuerte nivel de detalle y fidelidad de escena.",
"stable-diffusion-xl-base-1.0.description": "Un modelo de texto a imagen de código abierto de Stability AI con generación creativa de imágenes líder en la industria. Posee una sólida comprensión de instrucciones y admite definiciones inversas de prompts para una generación precisa.",
@@ -1355,7 +1349,6 @@
"x-ai/grok-4.1-fast.description": "Grok 4 Fast es el modelo de alta capacidad y bajo costo de xAI (admite ventana de contexto de 2M), ideal para casos de uso de alta concurrencia y contexto largo.",
"x-ai/grok-4.description": "Grok 4 es el modelo insignia de razonamiento de xAI con sólidas capacidades de razonamiento y multimodales.",
"x-ai/grok-code-fast-1.description": "Grok Code Fast 1 es el modelo rápido de código de xAI con salida legible y amigable para ingeniería.",
"x1.description": "Actualizaciones de X1.5: (1) añade modo de pensamiento dinámico controlado por el campo `thinking`; (2) mayor longitud de contexto con 64K de entrada y 64K de salida; (3) admite FunctionCall.",
"xai/grok-2-vision.description": "Grok 2 Vision sobresale en tareas visuales, ofreciendo rendimiento SOTA en razonamiento visual matemático (MathVista) y preguntas sobre documentos (DocVQA). Maneja documentos, gráficos, diagramas, capturas de pantalla y fotos.",
"xai/grok-2.description": "Grok 2 es un modelo de vanguardia con razonamiento de última generación, excelente en chat, codificación y rendimiento de razonamiento, superando a Claude 3.5 Sonnet y GPT-4 Turbo en LMSYS.",
"xai/grok-3-fast.description": "El modelo insignia de xAI sobresale en casos de uso empresariales como extracción de datos, codificación y resumen, con profundo conocimiento en finanzas, salud, derecho y ciencia. La variante rápida se ejecuta en infraestructura más veloz para respuestas mucho más rápidas con mayor costo por token.",
+21 -21
View File
@@ -69,9 +69,22 @@
"builtins.lobe-agent-management.render.installPlugin.plugin": "Complemento",
"builtins.lobe-agent-management.render.installPlugin.success": "Instalado correctamente",
"builtins.lobe-agent-management.title": "Gestor de agentes",
"builtins.lobe-agent-marketplace.apiName.showAgentMarketplace": "Abrir mercado de agentes",
"builtins.lobe-agent-marketplace.apiName.submitAgentPick": "Enviar selecciones de agentes",
"builtins.lobe-agent-marketplace.title": "Mercado de Agentes",
"builtins.lobe-agent.apiName.callSubAgent": "Llamar a subagente",
"builtins.lobe-agent.apiName.callSubAgent.completed": "Subagente enviado: ",
"builtins.lobe-agent.apiName.callSubAgent.loading": "Enviando subagente: ",
"builtins.lobe-agent.apiName.callSubAgents": "Llamar a subagentes",
"builtins.lobe-agent.apiName.clearTodos": "Borrar tareas",
"builtins.lobe-agent.apiName.clearTodos.modeAll": "todas",
"builtins.lobe-agent.apiName.clearTodos.modeCompleted": "completadas",
"builtins.lobe-agent.apiName.clearTodos.result": "Borrar <mode>{{mode}}</mode> tareas",
"builtins.lobe-agent.apiName.createPlan": "Crear plan",
"builtins.lobe-agent.apiName.createPlan.result": "Crear plan: <goal>{{goal}}</goal>",
"builtins.lobe-agent.apiName.createTodos": "Crear tareas",
"builtins.lobe-agent.apiName.updatePlan": "Actualizar plan",
"builtins.lobe-agent.apiName.updatePlan.completed": "Completado",
"builtins.lobe-agent.apiName.updatePlan.modified": "Modificado",
"builtins.lobe-agent.apiName.updateTodos": "Actualizar tareas",
"builtins.lobe-agent.title": "Agente Lobe",
"builtins.lobe-claude-code.agent.instruction": "Instrucción",
"builtins.lobe-claude-code.agent.result": "Resultado",
"builtins.lobe-claude-code.todoWrite.allDone": "Todas las tareas completadas",
@@ -139,24 +152,6 @@
"builtins.lobe-group-management.inspector.executeAgentTasks.title": "Asignando tareas a:",
"builtins.lobe-group-management.inspector.speak.title": "Habla el agente designado:",
"builtins.lobe-group-management.title": "Coordinador de Grupo",
"builtins.lobe-gtd.apiName.clearTodos": "Borrar tareas",
"builtins.lobe-gtd.apiName.clearTodos.modeAll": "todas",
"builtins.lobe-gtd.apiName.clearTodos.modeCompleted": "completadas",
"builtins.lobe-gtd.apiName.clearTodos.result": "Borrar tareas <mode>{{mode}}</mode>",
"builtins.lobe-gtd.apiName.completeTodos": "Completar tareas",
"builtins.lobe-gtd.apiName.createPlan": "Crear plan",
"builtins.lobe-gtd.apiName.createPlan.result": "Plan creado: <goal>{{goal}}</goal>",
"builtins.lobe-gtd.apiName.createTodos": "Crear tareas",
"builtins.lobe-gtd.apiName.execTask": "Ejecutar tarea",
"builtins.lobe-gtd.apiName.execTask.completed": "Tarea creada: ",
"builtins.lobe-gtd.apiName.execTask.loading": "Creando tarea: ",
"builtins.lobe-gtd.apiName.execTasks": "Ejecutar tareas",
"builtins.lobe-gtd.apiName.removeTodos": "Eliminar tareas",
"builtins.lobe-gtd.apiName.updatePlan": "Actualizar plan",
"builtins.lobe-gtd.apiName.updatePlan.completed": "Completado",
"builtins.lobe-gtd.apiName.updatePlan.modified": "Modificado",
"builtins.lobe-gtd.apiName.updateTodos": "Actualizar tareas",
"builtins.lobe-gtd.title": "Herramientas de Tareas",
"builtins.lobe-knowledge-base.apiName.readKnowledge": "Leer contenido de la biblioteca",
"builtins.lobe-knowledge-base.apiName.searchKnowledgeBase": "Buscar en la biblioteca",
"builtins.lobe-knowledge-base.inspector.andMoreFiles": "y {{count}} más",
@@ -317,6 +312,8 @@
"builtins.lobe-web-onboarding.apiName.finishOnboarding": "Finalizar incorporación",
"builtins.lobe-web-onboarding.apiName.readDocument": "Leer documento",
"builtins.lobe-web-onboarding.apiName.saveUserQuestion": "Guardar pregunta del usuario",
"builtins.lobe-web-onboarding.apiName.showAgentMarketplace": "Formar equipo de agentes",
"builtins.lobe-web-onboarding.apiName.submitAgentPick": "Enviar selección de agentes",
"builtins.lobe-web-onboarding.apiName.updateDocument": "Actualizar documento",
"builtins.lobe-web-onboarding.apiName.writeDocument": "Redactar documento",
"builtins.lobe-web-onboarding.docType.persona": "Persona de usuario",
@@ -327,6 +324,9 @@
"builtins.lobe-web-onboarding.inspector.hunkCount_other": "{{count}} cambios",
"builtins.lobe-web-onboarding.inspector.interests_one": "{{count}} interés",
"builtins.lobe-web-onboarding.inspector.interests_other": "{{count}} intereses",
"builtins.lobe-web-onboarding.render.agent": "Agente",
"builtins.lobe-web-onboarding.render.fullName": "Nombre completo",
"builtins.lobe-web-onboarding.render.interests": "Intereses",
"builtins.lobe-web-onboarding.title": "Incorporación del Usuario",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.delete": "Eliminar",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.deleteLines": "Eliminar líneas",
-1
View File
@@ -33,7 +33,6 @@
"jina.description": "Fundada en 2020, Jina AI es una empresa líder en búsqueda con IA. Su pila de búsqueda incluye modelos vectoriales, reordenadores y pequeños modelos de lenguaje para construir aplicaciones generativas y multimodales confiables y de alta calidad.",
"kimicodingplan.description": "Kimi Code de Moonshot AI proporciona acceso a los modelos Kimi, incluidos K2.5, para tareas de codificación.",
"lmstudio.description": "LM Studio es una aplicación de escritorio para desarrollar y experimentar con LLMs en tu ordenador.",
"lobehub.description": "LobeHub Cloud utiliza APIs oficiales para acceder a modelos de IA y mide el uso con Créditos vinculados a los tokens del modelo.",
"longcat.description": "LongCat es una serie de modelos grandes de inteligencia artificial generativa desarrollados de manera independiente por Meituan. Está diseñado para mejorar la productividad interna de la empresa y permitir aplicaciones innovadoras mediante una arquitectura computacional eficiente y sólidas capacidades multimodales.",
"minimax.description": "Fundada en 2021, MiniMax desarrolla IA de propósito general con modelos fundacionales multimodales, incluyendo modelos de texto MoE con billones de parámetros, modelos de voz y visión, junto con aplicaciones como Hailuo AI.",
"minimaxcodingplan.description": "El Plan de Tokens MiniMax proporciona acceso a los modelos MiniMax, incluidos M2.7, para tareas de codificación mediante una suscripción de tarifa fija.",
-2
View File
@@ -913,8 +913,6 @@
"tools.builtins.lobe-agent-documents.title": "Documentos",
"tools.builtins.lobe-agent-management.description": "Crea, gestiona y orquesta agentes de IA",
"tools.builtins.lobe-agent-management.title": "Gestión de Agentes",
"tools.builtins.lobe-agent-marketplace.description": "Muestra a los usuarios una tarjeta del Mercado de Agentes seleccionada y registra qué plantillas eligen.",
"tools.builtins.lobe-agent-marketplace.title": "Mercado de Agentes",
"tools.builtins.lobe-artifacts.description": "Genera y previsualiza en vivo componentes de interfaz interactivos, visualizaciones de datos, gráficos, imágenes SVG y aplicaciones web. Crea contenido visual enriquecido con el que los usuarios pueden interactuar directamente.",
"tools.builtins.lobe-artifacts.readme": "Genera y previsualiza en vivo componentes de interfaz interactivos, visualizaciones de datos, gráficos, SVG y aplicaciones web. Crea contenido visual enriquecido con el que los usuarios pueden interactuar directamente.",
"tools.builtins.lobe-artifacts.title": "Artefactos",
+45 -45
View File
@@ -56,51 +56,51 @@
"dalle.generating": "Generando...",
"dalle.images": "Imágenes:",
"dalle.prompt": "Prompt",
"lobe-gtd.actions.add": "Agregar",
"lobe-gtd.actions.clearCompleted": "Borrar Completados",
"lobe-gtd.actions.placeholder": "Introduce una tarea pendiente...",
"lobe-gtd.addTodo.placeholder": "Agregar una tarea pendiente...",
"lobe-gtd.clearTodos.cleared": "{{count}} elemento(s) borrado(s)",
"lobe-gtd.clearTodos.clearedCompleted": "{{count}} elemento(s) completado(s) borrado(s)",
"lobe-gtd.clearTodos.clearedCompleted_one": "{{count}} elemento completado borrado",
"lobe-gtd.clearTodos.clearedCompleted_other": "{{count}} elementos completados borrados",
"lobe-gtd.clearTodos.cleared_one": "{{count}} elemento borrado",
"lobe-gtd.clearTodos.cleared_other": "{{count}} elementos borrados",
"lobe-gtd.clearTodos.header": "Borrar Tareas Pendientes",
"lobe-gtd.clearTodos.label": "Elige qué borrar:",
"lobe-gtd.clearTodos.noItems": "No hay elementos para borrar",
"lobe-gtd.clearTodos.option.all": "Borrar todos los elementos (incluidos los pendientes)",
"lobe-gtd.clearTodos.option.completed": "Borrar solo los completados",
"lobe-gtd.clearTodos.remaining": "{{count}} elemento(s) restante(s)",
"lobe-gtd.clearTodos.remaining_one": "{{count}} elemento restante",
"lobe-gtd.clearTodos.remaining_other": "{{count}} elementos restantes",
"lobe-gtd.completeTodos.completed": "{{count}} elemento(s) completado(s)",
"lobe-gtd.completeTodos.completed_one": "{{count}} elemento completado",
"lobe-gtd.completeTodos.completed_other": "{{count}} elementos completados",
"lobe-gtd.createPlan.context.label": "Contexto (opcional)",
"lobe-gtd.createPlan.context.placeholder": "Antecedentes, restricciones, consideraciones...",
"lobe-gtd.createPlan.description.label": "Descripción",
"lobe-gtd.createPlan.description.placeholder": "Resumen breve del plan",
"lobe-gtd.createPlan.goal.label": "Objetivo",
"lobe-gtd.createPlan.goal.placeholder": "¿Qué deseas lograr?",
"lobe-gtd.createTodos.created": "{{count}} tarea(s) creada(s)",
"lobe-gtd.createTodos.created_one": "{{count}} tarea creada",
"lobe-gtd.createTodos.created_other": "{{count}} tareas creadas",
"lobe-gtd.createTodos.total": "Total: {{count}} elemento(s)",
"lobe-gtd.createTodos.total_one": "Total: {{count}} elemento",
"lobe-gtd.createTodos.total_other": "Total: {{count}} elementos",
"lobe-gtd.removeTodos.removed": "{{count}} elemento(s) eliminado(s)",
"lobe-gtd.removeTodos.removed_one": "{{count}} elemento eliminado",
"lobe-gtd.removeTodos.removed_other": "{{count}} elementos eliminados",
"lobe-gtd.status.done": "{{count}} completado(s)",
"lobe-gtd.status.pending": "{{count}} pendiente(s)",
"lobe-gtd.todoItem.placeholder": "Introduce una tarea pendiente...",
"lobe-gtd.todoList.empty": "La lista de tareas está vacía",
"lobe-gtd.todoList.items": "{{count}} elemento(s)",
"lobe-gtd.todoList.items_one": "{{count}} elemento",
"lobe-gtd.todoList.items_other": "{{count}} elementos",
"lobe-gtd.todoList.title": "Lista de Tareas",
"lobe-gtd.updateTodos.updated": "Lista de tareas actualizada",
"lobe-agent.actions.add": "Agregar",
"lobe-agent.actions.clearCompleted": "Limpiar completados",
"lobe-agent.actions.placeholder": "Introduce un elemento de la lista de tareas...",
"lobe-agent.addTodo.placeholder": "Añadir un elemento a la lista de tareas...",
"lobe-agent.clearTodos.cleared": "{{count}} elemento(s) eliminado(s)",
"lobe-agent.clearTodos.clearedCompleted": "{{count}} elemento(s) completado(s) eliminado(s)",
"lobe-agent.clearTodos.clearedCompleted_one": "{{count}} elemento completado eliminado",
"lobe-agent.clearTodos.clearedCompleted_other": "{{count}} elementos completados eliminados",
"lobe-agent.clearTodos.cleared_one": "{{count}} elemento eliminado",
"lobe-agent.clearTodos.cleared_other": "{{count}} elementos eliminados",
"lobe-agent.clearTodos.header": "Eliminar elementos de la lista de tareas",
"lobe-agent.clearTodos.label": "Elige qué eliminar:",
"lobe-agent.clearTodos.noItems": "No hay elementos para eliminar",
"lobe-agent.clearTodos.option.all": "Eliminar todos los elementos (incluidos los pendientes)",
"lobe-agent.clearTodos.option.completed": "Eliminar solo los elementos completados",
"lobe-agent.clearTodos.remaining": "{{count}} elemento(s) restante(s)",
"lobe-agent.clearTodos.remaining_one": "{{count}} elemento restante",
"lobe-agent.clearTodos.remaining_other": "{{count}} elementos restantes",
"lobe-agent.completeTodos.completed": "{{count}} elemento(s) completado(s)",
"lobe-agent.completeTodos.completed_one": "{{count}} elemento completado",
"lobe-agent.completeTodos.completed_other": "{{count}} elementos completados",
"lobe-agent.createPlan.context.label": "Contexto (opcional)",
"lobe-agent.createPlan.context.placeholder": "Antecedentes, restricciones, consideraciones...",
"lobe-agent.createPlan.description.label": "Descripción",
"lobe-agent.createPlan.description.placeholder": "Resumen breve del plan",
"lobe-agent.createPlan.goal.label": "Objetivo",
"lobe-agent.createPlan.goal.placeholder": "¿Qué quieres lograr?",
"lobe-agent.createTodos.created": "{{count}} elemento(s) de la lista de tareas creado(s)",
"lobe-agent.createTodos.created_one": "{{count}} elemento de la lista de tareas creado",
"lobe-agent.createTodos.created_other": "{{count}} elementos de la lista de tareas creados",
"lobe-agent.createTodos.total": "Total: {{count}} elemento(s)",
"lobe-agent.createTodos.total_one": "Total: {{count}} elemento",
"lobe-agent.createTodos.total_other": "Total: {{count}} elementos",
"lobe-agent.removeTodos.removed": "{{count}} elemento(s) eliminado(s)",
"lobe-agent.removeTodos.removed_one": "{{count}} elemento eliminado",
"lobe-agent.removeTodos.removed_other": "{{count}} elementos eliminados",
"lobe-agent.status.done": "{{count}} completado(s)",
"lobe-agent.status.pending": "{{count}} pendiente(s)",
"lobe-agent.todoItem.placeholder": "Introduce un elemento de la lista de tareas...",
"lobe-agent.todoList.empty": "La lista de tareas está vacía",
"lobe-agent.todoList.items": "{{count}} elemento(s)",
"lobe-agent.todoList.items_one": "{{count}} elemento",
"lobe-agent.todoList.items_other": "{{count}} elementos",
"lobe-agent.todoList.title": "Lista de Tareas",
"lobe-agent.updateTodos.updated": "Lista de tareas actualizada",
"lobe-knowledge-base.readKnowledge.meta.chars": "Cantidad de Caracteres",
"lobe-knowledge-base.readKnowledge.meta.lines": "Cantidad de Líneas",
"localFiles.editFile.newString": "Reemplazar con",
+4
View File
@@ -115,6 +115,10 @@
"channel.line.fetchBotInfoMissingToken": "ابتدا توکن دسترسی کانال را وارد کنید، سپس روی \"دریافت از LINE\" کلیک کنید.",
"channel.line.fetchBotInfoSuccess": "شناسه کاربری مقصد دریافت شد",
"channel.line.webhookManualSetup": "LINE اجازه ثبت وب‌هوک به صورت برنامه‌ریزی شده را نمی‌دهد. این URL را در کنسول توسعه‌دهندگان LINE (Messaging API → Webhook URL) کپی کنید، روی \"تأیید\" کلیک کنید و \"استفاده از وب‌هوک\" را فعال کنید.",
"channel.messengerPromo.action": "مسنجر را امتحان کنید",
"channel.messengerPromo.desc": "بدون نیاز به تنظیم ربات. با LobeHub در Slack، Discord، Telegram گفتگو کنید.",
"channel.messengerPromo.dismiss": "رد کردن",
"channel.messengerPromo.title": "از تنظیمات صرف‌نظر کنید",
"channel.openPlatform": "پلتفرم باز",
"channel.platforms": "پلتفرم‌ها",
"channel.publicKey": "کلید عمومی",
+4 -3
View File
@@ -314,7 +314,7 @@
"openInNewWindow": "باز کردن در پنجره جدید",
"operation.contextCompression": "متن بیش از حد طولانی است، در حال فشرده‌سازی تاریخچه...",
"operation.execAgentRuntime": "در حال آماده‌سازی پاسخ",
"operation.execClientTask": "در حال اجرای وظیفه",
"operation.execClientSubAgent": "اجرای زیرعامل",
"operation.execHeterogeneousAgent": "{{name}} در حال اجرا است",
"operation.execServerAgentRuntime": "در حال اجرا… می‌توانید وظایف را تغییر دهید یا صفحه را ببندید — وظیفه همچنان ادامه خواهد داشت.",
"operation.heterogeneousAgentFallback": "عامل خارجی",
@@ -567,6 +567,7 @@
"taskList.contextMenu.copyLink": "کپی لینک",
"taskList.contextMenu.copyLinkSuccess": "لینک کپی شد",
"taskList.contextMenu.priority": "اولویت",
"taskList.contextMenu.runNow": "اکنون اجرا کن",
"taskList.contextMenu.status": "وضعیت",
"taskList.empty": "هنوز وظیفه‌ای وجود ندارد",
"taskList.emptyHero.greeting": "امروز چه کاری را باید انجام دهیم؟",
@@ -771,6 +772,8 @@
"workflow.toolDisplayName.addPreferenceMemory": "حافظه ذخیره‌شده",
"workflow.toolDisplayName.calculate": "محاسبه‌شده",
"workflow.toolDisplayName.callAgent": "یک عامل فراخوانی شد",
"workflow.toolDisplayName.callSubAgent": "زیرعامل ارسال شد",
"workflow.toolDisplayName.callSubAgents": "زیرعامل‌ها ارسال شدند",
"workflow.toolDisplayName.clearTodos": "وظایف پاک شدند",
"workflow.toolDisplayName.copyDocument": "یک سند کپی شد",
"workflow.toolDisplayName.crawlMultiPages": "صفحات پیمایش‌شده",
@@ -785,8 +788,6 @@
"workflow.toolDisplayName.editTitle": "عنوان ویرایش‌شده",
"workflow.toolDisplayName.evaluate": "عبارت ارزیابی‌شده",
"workflow.toolDisplayName.execScript": "یک اسکریپت اجرا شد",
"workflow.toolDisplayName.execTask": "یک وظیفه اجرا شد",
"workflow.toolDisplayName.execTasks": "وظایف اجراشده",
"workflow.toolDisplayName.execute": "محاسبه انجام شد",
"workflow.toolDisplayName.executeCode": "کد اجرا شد",
"workflow.toolDisplayName.finishOnboarding": "اتمام فرایند آشنایی اولیه",
+2
View File
@@ -349,6 +349,8 @@
"loading": "در حال بارگذاری...",
"mail.business": "همکاری تجاری",
"mail.support": "پشتیبانی ایمیلی",
"messengerBanner.dismiss": "بستن",
"messengerBanner.title": "با Lobe AI در برنامه‌های پیام‌رسان محبوب خود صحبت کنید",
"more": "بیشتر",
"navPanel.agent": "نماینده",
"navPanel.customizeSidebar": "سفارشی‌سازی نوار کناری",
-1
View File
@@ -35,7 +35,6 @@
"messenger.linkModal.notConfigured": "این اتصال در حال حاضر در دسترس نیست. لطفاً بعداً دوباره امتحان کنید.",
"messenger.linkModal.openCta": "باز کردن در {{platform}}",
"messenger.linkModal.scanHint": "یا با تلفن خود اسکن کنید تا {{platform}} باز شود.",
"messenger.linkModal.title": "اتصال پیام‌رسان",
"messenger.list.discord.description": "با نمایندگان LobeHub خود از هر سرور Discord از طریق پیام مستقیم با ربات LobeHub گفتگو کنید.",
"messenger.list.slack.description": "با نمایندگان LobeHub خود از هر فضای کاری Slack از طریق پیام مستقیم یا @LobeHub گفتگو کنید.",
"messenger.list.telegram.description": "در Telegram با نمایندگان LobeHub خود گفتگو کنید و انتخاب کنید کدام یک پاسخ دهد.",
+12 -19
View File
@@ -106,7 +106,6 @@
"MiniMax-Hailuo-2.3.description": "مدل جدید تولید ویدئو با ارتقاهای جامع در حرکت بدن، واقع‌گرایی فیزیکی و پیروی از دستورالعمل‌ها.",
"MiniMax-M1.description": "یک مدل استدلالی داخلی جدید با ۸۰ هزار زنجیره تفکر و ورودی ۱ میلیون توکن، با عملکردی در سطح مدل‌های برتر جهانی.",
"MiniMax-M2-Stable.description": "طراحی‌شده برای کدنویسی کارآمد و جریان‌های کاری عامل‌محور، با هم‌زمانی بالاتر برای استفاده تجاری.",
"MiniMax-M2.1-Lightning.description": "قابلیت‌های برنامه‌نویسی چندزبانه قدرتمند با استنتاج سریع‌تر و کارآمدتر.",
"MiniMax-M2.1-highspeed.description": "قابلیت‌های برنامه‌نویسی چندزبانه قدرتمند، تجربه برنامه‌نویسی کاملاً ارتقاء یافته. سریع‌تر و کارآمدتر.",
"MiniMax-M2.1.description": "MiniMax-M2.1 یک مدل بزرگ متن‌باز پیشرفته از MiniMax است که بر حل وظایف پیچیده دنیای واقعی تمرکز دارد. نقاط قوت اصلی آن شامل توانایی برنامه‌نویسی چندزبانه و قابلیت عمل به‌عنوان یک عامل هوشمند برای حل مسائل پیچیده است.",
"MiniMax-M2.5-highspeed.description": "MiniMax M2.5 Highspeed: همان عملکرد M2.5 با استنتاج سریع‌تر.",
@@ -315,13 +314,13 @@
"claude-3-haiku-20240307.description": "Claude 3 Haiku سریع‌ترین و فشرده‌ترین مدل Anthropic است که برای پاسخ‌های تقریباً فوری با عملکرد سریع و دقیق طراحی شده است.",
"claude-3-opus-20240229.description": "Claude 3 Opus قدرتمندترین مدل Anthropic برای وظایف بسیار پیچیده است که در عملکرد، هوش، روانی و درک زبان برتری دارد.",
"claude-3-sonnet-20240229.description": "Claude 3 Sonnet تعادل بین هوش و سرعت را برای بارهای کاری سازمانی برقرار می‌کند و با هزینه کمتر، بهره‌وری بالا و استقرار قابل اعتماد در مقیاس وسیع را ارائه می‌دهد.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 سریع‌ترین و هوشمندترین مدل Haiku از Anthropic است، با سرعت فوق‌العاده و تفکر پیشرفته.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 سریع‌ترین و هوشمندترین مدل Haiku از Anthropic است که با سرعت فوق‌العاده و توانایی استدلال پیشرفته ارائه می‌شود.",
"claude-haiku-4-5.description": "Claude Haiku 4.5 از Anthropic — نسل جدید Haiku با استدلال و پردازش تصویری پیشرفته.",
"claude-haiku-4.5.description": "Claude Haiku 4.5 سریع‌ترین و هوشمندترین مدل Haiku از Anthropic است که با سرعت برق‌آسا و توانایی استدلال پیشرفته ارائه می‌شود.",
"claude-opus-4-1-20250805-thinking.description": "Claude Opus 4.1 Thinking یک نسخه پیشرفته است که می‌تواند فرآیند استدلال خود را آشکار کند.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 جدیدترین و توانمندترین مدل Anthropic برای وظایف بسیار پیچیده است که در عملکرد، هوش، روانی و درک برتری دارد.",
"claude-opus-4-1.description": "Claude Opus 4.1 از Anthropic — مدل استدلال سطح‌بالا با توانایی تحلیل عمیق.",
"claude-opus-4-20250514.description": "Claude Opus 4 قدرتمندترین مدل Anthropic برای وظایف بسیار پیچیده است که در عملکرد، هوش، روانی و درک برتری دارد.",
"claude-opus-4-20250514.description": "Claude Opus 4 قدرتمندترین مدل Anthropic برای وظایف بسیار پیچیده است که در عملکرد، هوش، روانی و فهم برتری دارد.",
"claude-opus-4-5-20251101.description": "Claude Opus 4.5 مدل پرچم‌دار Anthropic است که هوش برجسته را با عملکرد مقیاس‌پذیر ترکیب می‌کند و برای وظایف پیچیده‌ای که نیاز به پاسخ‌های باکیفیت و استدلال دارند، ایده‌آل است.",
"claude-opus-4-5.description": "Claude Opus 4.5 از Anthropic — مدل پرچم‌دار با استدلال و کدنویسی سطح‌بالا.",
"claude-opus-4-6.description": "Claude Opus 4.6 از Anthropic — مدل پرچم‌دار با پنجره زمینه ۱ میلیون و توانایی استدلال پیشرفته.",
@@ -330,7 +329,7 @@
"claude-opus-4.6-fast.description": "Claude Opus 4.6 هوشمندترین مدل Anthropic برای ساخت عوامل و کدنویسی است.",
"claude-opus-4.6.description": "Claude Opus 4.6 هوشمندترین مدل Anthropic برای ساخت عوامل و کدنویسی است.",
"claude-sonnet-4-20250514-thinking.description": "Claude Sonnet 4 Thinking می‌تواند پاسخ‌های تقریباً فوری یا تفکر گام‌به‌گام طولانی با فرآیند قابل مشاهده تولید کند.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 هوشمندترین مدل Anthropic تا به امروز است که پاسخ‌های تقریباً فوری یا تفکر گام‌به‌گام گسترده با کنترل دقیق برای کاربران API ارائه می‌دهد.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 می‌تواند پاسخ‌های تقریباً فوری یا تفکر گام‌به‌گام گسترده با فرآیند قابل مشاهده تولید کند.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5 هوشمندترین مدل Anthropic تا به امروز است.",
"claude-sonnet-4-5.description": "Claude Sonnet 4.5 از Anthropic — نسخه بهبود‌یافته Sonnet با عملکرد بهتر در کدنویسی.",
"claude-sonnet-4-6.description": "Claude Sonnet 4.6 از Anthropic — جدیدترین Sonnet با کدنویسی برتر و استفاده بهتر از ابزار.",
@@ -404,7 +403,7 @@
"deepseek-ai/deepseek-llm-67b-chat.description": "DeepSeek LLM Chat (67B) یک مدل نوآورانه با درک عمیق زبان و تعامل است.",
"deepseek-ai/deepseek-v3.1-terminus.description": "DeepSeek V3.1 یک مدل استدلال نسل بعدی با توانایی استدلال پیچیده و زنجیره تفکر برای وظایف تحلیلی عمیق است.",
"deepseek-ai/deepseek-v3.2.description": "DeepSeek V3.2 یک مدل استدلال نسل بعدی با قابلیت‌های استدلال پیچیده‌تر و زنجیره‌ای از تفکر است.",
"deepseek-chat.description": "نام مستعار سازگار برای حالت غیرتفکری DeepSeek V4 Flash. برنامه‌ریزی شده برای توقف استفاده — به جای آن از DeepSeek V4 Flash استفاده کنید.",
"deepseek-chat.description": "یک مدل متن‌باز جدید که توانایی‌های عمومی و کدنویسی را ترکیب می‌کند. این مدل گفتگوی عمومی مدل چت و کدنویسی قوی مدل کدنویس را حفظ کرده و با هم‌ترازی بهتر ترجیحات ارائه می‌دهد. DeepSeek-V2.5 همچنین نوشتن و پیروی از دستورالعمل‌ها را بهبود می‌بخشد.",
"deepseek-coder-33B-instruct.description": "DeepSeek Coder 33B یک مدل زبان برنامه‌نویسی است که با ۲ تریلیون توکن (۸۷٪ کد، ۱۳٪ متن چینی/انگلیسی) آموزش دیده است. این مدل دارای پنجره متنی ۱۶K و وظایف تکمیل در میانه است که تکمیل کد در سطح پروژه و پر کردن قطعات کد را فراهم می‌کند.",
"deepseek-coder-v2.description": "DeepSeek Coder V2 یک مدل کدنویسی MoE متن‌باز است که در وظایف برنامه‌نویسی عملکردی هم‌سطح با GPT-4 Turbo دارد.",
"deepseek-coder-v2:236b.description": "DeepSeek Coder V2 یک مدل کدنویسی MoE متن‌باز است که در وظایف برنامه‌نویسی عملکردی هم‌سطح با GPT-4 Turbo دارد.",
@@ -426,7 +425,7 @@
"deepseek-r1-fast-online.description": "نسخه کامل سریع DeepSeek R1 با جستجوی وب در زمان واقعی که توانایی در مقیاس ۶۷۱B را با پاسخ‌دهی سریع‌تر ترکیب می‌کند.",
"deepseek-r1-online.description": "نسخه کامل DeepSeek R1 با ۶۷۱ میلیارد پارامتر و جستجوی وب در زمان واقعی که درک و تولید قوی‌تری را ارائه می‌دهد.",
"deepseek-r1.description": "DeepSeek-R1 پیش از یادگیری تقویتی از داده‌های شروع سرد استفاده می‌کند و در وظایف ریاضی، کدنویسی و استدلال عملکردی هم‌سطح با OpenAI-o1 دارد.",
"deepseek-reasoner.description": "نام مستعار سازگار برای حالت تفکری DeepSeek V4 Flash. برنامه‌ریزی شده برای توقف استفاده — به جای آن از DeepSeek V4 Flash استفاده کنید.",
"deepseek-reasoner.description": "یک مدل استدلال DeepSeek که بر وظایف استدلال منطقی پیچیده متمرکز است.",
"deepseek-v2.description": "DeepSeek V2 یک مدل MoE کارآمد است که پردازش مقرون‌به‌صرفه را امکان‌پذیر می‌سازد.",
"deepseek-v2:236b.description": "DeepSeek V2 236B مدل متمرکز بر کدنویسی DeepSeek است که توانایی بالایی در تولید کد دارد.",
"deepseek-v3-0324.description": "DeepSeek-V3-0324 یک مدل MoE با ۶۷۱ میلیارد پارامتر است که در برنامه‌نویسی، توانایی‌های فنی، درک زمینه و پردازش متون بلند عملکرد برجسته‌ای دارد.",
@@ -491,8 +490,6 @@
"doubao-seedream-4-0-250828.description": "Seedream 4.0 یک مدل تولید تصویر از ByteDance Seed است که از ورودی‌های متن و تصویر پشتیبانی می‌کند و تولید تصویر با کیفیت بالا و قابل کنترل را ارائه می‌دهد. این مدل تصاویر را از دستورات متنی تولید می‌کند.",
"doubao-seedream-4-5-251128.description": "Seedream 4.5 جدیدترین مدل چندوجهی تصویر ByteDance است که قابلیت‌های تبدیل متن به تصویر، تصویر به تصویر و تولید دسته‌ای تصاویر را ادغام می‌کند و توانایی‌های استدلال و دانش عمومی را نیز در بر می‌گیرد. در مقایسه با نسخه قبلی 4.0، کیفیت تولید به‌طور قابل‌توجهی بهبود یافته است، با سازگاری بهتر در ویرایش و ترکیب چند تصویر. کنترل دقیق‌تری بر جزئیات بصری ارائه می‌دهد، متن‌های کوچک و چهره‌های کوچک را به‌طور طبیعی‌تر تولید می‌کند و به هماهنگی بهتر در چیدمان و رنگ دست می‌یابد، که زیبایی کلی را افزایش می‌دهد.",
"doubao-seedream-5-0-260128.description": "Doubao-Seedream-5.0-lite جدیدترین مدل تولید تصویر ByteDance است. برای اولین بار، قابلیت‌های بازیابی آنلاین را ادغام کرده است که به آن امکان می‌دهد اطلاعات وب لحظه‌ای را وارد کند و به‌موقع بودن تصاویر تولید شده را افزایش دهد. هوش مدل نیز ارتقا یافته است، که تفسیر دقیق دستورالعمل‌های پیچیده و محتوای بصری را امکان‌پذیر می‌کند. علاوه بر این، پوشش دانش جهانی، سازگاری مرجع و کیفیت تولید در سناریوهای حرفه‌ای بهبود یافته است، که نیازهای خلق بصری در سطح سازمانی را بهتر برآورده می‌کند.",
"dreamina-seedance-2-0-260128.description": "Seedance 2.0 از ByteDance قدرتمندترین مدل تولید ویدئو است که از تولید ویدئو چندوجهی مرجع، ویرایش ویدئو، گسترش ویدئو، متن به ویدئو و تصویر به ویدئو با صدای همگام‌سازی شده پشتیبانی می‌کند.",
"dreamina-seedance-2-0-fast-260128.description": "Seedance 2.0 Fast از ByteDance همان قابلیت‌های Seedance 2.0 را با سرعت تولید بالاتر و قیمت رقابتی‌تر ارائه می‌دهد.",
"emohaa.description": "Emohaa یک مدل سلامت روان با توانایی مشاوره حرفه‌ای است که به کاربران در درک مسائل احساسی کمک می‌کند.",
"ernie-4.5-0.3b.description": "ERNIE 4.5 0.3B یک مدل سبک متن‌باز برای استقرار محلی و سفارشی‌سازی شده است.",
"ernie-4.5-8k-preview.description": "پیش‌نمایش مدل با پنجره متنی ۸هزار توکن برای ارزیابی ERNIE 4.5.",
@@ -517,8 +514,7 @@
"ernie-x1-turbo-32k.description": "ERNIE X1 Turbo 32K یک مدل تفکر سریع با زمینه ۳۲K برای استدلال پیچیده و گفت‌وگوی چندمرحله‌ای است.",
"ernie-x1.1-preview.description": "پیش‌نمایش ERNIE X1.1 یک مدل تفکر برای ارزیابی و آزمایش است.",
"ernie-x1.1.description": "ERNIE X1.1 یک مدل تفکر پیش‌نمایش برای ارزیابی و آزمایش است.",
"fal-ai/bytedance/seedream/v4.5.description": "Seedream 4.5، ساخته شده توسط تیم Seed ByteDance، از ویرایش و ترکیب چندتصویری پشتیبانی می‌کند. ویژگی‌های آن شامل حفظ موضوع بهبود‌یافته، پیروی دقیق از دستورالعمل‌ها، درک منطق فضایی، بیان زیبایی‌شناختی، طراحی پوستر و لوگو با رندر متن-تصویر با دقت بالا است.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0، ساخته شده توسط تیم Seed ByteDance، از ورودی‌های متن و تصویر برای تولید تصاویر با کیفیت بالا و قابل کنترل از طریق دستورات پشتیبانی می‌کند.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0 یک مدل تولید تصویر از ByteDance Seed است که از ورودی‌های متنی و تصویری پشتیبانی می‌کند و تولید تصاویر با کیفیت بالا و قابل کنترل را ارائه می‌دهد. این مدل تصاویر را از دستورات متنی تولید می‌کند.",
"fal-ai/flux-kontext/dev.description": "مدل FLUX.1 با تمرکز بر ویرایش تصویر که از ورودی‌های متنی و تصویری پشتیبانی می‌کند.",
"fal-ai/flux-pro/kontext.description": "FLUX.1 Kontext [pro] ورودی‌های متنی و تصاویر مرجع را می‌پذیرد و امکان ویرایش‌های محلی هدفمند و تغییرات پیچیده در صحنه کلی را فراهم می‌کند.",
"fal-ai/flux/krea.description": "Flux Krea [dev] یک مدل تولید تصویر با تمایل زیبایی‌شناسی به تصاویر طبیعی و واقع‌گرایانه‌تر است.",
@@ -526,8 +522,8 @@
"fal-ai/hunyuan-image/v3.description": "یک مدل قدرتمند بومی چندوجهی برای تولید تصویر.",
"fal-ai/imagen4/preview.description": "مدل تولید تصویر با کیفیت بالا از گوگل.",
"fal-ai/nano-banana.description": "Nano Banana جدیدترین، سریع‌ترین و کارآمدترین مدل چندوجهی بومی گوگل است که امکان تولید و ویرایش تصویر از طریق مکالمه را فراهم می‌کند.",
"fal-ai/qwen-image-edit.description": "مدل ویرایش تصویر حرفه‌ای از تیم Qwen که از ویرایش‌های معنایی و ظاهری، ویرایش دقیق متن‌های چینی/انگلیسی، انتقال سبک، چرخش و موارد دیگر پشتیبانی می‌کند.",
"fal-ai/qwen-image.description": "مدل قدرتمند تولید تصویر از تیم Qwen با قابلیت رندر قوی متن چینی و سبک‌های بصری متنوع.",
"fal-ai/qwen-image-edit.description": "یک مدل ویرایش تصویر حرفه‌ای از تیم Qwen که از ویرایش‌های معنایی و ظاهری پشتیبانی می‌کند، متن‌های چینی و انگلیسی را با دقت ویرایش می‌کند و ویرایش‌های با کیفیت بالا مانند انتقال سبک و چرخش اشیاء را ممکن می‌سازد.",
"fal-ai/qwen-image.description": "یک مدل قدرتمند تولید تصویر از تیم Qwen با قابلیت‌های برجسته در رندر متن چینی و سبک‌های بصری متنوع.",
"flux-1-schnell.description": "مدل تبدیل متن به تصویر با ۱۲ میلیارد پارامتر از Black Forest Labs که از تقطیر انتشار تقابلی نهفته برای تولید تصاویر با کیفیت بالا در ۱ تا ۴ مرحله استفاده می‌کند. این مدل با جایگزین‌های بسته رقابت می‌کند و تحت مجوز Apache-2.0 برای استفاده شخصی، تحقیقاتی و تجاری منتشر شده است.",
"flux-dev.description": "مدل تولید تصویر متن‌باز برای تحقیق و توسعه، به‌طور کارآمد برای پژوهش‌های نوآورانهٔ غیرتجاری بهینه‌سازی شده است.",
"flux-kontext-max.description": "تولید و ویرایش تصویر متنی-زمینه‌ای پیشرفته که متن و تصویر را برای نتایج دقیق و منسجم ترکیب می‌کند.",
@@ -569,7 +565,7 @@
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro) مدل تولید تصویر گوگل است که از چت چندوجهی نیز پشتیبانی می‌کند.",
"gemini-3-pro-preview.description": "Gemini 3 Pro قدرتمندترین مدل عامل و کدنویسی احساسی گوگل است که تعاملات بصری غنی‌تر و تعامل عمیق‌تری را بر پایه استدلال پیشرفته ارائه می‌دهد.",
"gemini-3.1-flash-image-preview.description": "Gemini 3.1 Flash Image (Nano Banana 2) سریع‌ترین مدل تولید تصویر بومی گوگل با پشتیبانی از تفکر، تولید و ویرایش تصویر مکالمه‌ای است.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) کیفیت تصویر در سطح Pro را با سرعت Flash و پشتیبانی از چت چندوجهی ارائه می‌دهد.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) سریع‌ترین مدل تولید تصویر بومی گوگل است که از تفکر، تولید و ویرایش تصاویر در مکالمات پشتیبانی می‌کند.",
"gemini-3.1-flash-lite-preview.description": "Gemini 3.1 Flash-Lite Preview اقتصادی‌ترین مدل چندوجهی گوگل است که برای وظایف عامل‌محور با حجم بالا، ترجمه و پردازش داده‌ها بهینه شده است.",
"gemini-3.1-flash-lite.description": "Gemini 3.1 Flash-Lite اقتصادی‌ترین مدل چندوجهی گوگل است که برای وظایف عاملی با حجم بالا، ترجمه و پردازش داده بهینه شده است.",
"gemini-3.1-pro-preview.description": "پیش‌نمایش Gemini 3.1 Pro قابلیت‌های استدلال بهبود یافته را به Gemini 3 Pro اضافه می‌کند و از سطح تفکر متوسط پشتیبانی می‌کند.",
@@ -734,8 +730,6 @@
"grok-4-fast-reasoning.description": "با افتخار Grok 4 Fast را معرفی می‌کنیم، جدیدترین پیشرفت ما در مدل‌های استدلال مقرون‌به‌صرفه.",
"grok-4.20-0309-non-reasoning.description": "نسخه بدون استدلال برای کاربردهای ساده.",
"grok-4.20-0309-reasoning.description": "مدلی هوشمند و بسیار سریع که قبل از پاسخ استدلال می‌کند.",
"grok-4.20-beta-0309-non-reasoning.description": "یک نسخه غیرتفکری برای موارد استفاده ساده.",
"grok-4.20-beta-0309-reasoning.description": "مدلی هوشمند و فوق‌العاده سریع که قبل از پاسخ‌دهی استدلال می‌کند.",
"grok-4.20-multi-agent-0309.description": "مجموعه‌ای از ۴ یا ۱۶ ایجنت که در پژوهش عملکرد عالی دارد. در حال حاضر از ابزارهای سمت کاربر پشتیبانی نمی‌کند و تنها ابزارهای سمت سرور xAI (مانند X Search و Web Search) و ابزارهای MCP از راه دور را پشتیبانی می‌کند.",
"grok-4.3.description": "حقیقت‌جویانه‌ترین مدل زبان بزرگ در جهان",
"grok-4.description": "جدیدترین مدل پرچمدار Grok با عملکرد بی‌نظیر در زبان، ریاضیات و استدلال — یک مدل همه‌جانبه واقعی. در حال حاضر به grok-4-0709 اشاره دارد؛ به دلیل منابع محدود، قیمت آن موقتاً ۱۰٪ بالاتر از قیمت رسمی است و انتظار می‌رود به قیمت رسمی بازگردد.",
@@ -1220,8 +1214,6 @@
"qwq.description": "QwQ یک مدل استدلال در خانواده Qwen است. در مقایسه با مدل‌های تنظیم‌شده با دستورالعمل استاندارد، توانایی تفکر و استدلال آن عملکرد پایین‌دستی را به‌ویژه در مسائل دشوار به‌طور قابل توجهی بهبود می‌بخشد. QwQ-32B یک مدل استدلال میان‌رده است که با مدل‌های برتر مانند DeepSeek-R1 و o1-mini رقابت می‌کند.",
"qwq_32b.description": "مدل استدلال میان‌رده در خانواده Qwen. در مقایسه با مدل‌های تنظیم‌شده با دستورالعمل استاندارد، توانایی تفکر و استدلال QwQ عملکرد پایین‌دستی را به‌ویژه در مسائل دشوار به‌طور قابل توجهی بهبود می‌بخشد.",
"r1-1776.description": "R1-1776 نسخه پس‌آموزشی مدل DeepSeek R1 است که برای ارائه اطلاعات واقعی، بدون سانسور و بی‌طرف طراحی شده است.",
"seedance-1-5-pro-251215.description": "Seedance 1.5 Pro از ByteDance از متن به ویدئو، تصویر به ویدئو (فریم اول، فریم اول+آخر) و تولید صدا همگام با تصاویر پشتیبانی می‌کند.",
"seedream-5-0-260128.description": "ByteDance-Seedream-5.0-lite از BytePlus دارای تولید تقویت‌شده با بازیابی وب برای اطلاعات بلادرنگ، تفسیر پیشرفته دستورات پیچیده و بهبود سازگاری مرجع برای خلق بصری حرفه‌ای است.",
"solar-mini-ja.description": "Solar Mini (ژاپنی) نسخه‌ای از Solar Mini با تمرکز بر زبان ژاپنی است که در عین حال عملکرد قوی و کارآمدی در زبان‌های انگلیسی و کره‌ای حفظ می‌کند.",
"solar-mini.description": "Solar Mini یک مدل زبانی فشرده است که عملکردی بهتر از GPT-3.5 دارد و با پشتیبانی چندزبانه قوی از زبان‌های انگلیسی و کره‌ای، راه‌حلی کارآمد با حجم کم ارائه می‌دهد.",
"solar-pro.description": "Solar Pro یک مدل زبانی هوشمند از Upstage است که برای پیروی از دستورالعمل‌ها روی یک GPU طراحی شده و امتیاز IFEval بالای ۸۰ دارد. در حال حاضر از زبان انگلیسی پشتیبانی می‌کند؛ انتشار کامل آن برای نوامبر ۲۰۲۴ با پشتیبانی زبانی گسترده‌تر و زمینه طولانی‌تر برنامه‌ریزی شده است.",
@@ -1233,7 +1225,9 @@
"sophnet/deepseek-v3.2.description": "DeepSeek V3.2 مدلی است که بین کارایی محاسباتی بالا و عملکرد استدلال و عامل عالی تعادل برقرار می‌کند.",
"sora-2-pro.description": "Sora 2 Pro پیشرفته‌ترین مدل تولید رسانه‌ای ما است، که ویدئوهایی با صدای همگام‌شده تولید می‌کند. این مدل می‌تواند کلیپ‌های پویا و غنی از جزئیات را از زبان طبیعی یا تصاویر ایجاد کند.",
"sora-2.description": "Sora 2 مدل قدرتمند جدید تولید رسانه‌ای ما است، که ویدئوهایی با صدای همگام‌شده تولید می‌کند. این مدل می‌تواند کلیپ‌های پویا و غنی از جزئیات را از زبان طبیعی یا تصاویر ایجاد کند.",
"spark-x.description": ررسی قابلیت‌های X2: 1. معرفی تنظیم پویا حالت استدلال، کنترل شده از طریق فیلد `thinking`. 2. طول زمینه گسترش یافته: 64K توکن ورودی و 128K توکن خروجی. 3. از قابلیت Function Call پشتیبانی می‌کند.",
"spark-x1.5.description": ه‌روزرسانی‌های X1.5: (1) اضافه شدن حالت تفکر پویا که با فیلد `thinking` کنترل می‌شود؛ (2) طول زمینه بزرگ‌تر با 64K ورودی و 64K خروجی؛ (3) پشتیبانی از FunctionCall.",
"spark-x2-flash.description": "Spark X2-Flash از معماری MoE (ترکیب متخصصان) با 30 میلیارد پارامتر کل استفاده می‌کند و از پنجره زمینه‌ای تا 256K پشتیبانی می‌کند. این مدل بهبودهای قابل توجهی در قابلیت‌های عامل‌محور و کدنویسی ارائه می‌دهد و بر روی خوشه‌ای از پردازنده‌های Ascend 910B AI آموزش دیده است.",
"spark-x2.description": "مروری بر قابلیت‌های X2: 1. معرفی تنظیم پویا حالت استدلال که از طریق فیلد `thinking` کنترل می‌شود. 2. طول زمینه گسترش‌یافته: 64K توکن ورودی و 128K توکن خروجی. 3. پشتیبانی از قابلیت Function Call.",
"stable-diffusion-3-medium.description": "جدیدترین مدل تبدیل متن به تصویر از Stability AI. این نسخه کیفیت تصویر، درک متن و تنوع سبک را به‌طور قابل‌توجهی بهبود می‌بخشد، دستورات زبان طبیعی پیچیده را دقیق‌تر تفسیر کرده و تصاویر متنوع‌تری تولید می‌کند.",
"stable-diffusion-3.5-large-turbo.description": "Stable Diffusion 3.5 Large Turbo بر تولید تصاویر باکیفیت با رندر دقیق جزئیات و حفظ وفاداری صحنه تمرکز دارد.",
"stable-diffusion-xl-base-1.0.description": "یک مدل متن‌باز تبدیل متن به تصویر از Stability AI با قابلیت‌های خلاقانه پیشرو در صنعت. درک قوی از دستورالعمل‌ها دارد و از تعریف معکوس دستورات برای تولید دقیق پشتیبانی می‌کند.",
@@ -1355,7 +1349,6 @@
"x-ai/grok-4.1-fast.description": "Grok 4 Fast مدل با توان عملیاتی بالا و هزینه پایین از xAI است (با پشتیبانی از پنجره زمینه ۲ میلیون توکن) که برای موارد استفاده با هم‌زمانی بالا و زمینه‌های طولانی ایده‌آل است.",
"x-ai/grok-4.description": "Grok 4 مدل پرچم‌دار xAI با توانایی استدلال قوی و قابلیت چندوجهی است.",
"x-ai/grok-code-fast-1.description": "Grok Code Fast 1 مدل سریع کدنویسی از xAI است که خروجی‌هایی خوانا و مناسب برای مهندسی ارائه می‌دهد.",
"x1.description": "به‌روزرسانی‌های X1.5: (1) اضافه کردن حالت تفکر پویا که توسط فیلد `thinking` کنترل می‌شود؛ (2) طول زمینه بزرگ‌تر با 64K ورودی و 64K خروجی؛ (3) از FunctionCall پشتیبانی می‌کند.",
"xai/grok-2-vision.description": "Grok 2 Vision در وظایف بصری عملکردی عالی دارد و در استدلال ریاضی تصویری (MathVista) و پرسش‌وپاسخ اسناد (DocVQA) به سطح SOTA می‌رسد. این مدل اسناد، نمودارها، گراف‌ها، اسکرین‌شات‌ها و عکس‌ها را پردازش می‌کند.",
"xai/grok-2.description": "Grok 2 یک مدل پیشرفته با استدلال پیشرفته، چت قوی، کدنویسی و عملکرد استدلالی عالی است که در رتبه‌بندی LMSYS بالاتر از Claude 3.5 Sonnet و GPT-4 Turbo قرار دارد.",
"xai/grok-3-fast.description": "مدل پرچم‌دار xAI در کاربردهای سازمانی مانند استخراج داده، کدنویسی و خلاصه‌سازی برتری دارد و دانش عمیقی در حوزه‌های مالی، سلامت، حقوق و علوم دارد. نسخه سریع آن بر زیرساخت سریع‌تری اجرا می‌شود و پاسخ‌های بسیار سریع‌تری با هزینه بیشتر به ازای هر توکن ارائه می‌دهد.",
+21 -21
View File
@@ -69,9 +69,22 @@
"builtins.lobe-agent-management.render.installPlugin.plugin": "افزونه",
"builtins.lobe-agent-management.render.installPlugin.success": "با موفقیت نصب شد",
"builtins.lobe-agent-management.title": "مدیریت نمایندگان",
"builtins.lobe-agent-marketplace.apiName.showAgentMarketplace": "بازارچه نماینده را باز کنید",
"builtins.lobe-agent-marketplace.apiName.submitAgentPick": "انتخاب‌های نماینده را ارسال کنید",
"builtins.lobe-agent-marketplace.title": "بازارچه نماینده",
"builtins.lobe-agent.apiName.callSubAgent": "تماس با زیرعامل",
"builtins.lobe-agent.apiName.callSubAgent.completed": "زیرعامل ارسال شد: ",
"builtins.lobe-agent.apiName.callSubAgent.loading": "در حال ارسال زیرعامل: ",
"builtins.lobe-agent.apiName.callSubAgents": "تماس با زیرعامل‌ها",
"builtins.lobe-agent.apiName.clearTodos": "پاک کردن وظایف",
"builtins.lobe-agent.apiName.clearTodos.modeAll": "همه",
"builtins.lobe-agent.apiName.clearTodos.modeCompleted": "تکمیل‌شده",
"builtins.lobe-agent.apiName.clearTodos.result": "پاک کردن وظایف <mode>{{mode}}</mode>",
"builtins.lobe-agent.apiName.createPlan": "ایجاد برنامه",
"builtins.lobe-agent.apiName.createPlan.result": "ایجاد برنامه: <goal>{{goal}}</goal>",
"builtins.lobe-agent.apiName.createTodos": "ایجاد وظایف",
"builtins.lobe-agent.apiName.updatePlan": "به‌روزرسانی برنامه",
"builtins.lobe-agent.apiName.updatePlan.completed": "تکمیل شد",
"builtins.lobe-agent.apiName.updatePlan.modified": "ویرایش شد",
"builtins.lobe-agent.apiName.updateTodos": "به‌روزرسانی وظایف",
"builtins.lobe-agent.title": "عامل لوب",
"builtins.lobe-claude-code.agent.instruction": "دستورالعمل",
"builtins.lobe-claude-code.agent.result": "نتیجه",
"builtins.lobe-claude-code.todoWrite.allDone": "همه کارها انجام شدند",
@@ -139,24 +152,6 @@
"builtins.lobe-group-management.inspector.executeAgentTasks.title": "اختصاص وظایف به:",
"builtins.lobe-group-management.inspector.speak.title": "عامل مشخص صحبت می‌کند:",
"builtins.lobe-group-management.title": "هماهنگ‌کننده گروه",
"builtins.lobe-gtd.apiName.clearTodos": "پاک‌سازی کارها",
"builtins.lobe-gtd.apiName.clearTodos.modeAll": "همه",
"builtins.lobe-gtd.apiName.clearTodos.modeCompleted": "تکمیل‌شده",
"builtins.lobe-gtd.apiName.clearTodos.result": "پاک‌سازی کارهای <mode>{{mode}}</mode>",
"builtins.lobe-gtd.apiName.completeTodos": "تکمیل کارها",
"builtins.lobe-gtd.apiName.createPlan": "ایجاد برنامه",
"builtins.lobe-gtd.apiName.createPlan.result": "ایجاد برنامه: <goal>{{goal}}</goal>",
"builtins.lobe-gtd.apiName.createTodos": "ایجاد کارها",
"builtins.lobe-gtd.apiName.execTask": "اجرای وظیفه",
"builtins.lobe-gtd.apiName.execTask.completed": "وظیفه ایجاد شد: ",
"builtins.lobe-gtd.apiName.execTask.loading": "در حال ایجاد وظیفه: ",
"builtins.lobe-gtd.apiName.execTasks": "اجرای وظایف",
"builtins.lobe-gtd.apiName.removeTodos": "حذف کارها",
"builtins.lobe-gtd.apiName.updatePlan": "به‌روزرسانی برنامه",
"builtins.lobe-gtd.apiName.updatePlan.completed": "تکمیل‌شده",
"builtins.lobe-gtd.apiName.updatePlan.modified": "ویرایش‌شده",
"builtins.lobe-gtd.apiName.updateTodos": "به‌روزرسانی کارها",
"builtins.lobe-gtd.title": "ابزارهای وظیفه",
"builtins.lobe-knowledge-base.apiName.readKnowledge": "خواندن محتوای کتابخانه",
"builtins.lobe-knowledge-base.apiName.searchKnowledgeBase": "جستجوی کتابخانه",
"builtins.lobe-knowledge-base.inspector.andMoreFiles": "و {{count}} مورد دیگر",
@@ -317,6 +312,8 @@
"builtins.lobe-web-onboarding.apiName.finishOnboarding": "پایان فرآیند آشنایی",
"builtins.lobe-web-onboarding.apiName.readDocument": "خواندن سند",
"builtins.lobe-web-onboarding.apiName.saveUserQuestion": "ذخیره سوال کاربر",
"builtins.lobe-web-onboarding.apiName.showAgentMarketplace": "تشکیل تیم عامل",
"builtins.lobe-web-onboarding.apiName.submitAgentPick": "ارسال انتخاب‌های عامل",
"builtins.lobe-web-onboarding.apiName.updateDocument": "به‌روزرسانی سند",
"builtins.lobe-web-onboarding.apiName.writeDocument": "نوشتن سند",
"builtins.lobe-web-onboarding.docType.persona": "پرسونای کاربر",
@@ -327,6 +324,9 @@
"builtins.lobe-web-onboarding.inspector.hunkCount_other": "{{count}} تغییر",
"builtins.lobe-web-onboarding.inspector.interests_one": "{{count}} علاقه‌مندی",
"builtins.lobe-web-onboarding.inspector.interests_other": "{{count}} علاقه‌مندی",
"builtins.lobe-web-onboarding.render.agent": "عامل",
"builtins.lobe-web-onboarding.render.fullName": "نام کامل",
"builtins.lobe-web-onboarding.render.interests": "علاقه‌مندی‌ها",
"builtins.lobe-web-onboarding.title": "آشنایی کاربر",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.delete": "حذف",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.deleteLines": "حذف خطوط",
-1
View File
@@ -33,7 +33,6 @@
"jina.description": "Jina AI که در سال 2020 تأسیس شد، یک شرکت پیشرو در زمینه جستجوی هوش مصنوعی است. پشته جستجوی آن شامل مدل‌های برداری، رتبه‌بندها و مدل‌های زبانی کوچک برای ساخت اپلیکیشن‌های جستجوی مولد و چندوجهی با کیفیت بالا است.",
"kimicodingplan.description": "Kimi Code از Moonshot AI دسترسی به مدل‌های Kimi شامل K2.5 را برای وظایف کدنویسی فراهم می‌کند.",
"lmstudio.description": "LM Studio یک اپلیکیشن دسکتاپ برای توسعه و آزمایش مدل‌های زبانی بزرگ روی رایانه شخصی شماست.",
"lobehub.description": "LobeHub Cloud از APIهای رسمی برای دسترسی به مدل‌های هوش مصنوعی استفاده می‌کند و مصرف را با اعتباراتی که به توکن‌های مدل مرتبط هستند، اندازه‌گیری می‌کند.",
"longcat.description": "لانگ‌کت مجموعه‌ای از مدل‌های بزرگ هوش مصنوعی تولیدی است که به‌طور مستقل توسط میتوآن توسعه داده شده است. این مدل‌ها برای افزایش بهره‌وری داخلی شرکت و امکان‌پذیر کردن کاربردهای نوآورانه از طریق معماری محاسباتی کارآمد و قابلیت‌های چندوجهی قدرتمند طراحی شده‌اند.",
"minimax.description": "MiniMax که در سال 2021 تأسیس شد، هوش مصنوعی چندمنظوره با مدل‌های پایه چندوجهی از جمله مدل‌های متنی با پارامترهای تریلیونی، مدل‌های گفتاری و تصویری توسعه می‌دهد و اپ‌هایی مانند Hailuo AI را ارائه می‌کند.",
"minimaxcodingplan.description": "طرح توکن MiniMax دسترسی به مدل‌های MiniMax شامل M2.7 را برای وظایف کدنویسی از طریق اشتراک با هزینه ثابت فراهم می‌کند.",
-2
View File
@@ -913,8 +913,6 @@
"tools.builtins.lobe-agent-documents.title": "اسناد",
"tools.builtins.lobe-agent-management.description": "ایجاد، مدیریت و هماهنگ‌سازی عامل‌های هوش مصنوعی",
"tools.builtins.lobe-agent-management.title": "مدیریت عامل",
"tools.builtins.lobe-agent-marketplace.description": "به کاربران کارت بازارچه نماینده منتخب را نشان دهید و ثبت کنید که کدام الگوها را انتخاب می‌کنند.",
"tools.builtins.lobe-agent-marketplace.title": "بازارچه نماینده",
"tools.builtins.lobe-artifacts.description": "تولید و پیش‌نمایش زنده اجزای تعاملی رابط کاربری، نمودارها، گرافیک‌های SVG و برنامه‌های وب. ایجاد محتوای بصری غنی که کاربران بتوانند مستقیماً با آن تعامل داشته باشند.",
"tools.builtins.lobe-artifacts.readme": "اجزای رابط کاربری تعاملی، نمودارها، گرافیک‌های SVG و برنامه‌های وب را تولید کرده و به‌صورت زنده پیش‌نمایش دهید. محتوای بصری غنی ایجاد کنید که کاربران بتوانند مستقیماً با آن تعامل داشته باشند.",
"tools.builtins.lobe-artifacts.title": "آرتیفکت‌ها",
+45 -45
View File
@@ -56,51 +56,51 @@
"dalle.generating": "در حال تولید...",
"dalle.images": "تصاویر:",
"dalle.prompt": "دستور",
"lobe-gtd.actions.add": "افزودن",
"lobe-gtd.actions.clearCompleted": "پاک‌سازی موارد انجام‌شده",
"lobe-gtd.actions.placeholder": "یک مورد برای انجام وارد کنید...",
"lobe-gtd.addTodo.placeholder": "افزودن یک مورد برای انجام...",
"lobe-gtd.clearTodos.cleared": "{{count}} مورد پاک شد",
"lobe-gtd.clearTodos.clearedCompleted": "{{count}} مورد انجام‌شده پاک شد",
"lobe-gtd.clearTodos.clearedCompleted_one": "{{count}} مورد انجام‌شده پاک شد",
"lobe-gtd.clearTodos.clearedCompleted_other": "{{count}} مورد انجام‌شده پاک شد",
"lobe-gtd.clearTodos.cleared_one": "{{count}} مورد پاک شد",
"lobe-gtd.clearTodos.cleared_other": "{{count}} مورد پاک شد",
"lobe-gtd.clearTodos.header": "پاک‌سازی موارد انجام",
"lobe-gtd.clearTodos.label": "انتخاب موارد برای پاک‌سازی:",
"lobe-gtd.clearTodos.noItems": "موردی برای پاک‌سازی وجود ندارد",
"lobe-gtd.clearTodos.option.all": "پاک‌سازی همه موارد (شامل موارد در انتظار)",
"lobe-gtd.clearTodos.option.completed": "فقط پاک‌سازی موارد انجام‌شده",
"lobe-gtd.clearTodos.remaining": "{{count}} مورد باقیمانده",
"lobe-gtd.clearTodos.remaining_one": "{{count}} مورد باقیمانده",
"lobe-gtd.clearTodos.remaining_other": "{{count}} مورد باقیمانده",
"lobe-gtd.completeTodos.completed": "{{count}} مورد انجام شد",
"lobe-gtd.completeTodos.completed_one": "{{count}} مورد انجام شد",
"lobe-gtd.completeTodos.completed_other": "{{count}} مورد انجام شد",
"lobe-gtd.createPlan.context.label": "زمینه (اختیاری)",
"lobe-gtd.createPlan.context.placeholder": "پیش‌زمینه، محدودیت‌ها، ملاحظات...",
"lobe-gtd.createPlan.description.label": "توضیحات",
"lobe-gtd.createPlan.description.placeholder": "خلاصه‌ای از برنامه",
"lobe-gtd.createPlan.goal.label": "هدف",
"lobe-gtd.createPlan.goal.placeholder": "می‌خواهید به چه چیزی برسید؟",
"lobe-gtd.createTodos.created": "{{count}} مورد برای انجام ایجاد شد",
"lobe-gtd.createTodos.created_one": "{{count}} مورد برای انجام ایجاد شد",
"lobe-gtd.createTodos.created_other": "{{count}} مورد برای انجام ایجاد شد",
"lobe-gtd.createTodos.total": "مجموع: {{count}} مورد",
"lobe-gtd.createTodos.total_one": "مجموع: {{count}} مورد",
"lobe-gtd.createTodos.total_other": "مجموع: {{count}} مورد",
"lobe-gtd.removeTodos.removed": "{{count}} مورد حذف شد",
"lobe-gtd.removeTodos.removed_one": "{{count}} مورد حذف شد",
"lobe-gtd.removeTodos.removed_other": "{{count}} مورد حذف شد",
"lobe-gtd.status.done": "{{count}} انجام‌شده",
"lobe-gtd.status.pending": "{{count}} در انتظار",
"lobe-gtd.todoItem.placeholder": "موردی برای انجام وارد کنید...",
"lobe-gtd.todoList.empty": "لیست انجام خالی است",
"lobe-gtd.todoList.items": "{{count}} مورد",
"lobe-gtd.todoList.items_one": "{{count}} مورد",
"lobe-gtd.todoList.items_other": "{{count}} مورد",
"lobe-gtd.todoList.title": "لیست انجام",
"lobe-gtd.updateTodos.updated": "لیست انجام به‌روزرسانی شد",
"lobe-agent.actions.add": "افزودن",
"lobe-agent.actions.clearCompleted": "پاک کردن موارد تکمیل‌شده",
"lobe-agent.actions.placeholder": "یک مورد برای انجام وارد کنید...",
"lobe-agent.addTodo.placeholder": "یک مورد برای انجام اضافه کنید...",
"lobe-agent.clearTodos.cleared": "{{count}} مورد پاک شد",
"lobe-agent.clearTodos.clearedCompleted": "{{count}} مورد تکمیل‌شده پاک شد",
"lobe-agent.clearTodos.clearedCompleted_one": "{{count}} مورد تکمیل‌شده پاک شد",
"lobe-agent.clearTodos.clearedCompleted_other": "{{count}} مورد تکمیل‌شده پاک شد",
"lobe-agent.clearTodos.cleared_one": "{{count}} مورد پاک شد",
"lobe-agent.clearTodos.cleared_other": "{{count}} مورد پاک شد",
"lobe-agent.clearTodos.header": "پاک کردن موارد انجام",
"lobe-agent.clearTodos.label": "مواردی که باید پاک شوند را انتخاب کنید:",
"lobe-agent.clearTodos.noItems": "موردی برای پاک کردن وجود ندارد",
"lobe-agent.clearTodos.option.all": "پاک کردن همه موارد (شامل موارد در انتظار)",
"lobe-agent.clearTodos.option.completed": "فقط موارد تکمیل‌شده را پاک کن",
"lobe-agent.clearTodos.remaining": "{{count}} مورد باقی مانده",
"lobe-agent.clearTodos.remaining_one": "{{count}} مورد باقی مانده",
"lobe-agent.clearTodos.remaining_other": "{{count}} مورد باقی مانده",
"lobe-agent.completeTodos.completed": "{{count}} مورد تکمیل شد",
"lobe-agent.completeTodos.completed_one": "{{count}} مورد تکمیل شد",
"lobe-agent.completeTodos.completed_other": "{{count}} مورد تکمیل شد",
"lobe-agent.createPlan.context.label": "زمینه (اختیاری)",
"lobe-agent.createPlan.context.placeholder": "پیش‌زمینه، محدودیت‌ها، ملاحظات...",
"lobe-agent.createPlan.description.label": "توضیحات",
"lobe-agent.createPlan.description.placeholder": "خلاصه‌ای کوتاه از برنامه",
"lobe-agent.createPlan.goal.label": "هدف",
"lobe-agent.createPlan.goal.placeholder": "چه چیزی می‌خواهید به دست آورید؟",
"lobe-agent.createTodos.created": "{{count}} مورد برای انجام ایجاد شد",
"lobe-agent.createTodos.created_one": "{{count}} مورد برای انجام ایجاد شد",
"lobe-agent.createTodos.created_other": "{{count}} مورد برای انجام ایجاد شد",
"lobe-agent.createTodos.total": "مجموع: {{count}} مورد",
"lobe-agent.createTodos.total_one": "مجموع: {{count}} مورد",
"lobe-agent.createTodos.total_other": "مجموع: {{count}} مورد",
"lobe-agent.removeTodos.removed": "{{count}} مورد حذف شد",
"lobe-agent.removeTodos.removed_one": "{{count}} مورد حذف شد",
"lobe-agent.removeTodos.removed_other": "{{count}} مورد حذف شد",
"lobe-agent.status.done": "{{count}} تکمیل‌شده",
"lobe-agent.status.pending": "{{count}} در انتظار",
"lobe-agent.todoItem.placeholder": "موردی برای انجام وارد کنید...",
"lobe-agent.todoList.empty": "لیست انجام خالی است",
"lobe-agent.todoList.items": "{{count}} مورد",
"lobe-agent.todoList.items_one": "{{count}} مورد",
"lobe-agent.todoList.items_other": "{{count}} مورد",
"lobe-agent.todoList.title": "لیست انجام",
"lobe-agent.updateTodos.updated": "لیست انجام به‌روزرسانی شد",
"lobe-knowledge-base.readKnowledge.meta.chars": "تعداد کاراکترها",
"lobe-knowledge-base.readKnowledge.meta.lines": "تعداد خطوط",
"localFiles.editFile.newString": "جایگزین با",
+4
View File
@@ -115,6 +115,10 @@
"channel.line.fetchBotInfoMissingToken": "Saisissez d'abord le jeton d'accès au canal, puis cliquez sur \"Récupérer depuis LINE\".",
"channel.line.fetchBotInfoSuccess": "ID utilisateur de destination récupéré",
"channel.line.webhookManualSetup": "LINE n'autorise pas l'enregistrement programmatique des webhooks. Copiez cette URL dans la console des développeurs LINE (API de messagerie → URL du webhook), cliquez sur \"Vérifier\", et activez \"Utiliser le webhook\".",
"channel.messengerPromo.action": "Essayer Messenger",
"channel.messengerPromo.desc": "Pas de configuration de bot. Discutez avec LobeHub sur Slack, Discord, Telegram.",
"channel.messengerPromo.dismiss": "Ignorer",
"channel.messengerPromo.title": "Passez l'installation",
"channel.openPlatform": "Plateforme ouverte",
"channel.platforms": "Plateformes",
"channel.publicKey": "Clé publique",
+4 -3
View File
@@ -314,7 +314,7 @@
"openInNewWindow": "Ouvrir dans une nouvelle fenêtre",
"operation.contextCompression": "Contexte trop long, compression de l'historique...",
"operation.execAgentRuntime": "Préparation de la réponse",
"operation.execClientTask": "Exécution de la tâche",
"operation.execClientSubAgent": "Exécution du sous-agent",
"operation.execHeterogeneousAgent": "{{name}} est en cours dexécution",
"operation.execServerAgentRuntime": "En cours… Vous pouvez changer de tâche ou fermer la page — la tâche continuera.",
"operation.heterogeneousAgentFallback": "Agent externe",
@@ -567,6 +567,7 @@
"taskList.contextMenu.copyLink": "Copier le lien",
"taskList.contextMenu.copyLinkSuccess": "Lien copié",
"taskList.contextMenu.priority": "Priorité",
"taskList.contextMenu.runNow": "Exécuter maintenant",
"taskList.contextMenu.status": "Statut",
"taskList.empty": "Aucune tâche pour le moment",
"taskList.emptyHero.greeting": "Que devons-nous aborder aujourd'hui ?",
@@ -771,6 +772,8 @@
"workflow.toolDisplayName.addPreferenceMemory": "Mémoire enregistrée",
"workflow.toolDisplayName.calculate": "Calculé",
"workflow.toolDisplayName.callAgent": "Agent appelé",
"workflow.toolDisplayName.callSubAgent": "Sous-agent dispatché",
"workflow.toolDisplayName.callSubAgents": "Sous-agents dispatchés",
"workflow.toolDisplayName.clearTodos": "Tâches effacées",
"workflow.toolDisplayName.copyDocument": "Document copié",
"workflow.toolDisplayName.crawlMultiPages": "Pages explorées",
@@ -785,8 +788,6 @@
"workflow.toolDisplayName.editTitle": "Titre modifié",
"workflow.toolDisplayName.evaluate": "Expression évaluée",
"workflow.toolDisplayName.execScript": "Script exécuté",
"workflow.toolDisplayName.execTask": "A exécuté une tâche",
"workflow.toolDisplayName.execTasks": "Tâches exécutées",
"workflow.toolDisplayName.execute": "Calcul exécuté",
"workflow.toolDisplayName.executeCode": "Code exécuté",
"workflow.toolDisplayName.finishOnboarding": "Onboarding terminé",
+2
View File
@@ -349,6 +349,8 @@
"loading": "Chargement...",
"mail.business": "Coopération commerciale",
"mail.support": "Assistance par e-mail",
"messengerBanner.dismiss": "Fermer",
"messengerBanner.title": "Discutez avec Lobe AI sur vos applications de messagerie préférées",
"more": "Plus",
"navPanel.agent": "Agent",
"navPanel.customizeSidebar": "Personnaliser la barre latérale",
-1
View File
@@ -35,7 +35,6 @@
"messenger.linkModal.notConfigured": "Cette connexion n'est pas disponible pour le moment. Veuillez réessayer plus tard.",
"messenger.linkModal.openCta": "Ouvrir dans {{platform}}",
"messenger.linkModal.scanHint": "Ou scannez avec votre téléphone pour ouvrir {{platform}}.",
"messenger.linkModal.title": "Connecter Messenger",
"messenger.list.discord.description": "Discutez avec vos agents LobeHub depuis n'importe quel serveur Discord via un message direct avec le bot LobeHub.",
"messenger.list.slack.description": "Discutez avec vos agents LobeHub depuis n'importe quel espace de travail Slack via un message direct ou @LobeHub.",
"messenger.list.telegram.description": "Discutez avec vos agents LobeHub sur Telegram et choisissez lequel répond de n'importe où.",
+12 -19
View File
@@ -106,7 +106,6 @@
"MiniMax-Hailuo-2.3.description": "Nouveau modèle de génération vidéo avec des améliorations complètes dans les mouvements corporels, le réalisme physique et le suivi des instructions.",
"MiniMax-M1.description": "Un nouveau modèle de raisonnement interne avec 80 000 chaînes de pensée et 1 million dentrées, offrant des performances comparables aux meilleurs modèles mondiaux.",
"MiniMax-M2-Stable.description": "Conçu pour un codage efficace et des flux de travail dagents, avec une plus grande simultanéité pour un usage commercial.",
"MiniMax-M2.1-Lightning.description": "Capacités de programmation multilingues puissantes avec une inférence plus rapide et plus efficace.",
"MiniMax-M2.1-highspeed.description": "Des capacités de programmation multilingues puissantes, offrant une expérience de programmation entièrement améliorée. Plus rapide et plus efficace.",
"MiniMax-M2.1.description": "MiniMax-M2.1 est un modèle phare open source de MiniMax, conçu pour résoudre des tâches complexes du monde réel. Ses principaux atouts résident dans ses capacités de programmation multilingue et sa faculté à résoudre des problèmes complexes en tant qu'agent.",
"MiniMax-M2.5-highspeed.description": "MiniMax M2.5 Highspeed : Même performance que M2.5 avec une inférence plus rapide.",
@@ -315,11 +314,11 @@
"claude-3-haiku-20240307.description": "Claude 3 Haiku est le modèle le plus rapide et le plus compact dAnthropic, conçu pour des réponses quasi instantanées avec des performances rapides et précises.",
"claude-3-opus-20240229.description": "Claude 3 Opus est le modèle le plus puissant dAnthropic pour les tâches complexes, excellent en performance, intelligence, fluidité et compréhension.",
"claude-3-sonnet-20240229.description": "Claude 3 Sonnet équilibre intelligence et rapidité pour les charges de travail en entreprise, offrant une grande utilité à moindre coût et un déploiement fiable à grande échelle.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 est le modèle Haiku le plus rapide et le plus intelligent d'Anthropic, avec une vitesse fulgurante et une pensée étendue.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 est le modèle Haiku le plus rapide et le plus intelligent d'Anthropic, avec une vitesse fulgurante et un raisonnement étendu.",
"claude-haiku-4-5.description": "Claude Haiku 4.5 par Anthropic — modèle Haiku de nouvelle génération avec un raisonnement et une vision améliorés.",
"claude-haiku-4.5.description": "Claude Haiku 4.5 est le modèle Haiku le plus rapide et le plus intelligent dAnthropic, avec une vitesse fulgurante et un raisonnement étendu.",
"claude-opus-4-1-20250805-thinking.description": "Claude Opus 4.1 Thinking est une variante avancée capable de révéler son processus de raisonnement.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 est le modèle le plus récent et le plus performant d'Anthropic pour les tâches hautement complexes, excelle en performance, intelligence, fluidité et compréhension.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 est le dernier modèle d'Anthropic, le plus performant pour les tâches hautement complexes, excelle en performance, intelligence, fluidité et compréhension.",
"claude-opus-4-1.description": "Claude Opus 4.1 par Anthropic — modèle de raisonnement premium avec des capacités d'analyse approfondie.",
"claude-opus-4-20250514.description": "Claude Opus 4 est le modèle le plus puissant d'Anthropic pour les tâches hautement complexes, excelle en performance, intelligence, fluidité et compréhension.",
"claude-opus-4-5-20251101.description": "Claude Opus 4.5 est le modèle phare dAnthropic, combinant intelligence exceptionnelle et performance évolutive, idéal pour les tâches complexes nécessitant des réponses et un raisonnement de très haute qualité.",
@@ -330,7 +329,7 @@
"claude-opus-4.6-fast.description": "Claude Opus 4.6 est le modèle le plus intelligent dAnthropic pour la création dagents et le codage.",
"claude-opus-4.6.description": "Claude Opus 4.6 est le modèle le plus intelligent dAnthropic pour la création dagents et le codage.",
"claude-sonnet-4-20250514-thinking.description": "Claude Sonnet 4 Thinking peut produire des réponses quasi instantanées ou une réflexion détaillée étape par étape avec un processus visible.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 est le modèle le plus intelligent d'Anthropic à ce jour, offrant des réponses quasi-instantanées ou une pensée détaillée étape par étape avec un contrôle précis pour les utilisateurs d'API.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 peut produire des réponses quasi-instantanées ou un raisonnement détaillé étape par étape avec un processus visible.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5 est le modèle le plus intelligent d'Anthropic à ce jour.",
"claude-sonnet-4-5.description": "Claude Sonnet 4.5 par Anthropic — Sonnet amélioré avec des performances de codage accrues.",
"claude-sonnet-4-6.description": "Claude Sonnet 4.6 par Anthropic — dernier modèle Sonnet avec un codage supérieur et une utilisation d'outils avancée.",
@@ -404,7 +403,7 @@
"deepseek-ai/deepseek-llm-67b-chat.description": "DeepSeek LLM Chat (67B) est un modèle innovant offrant une compréhension linguistique approfondie et une interaction fluide.",
"deepseek-ai/deepseek-v3.1-terminus.description": "DeepSeek V3.1 est un modèle de raisonnement nouvelle génération avec un raisonnement complexe renforcé et une chaîne de pensée pour les tâches danalyse approfondie.",
"deepseek-ai/deepseek-v3.2.description": "DeepSeek V3.2 est un modèle de raisonnement de nouvelle génération avec des capacités renforcées de raisonnement complexe et de chaîne de pensée.",
"deepseek-chat.description": "Alias de compatibilité pour le mode non-pensant de DeepSeek V4 Flash. Prévu pour être obsolète — utilisez DeepSeek V4 Flash à la place.",
"deepseek-chat.description": "Un nouveau modèle open-source combinant des capacités générales et de codage. Il préserve le dialogue général du modèle de chat et les solides compétences en codage du modèle de programmation, avec un meilleur alignement des préférences. DeepSeek-V2.5 améliore également l'écriture et le suivi des instructions.",
"deepseek-coder-33B-instruct.description": "DeepSeek Coder 33B est un modèle de langage pour le code entraîné sur 2T de tokens (87 % de code, 13 % de texte en chinois/anglais). Il introduit une fenêtre de contexte de 16K et des tâches de remplissage au milieu, offrant une complétion de code à l’échelle du projet et un remplissage de fragments.",
"deepseek-coder-v2.description": "DeepSeek Coder V2 est un modèle de code MoE open source performant sur les tâches de programmation, comparable à GPT-4 Turbo.",
"deepseek-coder-v2:236b.description": "DeepSeek Coder V2 est un modèle de code MoE open source performant sur les tâches de programmation, comparable à GPT-4 Turbo.",
@@ -426,7 +425,7 @@
"deepseek-r1-fast-online.description": "Version complète rapide de DeepSeek R1 avec recherche web en temps réel, combinant des capacités à l’échelle de 671B et des réponses plus rapides.",
"deepseek-r1-online.description": "Version complète de DeepSeek R1 avec 671B de paramètres et recherche web en temps réel, offrant une meilleure compréhension et génération.",
"deepseek-r1.description": "DeepSeek-R1 utilise des données de démarrage à froid avant lapprentissage par renforcement et affiche des performances comparables à OpenAI-o1 en mathématiques, codage et raisonnement.",
"deepseek-reasoner.description": "Alias de compatibilité pour le mode pensant de DeepSeek V4 Flash. Prévu pour être obsolète — utilisez DeepSeek V4 Flash à la place.",
"deepseek-reasoner.description": "Un modèle de raisonnement DeepSeek axé sur les tâches de raisonnement logique complexes.",
"deepseek-v2.description": "DeepSeek V2 est un modèle MoE efficace pour un traitement économique.",
"deepseek-v2:236b.description": "DeepSeek V2 236B est le modèle axé sur le code de DeepSeek avec une forte génération de code.",
"deepseek-v3-0324.description": "DeepSeek-V3-0324 est un modèle MoE de 671B paramètres avec des points forts en programmation, compréhension du contexte et traitement de longs textes.",
@@ -491,8 +490,6 @@
"doubao-seedream-4-0-250828.description": "Seedream 4.0 est un modèle de génération dimage de ByteDance Seed, prenant en charge les entrées texte et image avec une génération dimage de haute qualité et hautement contrôlable. Il génère des images à partir dinvites textuelles.",
"doubao-seedream-4-5-251128.description": "Seedream 4.5 est le dernier modèle d'image multimodal de ByteDance, intégrant des capacités de génération de texte en image, d'image en image et de génération d'images par lots, tout en incorporant des compétences en raisonnement et en bon sens. Par rapport à la version précédente 4.0, il offre une qualité de génération nettement améliorée, avec une meilleure cohérence d'édition et une fusion multi-images. Il permet un contrôle plus précis des détails visuels, produisant des textes et des visages plus petits de manière plus naturelle, et atteint une mise en page et des couleurs plus harmonieuses, améliorant l'esthétique globale.",
"doubao-seedream-5-0-260128.description": "Doubao-Seedream-5.0-lite est le dernier modèle de génération d'images de ByteDance. Pour la première fois, il intègre des capacités de recherche en ligne, lui permettant d'incorporer des informations web en temps réel et d'améliorer la pertinence des images générées. L'intelligence du modèle a également été améliorée, permettant une interprétation précise des instructions complexes et du contenu visuel. De plus, il offre une meilleure couverture des connaissances globales, une cohérence des références et une qualité de génération dans des scénarios professionnels, répondant mieux aux besoins de création visuelle au niveau des entreprises.",
"dreamina-seedance-2-0-260128.description": "Seedance 2.0 de ByteDance est le modèle de génération vidéo le plus puissant, prenant en charge la génération de vidéos de référence multimodales, l'édition vidéo, l'extension vidéo, le texte-à-vidéo et l'image-à-vidéo avec audio synchronisé.",
"dreamina-seedance-2-0-fast-260128.description": "Seedance 2.0 Fast de ByteDance offre les mêmes capacités que Seedance 2.0 avec des vitesses de génération plus rapides à un prix plus compétitif.",
"emohaa.description": "Emohaa est un modèle de santé mentale doté de compétences professionnelles en conseil pour aider les utilisateurs à comprendre leurs problèmes émotionnels.",
"ernie-4.5-0.3b.description": "ERNIE 4.5 0.3B est un modèle léger open source conçu pour un déploiement local et personnalisé.",
"ernie-4.5-8k-preview.description": "ERNIE 4.5 8K Preview est un modèle de prévisualisation avec contexte 8K pour l’évaluation dERNIE 4.5.",
@@ -517,8 +514,7 @@
"ernie-x1-turbo-32k.description": "ERNIE X1 Turbo 32K est un modèle de réflexion rapide avec un contexte de 32K pour le raisonnement complexe et les dialogues multi-tours.",
"ernie-x1.1-preview.description": "ERNIE X1.1 Preview est une préversion de modèle de réflexion pour l’évaluation et les tests.",
"ernie-x1.1.description": "ERNIE X1.1 est un modèle de réflexion en aperçu pour évaluation et test.",
"fal-ai/bytedance/seedream/v4.5.description": "Seedream 4.5, développé par l'équipe Seed de ByteDance, prend en charge l'édition et la composition multi-images. Il offre une meilleure cohérence des sujets, un suivi précis des instructions, une compréhension de la logique spatiale, une expression esthétique, une mise en page de posters et la conception de logos avec un rendu texte-image de haute précision.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0, développé par ByteDance Seed, prend en charge les entrées texte et image pour une génération d'images de haute qualité et hautement contrôlable à partir de prompts.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0 est un modèle de génération d'images de ByteDance Seed, prenant en charge les entrées texte et image avec une génération d'images hautement contrôlable et de haute qualité. Il génère des images à partir de descriptions textuelles.",
"fal-ai/flux-kontext/dev.description": "Modèle FLUX.1 axé sur l’édition dimages, prenant en charge les entrées texte et image.",
"fal-ai/flux-pro/kontext.description": "FLUX.1 Kontext [pro] accepte des textes et des images de référence en entrée, permettant des modifications locales ciblées et des transformations globales complexes de scènes.",
"fal-ai/flux/krea.description": "Flux Krea [dev] est un modèle de génération dimages avec une préférence esthétique pour des images plus réalistes et naturelles.",
@@ -526,8 +522,8 @@
"fal-ai/hunyuan-image/v3.description": "Un puissant modèle natif multimodal de génération dimages.",
"fal-ai/imagen4/preview.description": "Modèle de génération dimages de haute qualité développé par Google.",
"fal-ai/nano-banana.description": "Nano Banana est le modèle multimodal natif le plus récent, le plus rapide et le plus efficace de Google, permettant la génération et l’édition dimages via la conversation.",
"fal-ai/qwen-image-edit.description": "Un modèle d'édition d'image professionnel de l'équipe Qwen, prenant en charge les modifications sémantiques et d'apparence, l'édition précise de texte en chinois/anglais, le transfert de style, la rotation et plus encore.",
"fal-ai/qwen-image.description": "Un modèle puissant de génération d'images de l'équipe Qwen avec un rendu texte chinois robuste et des styles visuels variés.",
"fal-ai/qwen-image-edit.description": "Un modèle professionnel d'édition d'images de l'équipe Qwen qui prend en charge les modifications sémantiques et d'apparence, édite précisément le texte en chinois et en anglais, et permet des modifications de haute qualité telles que le transfert de style et la rotation d'objets.",
"fal-ai/qwen-image.description": "Un modèle puissant de génération d'images de l'équipe Qwen avec un rendu impressionnant du texte en chinois et des styles visuels variés.",
"flux-1-schnell.description": "Modèle texte-vers-image à 12 milliards de paramètres de Black Forest Labs utilisant la distillation par diffusion latente adversariale pour générer des images de haute qualité en 1 à 4 étapes. Il rivalise avec les alternatives propriétaires et est publié sous licence Apache-2.0 pour un usage personnel, de recherche et commercial.",
"flux-dev.description": "Modèle open source de génération dimages destiné à la R&D, optimisé efficacement pour la recherche dinnovation non commerciale.",
"flux-kontext-max.description": "Génération et édition dimages contextuelles de pointe, combinant texte et images pour des résultats précis et cohérents.",
@@ -569,7 +565,7 @@
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro) est le modèle de génération d'images de Google et prend également en charge le chat multimodal.",
"gemini-3-pro-preview.description": "Gemini 3 Pro est le modèle agent et de codage le plus puissant de Google, offrant des visuels enrichis et une interaction plus poussée grâce à un raisonnement de pointe.",
"gemini-3.1-flash-image-preview.description": "Gemini 3.1 Flash Image (Nano Banana 2) est le modèle de génération d'images natif le plus rapide de Google avec prise en charge de la réflexion, génération et édition d'images conversationnelles.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) offre une qualité d'image de niveau Pro à une vitesse Flash avec prise en charge du chat multimodal.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) est le modèle de génération d'images natif le plus rapide de Google avec prise en charge de la réflexion, génération et édition d'images conversationnelles.",
"gemini-3.1-flash-lite-preview.description": "Gemini 3.1 Flash-Lite Preview est le modèle multimodal le plus économique de Google, optimisé pour les tâches agentiques à haut volume, la traduction et le traitement des données.",
"gemini-3.1-flash-lite.description": "Gemini 3.1 Flash-Lite est le modèle multimodal le plus économique de Google, optimisé pour les tâches agentiques à haut volume, la traduction et le traitement des données.",
"gemini-3.1-pro-preview.description": "Gemini 3.1 Pro Preview améliore Gemini 3 Pro avec des capacités de raisonnement renforcées et ajoute un support de niveau de réflexion moyen.",
@@ -734,8 +730,6 @@
"grok-4-fast-reasoning.description": "Nous sommes ravis de présenter Grok 4 Fast, notre dernière avancée en matière de modèles de raisonnement économiques.",
"grok-4.20-0309-non-reasoning.description": "Une variante sans raisonnement pour des cas d'utilisation simples.",
"grok-4.20-0309-reasoning.description": "Modèle intelligent et ultra-rapide qui raisonne avant de répondre.",
"grok-4.20-beta-0309-non-reasoning.description": "Une variante non-pensante pour des cas d'utilisation simples.",
"grok-4.20-beta-0309-reasoning.description": "Modèle intelligent et ultra-rapide qui raisonne avant de répondre.",
"grok-4.20-multi-agent-0309.description": "Une équipe de 4 ou 16 agents, excelle dans les cas d'utilisation de recherche. Ne prend actuellement pas en charge les outils côté client. Prend uniquement en charge les outils côté serveur xAI (par exemple X Search, outils de recherche Web) et les outils MCP distants.",
"grok-4.3.description": "Le modèle de langage de grande taille le plus axé sur la vérité au monde",
"grok-4.description": "Dernier modèle phare Grok avec des performances inégalées en langage, mathématiques et raisonnement — un véritable polyvalent. Actuellement pointé vers grok-4-0709 ; en raison de ressources limitées, son prix est temporairement 10 % plus élevé que le tarif officiel et devrait revenir au prix officiel ultérieurement.",
@@ -1220,8 +1214,6 @@
"qwq.description": "QwQ est un modèle de raisonnement de la famille Qwen. Comparé aux modèles classiques ajustés par instruction, il apporte des capacités de réflexion et de raisonnement qui améliorent considérablement les performances en aval, notamment sur les problèmes complexes. QwQ-32B est un modèle de raisonnement de taille moyenne qui rivalise avec les meilleurs modèles comme DeepSeek-R1 et o1-mini.",
"qwq_32b.description": "Modèle de raisonnement de taille moyenne de la famille Qwen. Comparé aux modèles classiques ajustés par instruction, les capacités de réflexion et de raisonnement de QwQ améliorent considérablement les performances en aval, notamment sur les problèmes complexes.",
"r1-1776.description": "R1-1776 est une variante post-entraînée de DeepSeek R1 conçue pour fournir des informations factuelles non censurées et impartiales.",
"seedance-1-5-pro-251215.description": "Seedance 1.5 Pro de ByteDance prend en charge le texte-à-vidéo, l'image-à-vidéo (première image, première+dernière image) et la génération audio synchronisée avec les visuels.",
"seedream-5-0-260128.description": "ByteDance-Seedream-5.0-lite par BytePlus propose une génération augmentée par récupération web pour des informations en temps réel, une interprétation améliorée des prompts complexes et une meilleure cohérence des références pour la création visuelle professionnelle.",
"solar-mini-ja.description": "Solar Mini (Ja) étend Solar Mini avec un accent sur le japonais tout en maintenant des performances efficaces et solides en anglais et en coréen.",
"solar-mini.description": "Solar Mini est un modèle LLM compact surpassant GPT-3.5, avec de solides capacités multilingues en anglais et en coréen, offrant une solution efficace à faible empreinte.",
"solar-pro.description": "Solar Pro est un LLM intelligent développé par Upstage, axé sur le suivi d'instructions sur un seul GPU, avec des scores IFEval supérieurs à 80. Il prend actuellement en charge l'anglais ; la version complète est prévue pour novembre 2024 avec un support linguistique élargi et un contexte plus long.",
@@ -1233,7 +1225,9 @@
"sophnet/deepseek-v3.2.description": "DeepSeek V3.2 est un modèle qui équilibre une haute efficacité computationnelle avec d'excellentes performances de raisonnement et d'agent.",
"sora-2-pro.description": "Sora 2 Pro est notre modèle de génération multimédia le plus avancé, générant des vidéos avec audio synchronisé. Il peut créer des clips dynamiques et richement détaillés à partir de langage naturel ou d'images.",
"sora-2.description": "Sora 2 est notre nouveau modèle puissant de génération multimédia, générant des vidéos avec audio synchronisé. Il peut créer des clips dynamiques et richement détaillés à partir de langage naturel ou d'images.",
"spark-x.description": "Aperçu des capacités X2 : 1. Introduit un ajustement dynamique du mode de raisonnement, contrôlé via le champ `thinking`. 2. Longueur de contexte étendue : 64K jetons d'entrée et 128K jetons de sortie. 3. Prend en charge la fonctionnalité Function Call.",
"spark-x1.5.description": "Mises à jour X1.5 : (1) ajoute un mode de réflexion dynamique contrôlé par le champ `thinking`; (2) longueur de contexte étendue avec 64K en entrée et 64K en sortie; (3) prend en charge FunctionCall.",
"spark-x2-flash.description": "Spark X2-Flash adopte une architecture MoE (Mixture of Experts) avec un total de 30 milliards de paramètres et prend en charge une fenêtre de contexte allant jusqu'à 256K. Il revendique des améliorations significatives des capacités agentiques et de codage, et a été entraîné sur un cluster de processeurs IA Ascend 910B.",
"spark-x2.description": "Aperçu des capacités X2 : 1. Introduit un ajustement dynamique du mode de raisonnement, contrôlé via le champ `thinking`. 2. Longueur de contexte étendue : 64K tokens en entrée et 128K tokens en sortie. 3. Prend en charge la fonctionnalité Function Call.",
"stable-diffusion-3-medium.description": "Le dernier modèle texte-vers-image de Stability AI. Cette version améliore considérablement la qualité des images, la compréhension du texte et la diversité des styles, interprétant plus précisément les requêtes en langage naturel complexes.",
"stable-diffusion-3.5-large-turbo.description": "Stable Diffusion 3.5 Large Turbo se concentre sur la génération dimages haute qualité avec un rendu précis des détails et une grande fidélité des scènes.",
"stable-diffusion-xl-base-1.0.description": "Un modèle texte-vers-image open source de Stability AI avec une génération d'images créative de pointe. Il comprend bien les instructions et prend en charge les définitions de requêtes inversées pour une génération précise.",
@@ -1355,7 +1349,6 @@
"x-ai/grok-4.1-fast.description": "Grok 4 Fast est le modèle à haut débit et faible coût de xAI (fenêtre de contexte de 2M), idéal pour les cas dusage à forte concurrence et à long contexte.",
"x-ai/grok-4.description": "Grok 4 est le modèle phare de xAI avec de solides capacités de raisonnement et multimodales.",
"x-ai/grok-code-fast-1.description": "Grok Code Fast 1 est le modèle rapide de xAI pour le code, avec une sortie lisible et adaptée aux ingénieurs.",
"x1.description": "Mises à jour X1.5 : (1) ajoute un mode de réflexion dynamique contrôlé par le champ `thinking` ; (2) longueur de contexte plus grande avec 64K en entrée et 64K en sortie ; (3) prend en charge FunctionCall.",
"xai/grok-2-vision.description": "Grok 2 Vision excelle dans les tâches visuelles, offrant des performances SOTA en raisonnement mathématique visuel (MathVista) et en questions-réponses sur documents (DocVQA). Il gère documents, graphiques, tableaux, captures d’écran et photos.",
"xai/grok-2.description": "Grok 2 est un modèle de pointe avec des performances de raisonnement, de discussion et de codage de haut niveau, surpassant Claude 3.5 Sonnet et GPT-4 Turbo sur LMSYS.",
"xai/grok-3-fast.description": "Le modèle phare de xAI excelle dans les cas dusage en entreprise comme lextraction de données, le codage et la synthèse, avec une expertise approfondie en finance, santé, droit et science. La variante rapide fonctionne sur une infrastructure plus rapide pour des réponses plus rapides à un coût par token plus élevé.",
+21 -21
View File
@@ -69,9 +69,22 @@
"builtins.lobe-agent-management.render.installPlugin.plugin": "Plugin",
"builtins.lobe-agent-management.render.installPlugin.success": "Installé avec succès",
"builtins.lobe-agent-management.title": "Gestionnaire d'agents",
"builtins.lobe-agent-marketplace.apiName.showAgentMarketplace": "Ouvrir le marché des agents",
"builtins.lobe-agent-marketplace.apiName.submitAgentPick": "Soumettre les choix d'agents",
"builtins.lobe-agent-marketplace.title": "Marché des Agents",
"builtins.lobe-agent.apiName.callSubAgent": "Appeler un sous-agent",
"builtins.lobe-agent.apiName.callSubAgent.completed": "Sous-agent envoyé : ",
"builtins.lobe-agent.apiName.callSubAgent.loading": "Envoi du sous-agent : ",
"builtins.lobe-agent.apiName.callSubAgents": "Appeler des sous-agents",
"builtins.lobe-agent.apiName.clearTodos": "Effacer les tâches",
"builtins.lobe-agent.apiName.clearTodos.modeAll": "toutes",
"builtins.lobe-agent.apiName.clearTodos.modeCompleted": "terminées",
"builtins.lobe-agent.apiName.clearTodos.result": "Effacer les tâches <mode>{{mode}}</mode>",
"builtins.lobe-agent.apiName.createPlan": "Créer un plan",
"builtins.lobe-agent.apiName.createPlan.result": "Créer un plan : <goal>{{goal}}</goal>",
"builtins.lobe-agent.apiName.createTodos": "Créer des tâches",
"builtins.lobe-agent.apiName.updatePlan": "Mettre à jour le plan",
"builtins.lobe-agent.apiName.updatePlan.completed": "Terminé",
"builtins.lobe-agent.apiName.updatePlan.modified": "Modifié",
"builtins.lobe-agent.apiName.updateTodos": "Mettre à jour les tâches",
"builtins.lobe-agent.title": "Agent Lobe",
"builtins.lobe-claude-code.agent.instruction": "Consigne",
"builtins.lobe-claude-code.agent.result": "Résultat",
"builtins.lobe-claude-code.todoWrite.allDone": "Toutes les tâches sont terminées",
@@ -139,24 +152,6 @@
"builtins.lobe-group-management.inspector.executeAgentTasks.title": "Attribution des tâches à :",
"builtins.lobe-group-management.inspector.speak.title": "L'agent désigné parle :",
"builtins.lobe-group-management.title": "Coordinateur de groupe",
"builtins.lobe-gtd.apiName.clearTodos": "Effacer les tâches",
"builtins.lobe-gtd.apiName.clearTodos.modeAll": "toutes",
"builtins.lobe-gtd.apiName.clearTodos.modeCompleted": "terminées",
"builtins.lobe-gtd.apiName.clearTodos.result": "Effacer les tâches <mode>{{mode}}</mode>",
"builtins.lobe-gtd.apiName.completeTodos": "Marquer les tâches comme terminées",
"builtins.lobe-gtd.apiName.createPlan": "Créer un plan",
"builtins.lobe-gtd.apiName.createPlan.result": "Plan créé : <goal>{{goal}}</goal>",
"builtins.lobe-gtd.apiName.createTodos": "Créer des tâches",
"builtins.lobe-gtd.apiName.execTask": "Exécuter la tâche",
"builtins.lobe-gtd.apiName.execTask.completed": "Tâche créée : ",
"builtins.lobe-gtd.apiName.execTask.loading": "Création de la tâche : ",
"builtins.lobe-gtd.apiName.execTasks": "Exécuter les tâches",
"builtins.lobe-gtd.apiName.removeTodos": "Supprimer les tâches",
"builtins.lobe-gtd.apiName.updatePlan": "Mettre à jour le plan",
"builtins.lobe-gtd.apiName.updatePlan.completed": "Terminé",
"builtins.lobe-gtd.apiName.updatePlan.modified": "Modifié",
"builtins.lobe-gtd.apiName.updateTodos": "Mettre à jour les tâches",
"builtins.lobe-gtd.title": "Outils de tâches",
"builtins.lobe-knowledge-base.apiName.readKnowledge": "Lire le contenu de la Bibliothèque",
"builtins.lobe-knowledge-base.apiName.searchKnowledgeBase": "Rechercher dans la Bibliothèque",
"builtins.lobe-knowledge-base.inspector.andMoreFiles": "et {{count}} de plus",
@@ -317,6 +312,8 @@
"builtins.lobe-web-onboarding.apiName.finishOnboarding": "Terminer l'intégration",
"builtins.lobe-web-onboarding.apiName.readDocument": "Lire le document",
"builtins.lobe-web-onboarding.apiName.saveUserQuestion": "Enregistrer la question de l'utilisateur",
"builtins.lobe-web-onboarding.apiName.showAgentMarketplace": "Assembler une équipe d'agents",
"builtins.lobe-web-onboarding.apiName.submitAgentPick": "Soumettre les choix d'agents",
"builtins.lobe-web-onboarding.apiName.updateDocument": "Mettre à jour le document",
"builtins.lobe-web-onboarding.apiName.writeDocument": "Rédiger le document",
"builtins.lobe-web-onboarding.docType.persona": "Persona utilisateur",
@@ -327,6 +324,9 @@
"builtins.lobe-web-onboarding.inspector.hunkCount_other": "{{count}} modifications",
"builtins.lobe-web-onboarding.inspector.interests_one": "{{count}} intérêt",
"builtins.lobe-web-onboarding.inspector.interests_other": "{{count}} intérêts",
"builtins.lobe-web-onboarding.render.agent": "Agent",
"builtins.lobe-web-onboarding.render.fullName": "Nom complet",
"builtins.lobe-web-onboarding.render.interests": "Centres d'intérêt",
"builtins.lobe-web-onboarding.title": "Intégration utilisateur",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.delete": "Supprimer",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.deleteLines": "Supprimer les lignes",
-1
View File
@@ -33,7 +33,6 @@
"jina.description": "Fondée en 2020, Jina AI est une entreprise leader en IA de recherche. Sa pile technologique comprend des modèles vectoriels, des rerankers et de petits modèles linguistiques pour créer des applications de recherche générative et multimodale fiables et de haute qualité.",
"kimicodingplan.description": "Kimi Code de Moonshot AI offre un accès aux modèles Kimi, y compris K2.5, pour des tâches de codage.",
"lmstudio.description": "LM Studio est une application de bureau pour développer et expérimenter avec des LLMs sur votre ordinateur.",
"lobehub.description": "LobeHub Cloud utilise des API officielles pour accéder aux modèles d'IA et mesure l'utilisation avec des Crédits liés aux jetons des modèles.",
"longcat.description": "LongCat est une série de grands modèles d'IA générative développés indépendamment par Meituan. Elle est conçue pour améliorer la productivité interne de l'entreprise et permettre des applications innovantes grâce à une architecture informatique efficace et de puissantes capacités multimodales.",
"minimax.description": "Fondée en 2021, MiniMax développe une IA généraliste avec des modèles fondamentaux multimodaux, incluant des modèles texte MoE à un billion de paramètres, des modèles vocaux et visuels, ainsi que des applications comme Hailuo AI.",
"minimaxcodingplan.description": "Le plan de jetons MiniMax offre un accès aux modèles MiniMax, y compris M2.7, pour des tâches de codage via un abonnement à tarif fixe.",
-2
View File
@@ -913,8 +913,6 @@
"tools.builtins.lobe-agent-documents.title": "Documents",
"tools.builtins.lobe-agent-management.description": "Créer, gérer et orchestrer des agents IA",
"tools.builtins.lobe-agent-management.title": "Gestion dAgents",
"tools.builtins.lobe-agent-marketplace.description": "Afficher aux utilisateurs une carte de marché d'agents sélectionnée et enregistrer les modèles qu'ils choisissent.",
"tools.builtins.lobe-agent-marketplace.title": "Marché des Agents",
"tools.builtins.lobe-artifacts.description": "Générez et prévisualisez en direct des composants d'interface interactifs, des visualisations de données, des graphiques, des illustrations SVG et des applications web. Créez du contenu visuel riche avec lequel les utilisateurs peuvent interagir directement.",
"tools.builtins.lobe-artifacts.readme": "Générez et prévisualisez en direct des composants d'interface utilisateur interactifs, des visualisations de données, des graphiques, des illustrations SVG et des applications web. Créez du contenu visuel riche avec lequel les utilisateurs peuvent interagir directement.",
"tools.builtins.lobe-artifacts.title": "Artefacts",
+45 -45
View File
@@ -56,51 +56,51 @@
"dalle.generating": "Génération en cours...",
"dalle.images": "Images :",
"dalle.prompt": "Invite",
"lobe-gtd.actions.add": "Ajouter",
"lobe-gtd.actions.clearCompleted": "Effacer les tâches terminées",
"lobe-gtd.actions.placeholder": "Saisir une tâche à faire...",
"lobe-gtd.addTodo.placeholder": "Ajouter une tâche à faire...",
"lobe-gtd.clearTodos.cleared": "{{count}} élément(s) effacé(s)",
"lobe-gtd.clearTodos.clearedCompleted": "{{count}} tâche(s) terminée(s) effacée(s)",
"lobe-gtd.clearTodos.clearedCompleted_one": "{{count}} tâche terminée effacée",
"lobe-gtd.clearTodos.clearedCompleted_other": "{{count}} tâches terminées effacées",
"lobe-gtd.clearTodos.cleared_one": "{{count}} élément effacé",
"lobe-gtd.clearTodos.cleared_other": "{{count}} éléments effacés",
"lobe-gtd.clearTodos.header": "Effacer les tâches à faire",
"lobe-gtd.clearTodos.label": "Choisissez ce que vous souhaitez effacer :",
"lobe-gtd.clearTodos.noItems": "Aucun élément à effacer",
"lobe-gtd.clearTodos.option.all": "Effacer tous les éléments (y compris ceux en attente)",
"lobe-gtd.clearTodos.option.completed": "Effacer uniquement les tâches terminées",
"lobe-gtd.clearTodos.remaining": "{{count}} élément(s) restant(s)",
"lobe-gtd.clearTodos.remaining_one": "{{count}} élément restant",
"lobe-gtd.clearTodos.remaining_other": "{{count}} éléments restants",
"lobe-gtd.completeTodos.completed": "{{count}} tâche(s) terminée(s)",
"lobe-gtd.completeTodos.completed_one": "{{count}} tâche terminée",
"lobe-gtd.completeTodos.completed_other": "{{count}} tâches terminées",
"lobe-gtd.createPlan.context.label": "Contexte (optionnel)",
"lobe-gtd.createPlan.context.placeholder": "Contexte, contraintes, considérations...",
"lobe-gtd.createPlan.description.label": "Description",
"lobe-gtd.createPlan.description.placeholder": "Résumé du plan",
"lobe-gtd.createPlan.goal.label": "Objectif",
"lobe-gtd.createPlan.goal.placeholder": "Quel est votre objectif ?",
"lobe-gtd.createTodos.created": "{{count}} tâche(s) à faire créée(s)",
"lobe-gtd.createTodos.created_one": "{{count}} tâche à faire créée",
"lobe-gtd.createTodos.created_other": "{{count}} tâches à faire créées",
"lobe-gtd.createTodos.total": "Total : {{count}} élément(s)",
"lobe-gtd.createTodos.total_one": "Total : {{count}} élément",
"lobe-gtd.createTodos.total_other": "Total : {{count}} éléments",
"lobe-gtd.removeTodos.removed": "{{count}} élément(s) supprimé(s)",
"lobe-gtd.removeTodos.removed_one": "{{count}} élément supprimé",
"lobe-gtd.removeTodos.removed_other": "{{count}} éléments supprimés",
"lobe-gtd.status.done": "{{count}} terminé(s)",
"lobe-gtd.status.pending": "{{count}} en attente",
"lobe-gtd.todoItem.placeholder": "Saisir une tâche à faire...",
"lobe-gtd.todoList.empty": "La liste de tâches est vide",
"lobe-gtd.todoList.items": "{{count}} élément(s)",
"lobe-gtd.todoList.items_one": "{{count}} élément",
"lobe-gtd.todoList.items_other": "{{count}} éléments",
"lobe-gtd.todoList.title": "Liste de tâches",
"lobe-gtd.updateTodos.updated": "Liste de tâches mise à jour",
"lobe-agent.actions.add": "Ajouter",
"lobe-agent.actions.clearCompleted": "Effacer les éléments terminés",
"lobe-agent.actions.placeholder": "Entrez un élément à faire...",
"lobe-agent.addTodo.placeholder": "Ajoutez un élément à faire...",
"lobe-agent.clearTodos.cleared": "{{count}} élément(s) effacé(s)",
"lobe-agent.clearTodos.clearedCompleted": "{{count}} élément(s) terminé(s) effacé(s)",
"lobe-agent.clearTodos.clearedCompleted_one": "{{count}} élément terminé effacé",
"lobe-agent.clearTodos.clearedCompleted_other": "{{count}} éléments terminés effacés",
"lobe-agent.clearTodos.cleared_one": "{{count}} élément effacé",
"lobe-agent.clearTodos.cleared_other": "{{count}} éléments effacés",
"lobe-agent.clearTodos.header": "Effacer les éléments à faire",
"lobe-agent.clearTodos.label": "Choisissez quoi effacer :",
"lobe-agent.clearTodos.noItems": "Aucun élément à effacer",
"lobe-agent.clearTodos.option.all": "Effacer tous les éléments (y compris en attente)",
"lobe-agent.clearTodos.option.completed": "Effacer uniquement les éléments terminés",
"lobe-agent.clearTodos.remaining": "{{count}} élément(s) restant(s)",
"lobe-agent.clearTodos.remaining_one": "{{count}} élément restant",
"lobe-agent.clearTodos.remaining_other": "{{count}} éléments restants",
"lobe-agent.completeTodos.completed": "{{count}} élément(s) terminé(s)",
"lobe-agent.completeTodos.completed_one": "{{count}} élément terminé",
"lobe-agent.completeTodos.completed_other": "{{count}} éléments terminés",
"lobe-agent.createPlan.context.label": "Contexte (facultatif)",
"lobe-agent.createPlan.context.placeholder": "Contexte, contraintes, considérations...",
"lobe-agent.createPlan.description.label": "Description",
"lobe-agent.createPlan.description.placeholder": "Résumé succinct du plan",
"lobe-agent.createPlan.goal.label": "Objectif",
"lobe-agent.createPlan.goal.placeholder": "Que voulez-vous accomplir ?",
"lobe-agent.createTodos.created": "{{count}} élément(s) à faire créé(s)",
"lobe-agent.createTodos.created_one": "{{count}} élément à faire créé",
"lobe-agent.createTodos.created_other": "{{count}} éléments à faire créés",
"lobe-agent.createTodos.total": "Total : {{count}} élément(s)",
"lobe-agent.createTodos.total_one": "Total : {{count}} élément",
"lobe-agent.createTodos.total_other": "Total : {{count}} éléments",
"lobe-agent.removeTodos.removed": "{{count}} élément(s) supprimé(s)",
"lobe-agent.removeTodos.removed_one": "{{count}} élément supprimé",
"lobe-agent.removeTodos.removed_other": "{{count}} éléments supprimés",
"lobe-agent.status.done": "{{count}} terminé(s)",
"lobe-agent.status.pending": "{{count}} en attente",
"lobe-agent.todoItem.placeholder": "Entrez un élément à faire...",
"lobe-agent.todoList.empty": "La liste des tâches est vide",
"lobe-agent.todoList.items": "{{count}} élément(s)",
"lobe-agent.todoList.items_one": "{{count}} élément",
"lobe-agent.todoList.items_other": "{{count}} éléments",
"lobe-agent.todoList.title": "Liste des tâches",
"lobe-agent.updateTodos.updated": "Liste des tâches mise à jour",
"lobe-knowledge-base.readKnowledge.meta.chars": "Nombre de caractères",
"lobe-knowledge-base.readKnowledge.meta.lines": "Nombre de lignes",
"localFiles.editFile.newString": "Remplacer par",
+4
View File
@@ -115,6 +115,10 @@
"channel.line.fetchBotInfoMissingToken": "Inserisci prima il Token di accesso al canale, quindi clicca su \"Recupera da LINE\".",
"channel.line.fetchBotInfoSuccess": "ID utente di destinazione recuperato",
"channel.line.webhookManualSetup": "LINE non consente la registrazione programmatica dei webhook. Copia questo URL nella Console degli sviluppatori LINE (API di messaggistica → URL del webhook), clicca su \"Verifica\" e abilita \"Usa webhook\".",
"channel.messengerPromo.action": "Prova Messenger",
"channel.messengerPromo.desc": "Nessuna configurazione del bot. Chatta con LobeHub su Slack, Discord, Telegram.",
"channel.messengerPromo.dismiss": "Ignora",
"channel.messengerPromo.title": "Salta la configurazione",
"channel.openPlatform": "Piattaforma aperta",
"channel.platforms": "Piattaforme",
"channel.publicKey": "Chiave Pubblica",
+4 -3
View File
@@ -314,7 +314,7 @@
"openInNewWindow": "Apri in una nuova finestra",
"operation.contextCompression": "Contesto troppo lungo, compressione della cronologia in corso...",
"operation.execAgentRuntime": "Preparazione della risposta",
"operation.execClientTask": "Esecuzione attività",
"operation.execClientSubAgent": "Esecuzione del sotto-agente",
"operation.execHeterogeneousAgent": "{{name}} è in esecuzione",
"operation.execServerAgentRuntime": "In esecuzione… Puoi cambiare attività o chiudere la pagina: l'attività continuerà.",
"operation.heterogeneousAgentFallback": "Agente esterno",
@@ -567,6 +567,7 @@
"taskList.contextMenu.copyLink": "Copia link",
"taskList.contextMenu.copyLinkSuccess": "Link copiato",
"taskList.contextMenu.priority": "Priorità",
"taskList.contextMenu.runNow": "Esegui ora",
"taskList.contextMenu.status": "Stato",
"taskList.empty": "Nessuna attività",
"taskList.emptyHero.greeting": "Cosa affrontiamo oggi?",
@@ -771,6 +772,8 @@
"workflow.toolDisplayName.addPreferenceMemory": "Memoria salvata",
"workflow.toolDisplayName.calculate": "Calcolato",
"workflow.toolDisplayName.callAgent": "Ha chiamato un agente",
"workflow.toolDisplayName.callSubAgent": "Sotto-agente inviato",
"workflow.toolDisplayName.callSubAgents": "Sotto-agenti inviati",
"workflow.toolDisplayName.clearTodos": "Attività cancellate",
"workflow.toolDisplayName.copyDocument": "Ha copiato un documento",
"workflow.toolDisplayName.crawlMultiPages": "Pagine sottoposte a scansione",
@@ -785,8 +788,6 @@
"workflow.toolDisplayName.editTitle": "Titolo modificato",
"workflow.toolDisplayName.evaluate": "Espressione valutata",
"workflow.toolDisplayName.execScript": "Ha eseguito uno script",
"workflow.toolDisplayName.execTask": "Ha eseguito un'attività",
"workflow.toolDisplayName.execTasks": "Attività eseguite",
"workflow.toolDisplayName.execute": "Calcolo eseguito",
"workflow.toolDisplayName.executeCode": "Codice eseguito",
"workflow.toolDisplayName.finishOnboarding": "Onboarding completato",
+2
View File
@@ -349,6 +349,8 @@
"loading": "Caricamento...",
"mail.business": "Collaborazioni commerciali",
"mail.support": "Supporto via email",
"messengerBanner.dismiss": "Chiudi",
"messengerBanner.title": "Parla con Lobe AI sulle tue app di messaggistica preferite",
"more": "Altro",
"navPanel.agent": "Agente",
"navPanel.customizeSidebar": "Personalizza barra laterale",
-1
View File
@@ -35,7 +35,6 @@
"messenger.linkModal.notConfigured": "Questa connessione non è disponibile al momento. Riprova più tardi.",
"messenger.linkModal.openCta": "Apri in {{platform}}",
"messenger.linkModal.scanHint": "Oppure scansiona con il tuo telefono per aprire {{platform}}.",
"messenger.linkModal.title": "Connetti Messenger",
"messenger.list.discord.description": "Chatta con i tuoi agenti LobeHub da qualsiasi server Discord tramite DM con il bot LobeHub.",
"messenger.list.slack.description": "Chatta con i tuoi agenti LobeHub da qualsiasi workspace Slack tramite DM o @LobeHub.",
"messenger.list.telegram.description": "Chatta con i tuoi agenti LobeHub in Telegram e scegli chi risponde da qualsiasi luogo.",
+13 -20
View File
@@ -106,7 +106,6 @@
"MiniMax-Hailuo-2.3.description": "Nuovo modello di generazione video con aggiornamenti completi nei movimenti del corpo, realismo fisico e aderenza alle istruzioni.",
"MiniMax-M1.description": "Nuovo modello di ragionamento proprietario con 80K chain-of-thought e 1M di input, con prestazioni comparabili ai migliori modelli globali.",
"MiniMax-M2-Stable.description": "Progettato per flussi di lavoro di codifica e agenti efficienti, con maggiore concorrenza per l'uso commerciale.",
"MiniMax-M2.1-Lightning.description": "Potenti capacità di programmazione multilingue con inferenza più veloce ed efficiente.",
"MiniMax-M2.1-highspeed.description": "Potenti capacità di programmazione multilingue, esperienza di programmazione completamente aggiornata. Più veloce ed efficiente.",
"MiniMax-M2.1.description": "MiniMax-M2.1 è un modello open-source di punta di MiniMax, progettato per affrontare compiti complessi del mondo reale. I suoi punti di forza principali sono le capacità di programmazione multilingue e la risoluzione di compiti complessi come agente.",
"MiniMax-M2.5-highspeed.description": "MiniMax M2.5 Highspeed: Stesse prestazioni di M2.5 con inferenza più veloce.",
@@ -315,11 +314,11 @@
"claude-3-haiku-20240307.description": "Claude 3 Haiku è il modello più veloce e compatto di Anthropic, progettato per risposte quasi istantanee con prestazioni rapide e accurate.",
"claude-3-opus-20240229.description": "Claude 3 Opus è il modello più potente di Anthropic per compiti altamente complessi, eccellendo in prestazioni, intelligenza, fluidità e comprensione.",
"claude-3-sonnet-20240229.description": "Claude 3 Sonnet bilancia intelligenza e velocità per carichi di lavoro aziendali, offrendo alta utilità a costi inferiori e distribuzione affidabile su larga scala.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 è il modello Haiku più veloce e intelligente di Anthropic, con velocità fulminea e pensiero esteso.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 è il modello Haiku più veloce e intelligente di Anthropic, con velocità fulminea e capacità di ragionamento estese.",
"claude-haiku-4-5.description": "Claude Haiku 4.5 di Anthropic — Haiku di nuova generazione con ragionamento e visione migliorati.",
"claude-haiku-4.5.description": "Claude Haiku 4.5 è il modello Haiku più veloce e intelligente di Anthropic, con velocità fulminea e capacità di ragionamento estese.",
"claude-opus-4-1-20250805-thinking.description": "Claude Opus 4.1 Thinking è una variante avanzata in grado di mostrare il proprio processo di ragionamento.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 è il modello più recente e avanzato di Anthropic per compiti altamente complessi, eccellendo in prestazioni, intelligenza, fluidità e comprensione.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 è l'ultimo e più avanzato modello di Anthropic per compiti altamente complessi, eccellendo in prestazioni, intelligenza, fluidità e comprensione.",
"claude-opus-4-1.description": "Claude Opus 4.1 di Anthropic — modello premium di ragionamento con capacità di analisi approfondita.",
"claude-opus-4-20250514.description": "Claude Opus 4 è il modello più potente di Anthropic per compiti altamente complessi, eccellendo in prestazioni, intelligenza, fluidità e comprensione.",
"claude-opus-4-5-20251101.description": "Claude Opus 4.5 è il modello di punta di Anthropic, che combina intelligenza eccezionale e prestazioni scalabili, ideale per compiti complessi che richiedono risposte e ragionamenti di altissima qualità.",
@@ -330,8 +329,8 @@
"claude-opus-4.6-fast.description": "Claude Opus 4.6 è il modello più intelligente di Anthropic per la creazione di agenti e la programmazione.",
"claude-opus-4.6.description": "Claude Opus 4.6 è il modello più intelligente di Anthropic per la creazione di agenti e la programmazione.",
"claude-sonnet-4-20250514-thinking.description": "Claude Sonnet 4 Thinking può produrre risposte quasi istantanee o riflessioni estese passo dopo passo con processo visibile.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 è il modello più intelligente di Anthropic fino ad oggi, offrendo risposte quasi istantanee o pensiero esteso passo dopo passo con controllo dettagliato per gli utenti API.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5 è il modello più intelligente di Anthropic fino ad oggi.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 può produrre risposte quasi istantanee o pensieri estesi passo dopo passo con un processo visibile.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5 è il modello più intelligente mai creato da Anthropic.",
"claude-sonnet-4-5.description": "Claude Sonnet 4.5 di Anthropic — Sonnet migliorato con prestazioni di codifica avanzate.",
"claude-sonnet-4-6.description": "Claude Sonnet 4.6 di Anthropic — ultimo Sonnet con codifica superiore e utilizzo di strumenti.",
"claude-sonnet-4.5.description": "Claude Sonnet 4.5 è il modello più intelligente mai creato da Anthropic.",
@@ -404,7 +403,7 @@
"deepseek-ai/deepseek-llm-67b-chat.description": "DeepSeek LLM Chat (67B) è un modello innovativo che offre una profonda comprensione linguistica e interazione.",
"deepseek-ai/deepseek-v3.1-terminus.description": "DeepSeek V3.1 è un modello di nuova generazione per il ragionamento, con capacità avanzate di ragionamento complesso e chain-of-thought per compiti di analisi approfondita.",
"deepseek-ai/deepseek-v3.2.description": "DeepSeek V3.2 è un modello di ragionamento di nuova generazione con capacità avanzate di ragionamento complesso e catena di pensiero.",
"deepseek-chat.description": "Alias di compatibilità per la modalità non-pensante di DeepSeek V4 Flash. Programmato per la deprecazione — utilizzare invece DeepSeek V4 Flash.",
"deepseek-chat.description": "Un nuovo modello open-source che combina capacità generali e di codifica. Preserva il dialogo generale del modello di chat e la forte capacità di codifica del modello coder, con un migliore allineamento delle preferenze. DeepSeek-V2.5 migliora anche la scrittura e il seguito delle istruzioni.",
"deepseek-coder-33B-instruct.description": "DeepSeek Coder 33B è un modello linguistico per il codice addestrato su 2 trilioni di token (87% codice, 13% testo in cinese/inglese). Introduce una finestra di contesto da 16K e compiti di completamento intermedio, offrendo completamento di codice a livello di progetto e riempimento di snippet.",
"deepseek-coder-v2.description": "DeepSeek Coder V2 è un modello MoE open-source per il codice che ottiene ottimi risultati nei compiti di programmazione, comparabile a GPT-4 Turbo.",
"deepseek-coder-v2:236b.description": "DeepSeek Coder V2 è un modello MoE open-source per il codice che ottiene ottimi risultati nei compiti di programmazione, comparabile a GPT-4 Turbo.",
@@ -426,7 +425,7 @@
"deepseek-r1-fast-online.description": "DeepSeek R1 versione completa veloce con ricerca web in tempo reale, che combina capacità su scala 671B e risposte rapide.",
"deepseek-r1-online.description": "DeepSeek R1 versione completa con 671 miliardi di parametri e ricerca web in tempo reale, che offre una comprensione e generazione più avanzate.",
"deepseek-r1.description": "DeepSeek-R1 utilizza dati cold-start prima dell'RL e ottiene prestazioni comparabili a OpenAI-o1 in matematica, programmazione e ragionamento.",
"deepseek-reasoner.description": "Alias di compatibilità per la modalità pensante di DeepSeek V4 Flash. Programmato per la deprecazione — utilizzare invece DeepSeek V4 Flash.",
"deepseek-reasoner.description": "Un modello di ragionamento DeepSeek focalizzato su compiti di ragionamento logico complessi.",
"deepseek-v2.description": "DeepSeek V2 è un modello MoE efficiente per un'elaborazione conveniente.",
"deepseek-v2:236b.description": "DeepSeek V2 236B è il modello DeepSeek focalizzato sul codice con forte capacità di generazione.",
"deepseek-v3-0324.description": "DeepSeek-V3-0324 è un modello MoE con 671 miliardi di parametri, con punti di forza nella programmazione, capacità tecnica, comprensione del contesto e gestione di testi lunghi.",
@@ -491,8 +490,6 @@
"doubao-seedream-4-0-250828.description": "Seedream 4.0 è un modello di generazione di immagini di ByteDance Seed, che supporta input di testo e immagini con generazione di immagini di alta qualità e altamente controllabile. Genera immagini da prompt testuali.",
"doubao-seedream-4-5-251128.description": "Seedream 4.5 è l'ultimo modello multimodale di ByteDance, che integra capacità di generazione da testo a immagine, immagine a immagine e generazione di immagini in batch, incorporando anche conoscenze di senso comune e capacità di ragionamento. Rispetto alla versione precedente 4.0, offre una qualità di generazione significativamente migliorata, con una maggiore coerenza nell'editing e nella fusione di più immagini. Offre un controllo più preciso sui dettagli visivi, producendo testi e volti piccoli in modo più naturale, e raggiunge una disposizione e una colorazione più armoniose, migliorando l'estetica complessiva.",
"doubao-seedream-5-0-260128.description": "Doubao-Seedream-5.0-lite è l'ultimo modello di generazione di immagini di ByteDance. Per la prima volta, integra capacità di recupero online, consentendo di incorporare informazioni web in tempo reale e migliorare la tempestività delle immagini generate. L'intelligenza del modello è stata inoltre aggiornata, consentendo un'interpretazione precisa di istruzioni complesse e contenuti visivi. Inoltre, offre una copertura globale della conoscenza migliorata, una maggiore coerenza di riferimento e una qualità di generazione superiore in scenari professionali, soddisfacendo meglio le esigenze di creazione visiva a livello aziendale.",
"dreamina-seedance-2-0-260128.description": "Seedance 2.0 di ByteDance è il modello di generazione video più potente, supportando generazione di video multimodali di riferimento, editing video, estensione video, testo-a-video e immagine-a-video con audio sincronizzato.",
"dreamina-seedance-2-0-fast-260128.description": "Seedance 2.0 Fast di ByteDance offre le stesse capacità di Seedance 2.0 con velocità di generazione più rapide a un prezzo più competitivo.",
"emohaa.description": "Emohaa è un modello per la salute mentale con capacità di consulenza professionale per aiutare gli utenti a comprendere le problematiche emotive.",
"ernie-4.5-0.3b.description": "ERNIE 4.5 0.3B è un modello open-source leggero per implementazioni locali e personalizzate.",
"ernie-4.5-8k-preview.description": "ERNIE 4.5 8K Preview è un modello di anteprima con finestra contestuale da 8K per la valutazione di ERNIE 4.5.",
@@ -517,8 +514,7 @@
"ernie-x1-turbo-32k.description": "ERNIE X1 Turbo 32K è un modello di pensiero veloce con contesto da 32K per ragionamento complesso e chat multi-turno.",
"ernie-x1.1-preview.description": "ERNIE X1.1 Preview è unanteprima del modello di pensiero per valutazioni e test.",
"ernie-x1.1.description": "ERNIE X1.1 è un'anteprima del modello di pensiero per valutazione e test.",
"fal-ai/bytedance/seedream/v4.5.description": "Seedream 4.5, sviluppato dal team Seed di ByteDance, supporta l'editing e la composizione multi-immagine. Presenta una maggiore coerenza del soggetto, un'istruzione precisa, comprensione della logica spaziale, espressione estetica, layout di poster e design di loghi con rendering testo-immagine ad alta precisione.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0, sviluppato da ByteDance Seed, supporta input di testo e immagini per una generazione di immagini altamente controllabile e di alta qualità a partire da prompt.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0 è un modello di generazione di immagini di ByteDance Seed, che supporta input di testo e immagini con generazione di immagini altamente controllabile e di alta qualità. Genera immagini a partire da prompt testuali.",
"fal-ai/flux-kontext/dev.description": "FLUX.1 è un modello focalizzato sullediting di immagini, che supporta input di testo e immagini.",
"fal-ai/flux-pro/kontext.description": "FLUX.1 Kontext [pro] accetta testo e immagini di riferimento come input, consentendo modifiche locali mirate e trasformazioni complesse della scena globale.",
"fal-ai/flux/krea.description": "Flux Krea [dev] è un modello di generazione di immagini con una preferenza estetica per immagini più realistiche e naturali.",
@@ -526,8 +522,8 @@
"fal-ai/hunyuan-image/v3.description": "Un potente modello nativo multimodale per la generazione di immagini.",
"fal-ai/imagen4/preview.description": "Modello di generazione di immagini di alta qualità sviluppato da Google.",
"fal-ai/nano-banana.description": "Nano Banana è il modello multimodale nativo più recente, veloce ed efficiente di Google, che consente la generazione e lediting di immagini tramite conversazione.",
"fal-ai/qwen-image-edit.description": "Un modello professionale di editing immagini del team Qwen, che supporta modifiche semantiche e di aspetto, editing preciso di testo in cinese/inglese, trasferimento di stile, rotazione e altro.",
"fal-ai/qwen-image.description": "Un potente modello di generazione di immagini del team Qwen con una forte resa del testo cinese e stili visivi diversificati.",
"fal-ai/qwen-image-edit.description": "Un modello professionale di editing di immagini del team Qwen che supporta modifiche semantiche e di aspetto, modifica con precisione testo in cinese e inglese, e consente modifiche di alta qualità come trasferimento di stile e rotazione di oggetti.",
"fal-ai/qwen-image.description": "Un potente modello di generazione di immagini del team Qwen con impressionante rendering di testo in cinese e stili visivi diversificati.",
"flux-1-schnell.description": "Modello testo-immagine da 12 miliardi di parametri di Black Forest Labs che utilizza la distillazione latente avversariale per generare immagini di alta qualità in 1-4 passaggi. Con licenza Apache-2.0 per uso personale, di ricerca e commerciale.",
"flux-dev.description": "Modello open-source per la ricerca e sviluppo nella generazione di immagini, ottimizzato in modo efficiente per la ricerca innovativa non commerciale.",
"flux-kontext-max.description": "Generazione ed editing di immagini contestuali allavanguardia, combinando testo e immagini per risultati precisi e coerenti.",
@@ -569,7 +565,7 @@
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro) è il modello di generazione di immagini di Google e supporta anche la chat multimodale.",
"gemini-3-pro-preview.description": "Gemini 3 Pro è il modello più potente di Google per agenti e codifica creativa, offrendo visuali più ricche e interazioni più profonde grazie a un ragionamento all'avanguardia.",
"gemini-3.1-flash-image-preview.description": "Gemini 3.1 Flash Image (Nano Banana 2) è il modello di generazione di immagini nativo più veloce di Google con supporto al pensiero, generazione e modifica di immagini conversazionali.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) offre qualità di immagine a livello Pro a velocità Flash con supporto per la chat multimodale.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) è il modello di generazione di immagini nativo più veloce di Google con supporto al pensiero, generazione e modifica di immagini conversazionali.",
"gemini-3.1-flash-lite-preview.description": "Gemini 3.1 Flash-Lite Preview è il modello multimodale più economico di Google, ottimizzato per compiti agentici ad alto volume, traduzione e elaborazione dati.",
"gemini-3.1-flash-lite.description": "Gemini 3.1 Flash-Lite è il modello multimodale più economico di Google, ottimizzato per compiti agentici ad alto volume, traduzione e elaborazione dati.",
"gemini-3.1-pro-preview.description": "Gemini 3.1 Pro Preview migliora Gemini 3 Pro con capacità di ragionamento avanzate e aggiunge supporto per un livello di pensiero medio.",
@@ -734,8 +730,6 @@
"grok-4-fast-reasoning.description": "Siamo entusiasti di presentare Grok 4 Fast, il nostro ultimo progresso nei modelli di ragionamento a basso costo.",
"grok-4.20-0309-non-reasoning.description": "Una variante senza ragionamento per casi d'uso semplici.",
"grok-4.20-0309-reasoning.description": "Modello intelligente e velocissimo che ragiona prima di rispondere.",
"grok-4.20-beta-0309-non-reasoning.description": "Una variante non-pensante per casi d'uso semplici.",
"grok-4.20-beta-0309-reasoning.description": "Modello intelligente e ultra-veloce che ragiona prima di rispondere.",
"grok-4.20-multi-agent-0309.description": "Un team di 4 o 16 agenti, eccelle nei casi d'uso di ricerca, non supporta attualmente strumenti client-side. Supporta solo strumenti server-side xAI (es. X Search, strumenti di ricerca web) e strumenti MCP remoti.",
"grok-4.3.description": "Il modello linguistico di grandi dimensioni più orientato alla verità al mondo",
"grok-4.description": "Ultimo modello di punta Grok con prestazioni ineguagliabili in linguaggio, matematica e ragionamento — un vero tuttofare. Attualmente punta a grok-4-0709; a causa di risorse limitate, il prezzo è temporaneamente superiore del 10% rispetto al prezzo ufficiale e si prevede un ritorno al prezzo ufficiale in seguito.",
@@ -1220,8 +1214,6 @@
"qwq.description": "QwQ è un modello di ragionamento della famiglia Qwen. Rispetto ai modelli standard ottimizzati per istruzioni, offre capacità di pensiero e ragionamento che migliorano significativamente le prestazioni nei compiti difficili. QwQ-32B è un modello di medie dimensioni che compete con i migliori modelli di ragionamento come DeepSeek-R1 e o1-mini.",
"qwq_32b.description": "Modello di ragionamento di medie dimensioni della famiglia Qwen. Rispetto ai modelli standard ottimizzati per istruzioni, le capacità di pensiero e ragionamento di QwQ migliorano significativamente le prestazioni nei compiti difficili.",
"r1-1776.description": "R1-1776 è una variante post-addestrata di DeepSeek R1 progettata per fornire informazioni fattuali non censurate e imparziali.",
"seedance-1-5-pro-251215.description": "Seedance 1.5 Pro di ByteDance supporta testo-a-video, immagine-a-video (primo fotogramma, primo+ultimo fotogramma) e generazione audio sincronizzata con i visual.",
"seedream-5-0-260128.description": "ByteDance-Seedream-5.0-lite di BytePlus presenta una generazione aumentata da recupero web per informazioni in tempo reale, interpretazione migliorata di prompt complessi e maggiore coerenza di riferimento per creazioni visive professionali.",
"solar-mini-ja.description": "Solar Mini (Ja) estende Solar Mini con un focus sul giapponese, mantenendo prestazioni efficienti e solide in inglese e coreano.",
"solar-mini.description": "Solar Mini è un LLM compatto che supera GPT-3.5, con forte capacità multilingue in inglese e coreano, offrendo una soluzione efficiente e leggera.",
"solar-pro.description": "Solar Pro è un LLM ad alta intelligenza di Upstage, focalizzato sullesecuzione di istruzioni su una singola GPU, con punteggi IFEval superiori a 80. Attualmente supporta linglese; il rilascio completo è previsto per novembre 2024 con supporto linguistico ampliato e contesto più lungo.",
@@ -1233,7 +1225,9 @@
"sophnet/deepseek-v3.2.description": "DeepSeek V3.2 è un modello che bilancia alta efficienza computazionale con eccellenti prestazioni di ragionamento e agenti.",
"sora-2-pro.description": "Sora 2 Pro è il nostro modello di generazione multimediale più avanzato, che genera video con audio sincronizzato. Può creare clip dinamici e riccamente dettagliati da linguaggio naturale o immagini.",
"sora-2.description": "Sora 2 è il nostro nuovo potente modello di generazione multimediale, che genera video con audio sincronizzato. Può creare clip dinamici e riccamente dettagliati da linguaggio naturale o immagini.",
"spark-x.description": "Panoramica delle capacità di X2: 1. Introduce l'adattamento dinamico della modalità di ragionamento, controllato tramite il campo `thinking`. 2. Lunghezza del contesto espansa: 64K token di input e 128K token di output. 3. Supporta la funzionalità Function Call.",
"spark-x1.5.description": "Aggiornamenti X1.5: (1) aggiunge la modalità di pensiero dinamico controllata dal campo `thinking`; (2) lunghezza del contesto maggiore con 64K di input e 64K di output; (3) supporta FunctionCall.",
"spark-x2-flash.description": "Spark X2-Flash adotta un'architettura MoE (Mixture of Experts) con un totale di 30 miliardi di parametri e supporta fino a una finestra di contesto di 256K. Offre miglioramenti significativi nelle capacità agentiche e di codifica, ed è stato addestrato su un cluster di processori AI Ascend 910B.",
"spark-x2.description": "Panoramica delle capacità di X2: 1. Introduce la regolazione dinamica della modalità di ragionamento, controllata tramite il campo `thinking`. 2. Lunghezza del contesto espansa: 64K token di input e 128K token di output. 3. Supporta la funzionalità Function Call.",
"stable-diffusion-3-medium.description": "L'ultimo modello text-to-image di Stability AI. Questa versione migliora significativamente la qualità delle immagini, la comprensione del testo e la diversità stilistica, interpretando con maggiore precisione prompt complessi in linguaggio naturale e generando immagini più accurate e varie.",
"stable-diffusion-3.5-large-turbo.description": "Stable Diffusion 3.5 Large Turbo è focalizzato sulla generazione di immagini di alta qualità, con una forte resa dei dettagli e fedeltà della scena.",
"stable-diffusion-xl-base-1.0.description": "Modello open-source text-to-image di Stability AI con generazione creativa di immagini leader nel settore. Ha una forte comprensione delle istruzioni e supporta definizioni inverse dei prompt per generazioni precise.",
@@ -1355,7 +1349,6 @@
"x-ai/grok-4.1-fast.description": "Grok 4 Fast è il modello ad alta capacità e basso costo di xAI (supporta una finestra di contesto da 2M), ideale per casi d'uso con alta concorrenza e contesti lunghi.",
"x-ai/grok-4.description": "Grok 4 è il modello di punta di xAI con forti capacità di ragionamento e multimodalità.",
"x-ai/grok-code-fast-1.description": "Grok Code Fast 1 è il modello veloce di xAI per la programmazione, con output leggibile e adatto all'ingegneria.",
"x1.description": "Aggiornamenti di X1.5: (1) aggiunge una modalità di pensiero dinamico controllata dal campo `thinking`; (2) lunghezza del contesto maggiore con 64K di input e 64K di output; (3) supporta FunctionCall.",
"xai/grok-2-vision.description": "Grok 2 Vision eccelle nei compiti visivi, offrendo prestazioni all'avanguardia nel ragionamento matematico visivo (MathVista) e nella QA su documenti (DocVQA). Gestisce documenti, grafici, tabelle, screenshot e foto.",
"xai/grok-2.description": "Grok 2 è un modello all'avanguardia con prestazioni eccellenti in ragionamento, chat, programmazione e classificato sopra Claude 3.5 Sonnet e GPT-4 Turbo su LMSYS.",
"xai/grok-3-fast.description": "Il modello di punta di xAI eccelle in casi d'uso aziendali come estrazione dati, programmazione e sintesi, con profonda conoscenza nei settori finanza, sanità, diritto e scienza. La variante veloce utilizza un'infrastruttura più rapida per risposte molto più veloci a un costo per token più elevato.",
+21 -21
View File
@@ -69,9 +69,22 @@
"builtins.lobe-agent-management.render.installPlugin.plugin": "Plugin",
"builtins.lobe-agent-management.render.installPlugin.success": "Installato con successo",
"builtins.lobe-agent-management.title": "Gestore Agenti",
"builtins.lobe-agent-marketplace.apiName.showAgentMarketplace": "Apri il mercato degli agenti",
"builtins.lobe-agent-marketplace.apiName.submitAgentPick": "Invia le scelte degli agenti",
"builtins.lobe-agent-marketplace.title": "Mercato degli Agenti",
"builtins.lobe-agent.apiName.callSubAgent": "Chiama sub-agente",
"builtins.lobe-agent.apiName.callSubAgent.completed": "Sub-agente inviato: ",
"builtins.lobe-agent.apiName.callSubAgent.loading": "Invio sub-agente: ",
"builtins.lobe-agent.apiName.callSubAgents": "Chiama sub-agenti",
"builtins.lobe-agent.apiName.clearTodos": "Cancella attività",
"builtins.lobe-agent.apiName.clearTodos.modeAll": "tutte",
"builtins.lobe-agent.apiName.clearTodos.modeCompleted": "completate",
"builtins.lobe-agent.apiName.clearTodos.result": "Cancella <mode>{{mode}}</mode> attività",
"builtins.lobe-agent.apiName.createPlan": "Crea piano",
"builtins.lobe-agent.apiName.createPlan.result": "Crea piano: <goal>{{goal}}</goal>",
"builtins.lobe-agent.apiName.createTodos": "Crea attività",
"builtins.lobe-agent.apiName.updatePlan": "Aggiorna piano",
"builtins.lobe-agent.apiName.updatePlan.completed": "Completato",
"builtins.lobe-agent.apiName.updatePlan.modified": "Modificato",
"builtins.lobe-agent.apiName.updateTodos": "Aggiorna attività",
"builtins.lobe-agent.title": "Agente Lobe",
"builtins.lobe-claude-code.agent.instruction": "Istruzione",
"builtins.lobe-claude-code.agent.result": "Risultato",
"builtins.lobe-claude-code.todoWrite.allDone": "Tutte le attività completate",
@@ -139,24 +152,6 @@
"builtins.lobe-group-management.inspector.executeAgentTasks.title": "Assegnazione attività a:",
"builtins.lobe-group-management.inspector.speak.title": "Parla l'Agente designato:",
"builtins.lobe-group-management.title": "Coordinatore del Gruppo",
"builtins.lobe-gtd.apiName.clearTodos": "Cancella attività",
"builtins.lobe-gtd.apiName.clearTodos.modeAll": "tutte",
"builtins.lobe-gtd.apiName.clearTodos.modeCompleted": "completate",
"builtins.lobe-gtd.apiName.clearTodos.result": "Cancellate attività <mode>{{mode}}</mode>",
"builtins.lobe-gtd.apiName.completeTodos": "Completa attività",
"builtins.lobe-gtd.apiName.createPlan": "Crea piano",
"builtins.lobe-gtd.apiName.createPlan.result": "Creato piano: <goal>{{goal}}</goal>",
"builtins.lobe-gtd.apiName.createTodos": "Crea attività",
"builtins.lobe-gtd.apiName.execTask": "Esegui attività",
"builtins.lobe-gtd.apiName.execTask.completed": "Attività creata: ",
"builtins.lobe-gtd.apiName.execTask.loading": "Creazione dell'attività in corso: ",
"builtins.lobe-gtd.apiName.execTasks": "Esegui attività",
"builtins.lobe-gtd.apiName.removeTodos": "Elimina attività",
"builtins.lobe-gtd.apiName.updatePlan": "Aggiorna piano",
"builtins.lobe-gtd.apiName.updatePlan.completed": "Completato",
"builtins.lobe-gtd.apiName.updatePlan.modified": "Modificato",
"builtins.lobe-gtd.apiName.updateTodos": "Aggiorna attività",
"builtins.lobe-gtd.title": "Strumenti per Attività",
"builtins.lobe-knowledge-base.apiName.readKnowledge": "Leggi contenuto della Libreria",
"builtins.lobe-knowledge-base.apiName.searchKnowledgeBase": "Cerca nella Libreria",
"builtins.lobe-knowledge-base.inspector.andMoreFiles": "e altri {{count}}",
@@ -317,6 +312,8 @@
"builtins.lobe-web-onboarding.apiName.finishOnboarding": "Termina onboarding",
"builtins.lobe-web-onboarding.apiName.readDocument": "Leggi documento",
"builtins.lobe-web-onboarding.apiName.saveUserQuestion": "Salva domanda dell'utente",
"builtins.lobe-web-onboarding.apiName.showAgentMarketplace": "Forma il team di agenti",
"builtins.lobe-web-onboarding.apiName.submitAgentPick": "Invia selezione agenti",
"builtins.lobe-web-onboarding.apiName.updateDocument": "Aggiorna documento",
"builtins.lobe-web-onboarding.apiName.writeDocument": "Scrivi documento",
"builtins.lobe-web-onboarding.docType.persona": "Persona utente",
@@ -327,6 +324,9 @@
"builtins.lobe-web-onboarding.inspector.hunkCount_other": "{{count}} modifiche",
"builtins.lobe-web-onboarding.inspector.interests_one": "{{count}} interesse",
"builtins.lobe-web-onboarding.inspector.interests_other": "{{count}} interessi",
"builtins.lobe-web-onboarding.render.agent": "Agente",
"builtins.lobe-web-onboarding.render.fullName": "Nome completo",
"builtins.lobe-web-onboarding.render.interests": "Interessi",
"builtins.lobe-web-onboarding.title": "Onboarding Utente",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.delete": "Elimina",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.deleteLines": "Elimina righe",
-1
View File
@@ -33,7 +33,6 @@
"jina.description": "Fondata nel 2020, Jina AI è un'azienda leader nell'AI per la ricerca. Il suo stack include modelli vettoriali, reranker e piccoli modelli linguistici per costruire app di ricerca generativa e multimodale affidabili e di alta qualità.",
"kimicodingplan.description": "Kimi Code di Moonshot AI offre accesso ai modelli Kimi, inclusi K2.5, per attività di codifica.",
"lmstudio.description": "LM Studio è un'app desktop per sviluppare e sperimentare con LLM direttamente sul tuo computer.",
"lobehub.description": "LobeHub Cloud utilizza API ufficiali per accedere ai modelli di intelligenza artificiale e misura l'utilizzo con Crediti legati ai token del modello.",
"longcat.description": "LongCat è una serie di modelli AI generativi di grandi dimensioni sviluppati indipendentemente da Meituan. È progettato per migliorare la produttività interna dell'azienda e consentire applicazioni innovative attraverso un'architettura computazionale efficiente e potenti capacità multimodali.",
"minimax.description": "Fondata nel 2021, MiniMax sviluppa AI generali con modelli fondamentali multimodali, inclusi modelli testuali MoE da trilioni di parametri, modelli vocali e visivi, oltre ad app come Hailuo AI.",
"minimaxcodingplan.description": "Il piano di token MiniMax offre accesso ai modelli MiniMax, inclusi M2.7, per attività di codifica tramite un abbonamento a tariffa fissa.",
-2
View File
@@ -913,8 +913,6 @@
"tools.builtins.lobe-agent-documents.title": "Documenti",
"tools.builtins.lobe-agent-management.description": "Crea, gestisci e organizza agenti AI",
"tools.builtins.lobe-agent-management.title": "Gestione Agente",
"tools.builtins.lobe-agent-marketplace.description": "Mostra agli utenti una scheda del Mercato degli Agenti curata e registra i modelli che scelgono.",
"tools.builtins.lobe-agent-marketplace.title": "Mercato degli Agenti",
"tools.builtins.lobe-artifacts.description": "Genera e visualizza in anteprima componenti UI interattivi, grafici e contenuti web",
"tools.builtins.lobe-artifacts.readme": "Genera e visualizza in anteprima componenti UI interattivi, visualizzazioni di dati, grafici, grafica SVG e applicazioni web. Crea contenuti visivi ricchi con cui gli utenti possono interagire direttamente.",
"tools.builtins.lobe-artifacts.title": "Artefatti",
+45 -45
View File
@@ -56,51 +56,51 @@
"dalle.generating": "Generazione in corso...",
"dalle.images": "Immagini:",
"dalle.prompt": "Prompt",
"lobe-gtd.actions.add": "Aggiungi",
"lobe-gtd.actions.clearCompleted": "Cancella Completati",
"lobe-gtd.actions.placeholder": "Inserisci un'attività da fare...",
"lobe-gtd.addTodo.placeholder": "Aggiungi un'attività da fare...",
"lobe-gtd.clearTodos.cleared": "{{count}} elemento(i) cancellato(i)",
"lobe-gtd.clearTodos.clearedCompleted": "{{count}} elemento(i) completato(i) cancellato(i)",
"lobe-gtd.clearTodos.clearedCompleted_one": "{{count}} elemento completato cancellato",
"lobe-gtd.clearTodos.clearedCompleted_other": "{{count}} elementi completati cancellati",
"lobe-gtd.clearTodos.cleared_one": "{{count}} elemento cancellato",
"lobe-gtd.clearTodos.cleared_other": "{{count}} elementi cancellati",
"lobe-gtd.clearTodos.header": "Cancella Attività",
"lobe-gtd.clearTodos.label": "Scegli cosa cancellare:",
"lobe-gtd.clearTodos.noItems": "Nessun elemento da cancellare",
"lobe-gtd.clearTodos.option.all": "Cancella tutti gli elementi (inclusi quelli in sospeso)",
"lobe-gtd.clearTodos.option.completed": "Cancella solo gli elementi completati",
"lobe-gtd.clearTodos.remaining": "{{count}} elemento(i) rimanente(i)",
"lobe-gtd.clearTodos.remaining_one": "{{count}} elemento rimanente",
"lobe-gtd.clearTodos.remaining_other": "{{count}} elementi rimanenti",
"lobe-gtd.completeTodos.completed": "{{count}} elemento(i) completato(i)",
"lobe-gtd.completeTodos.completed_one": "{{count}} elemento completato",
"lobe-gtd.completeTodos.completed_other": "{{count}} elementi completati",
"lobe-gtd.createPlan.context.label": "Contesto (opzionale)",
"lobe-gtd.createPlan.context.placeholder": "Contesto, vincoli, considerazioni...",
"lobe-gtd.createPlan.description.label": "Descrizione",
"lobe-gtd.createPlan.description.placeholder": "Breve riassunto del piano",
"lobe-gtd.createPlan.goal.label": "Obiettivo",
"lobe-gtd.createPlan.goal.placeholder": "Cosa vuoi ottenere?",
"lobe-gtd.createTodos.created": "{{count}} attività da fare creata(e)",
"lobe-gtd.createTodos.created_one": "{{count}} attività da fare creata",
"lobe-gtd.createTodos.created_other": "{{count}} attività da fare create",
"lobe-gtd.createTodos.total": "Totale: {{count}} elemento(i)",
"lobe-gtd.createTodos.total_one": "Totale: {{count}} elemento",
"lobe-gtd.createTodos.total_other": "Totale: {{count}} elementi",
"lobe-gtd.removeTodos.removed": "{{count}} elemento(i) rimosso(i)",
"lobe-gtd.removeTodos.removed_one": "{{count}} elemento rimosso",
"lobe-gtd.removeTodos.removed_other": "{{count}} elementi rimossi",
"lobe-gtd.status.done": "{{count}} completato(i)",
"lobe-gtd.status.pending": "{{count}} in sospeso",
"lobe-gtd.todoItem.placeholder": "Inserisci attività da fare...",
"lobe-gtd.todoList.empty": "La lista delle attività è vuota",
"lobe-gtd.todoList.items": "{{count}} elemento(i)",
"lobe-gtd.todoList.items_one": "{{count}} elemento",
"lobe-gtd.todoList.items_other": "{{count}} elementi",
"lobe-gtd.todoList.title": "Lista delle Attività",
"lobe-gtd.updateTodos.updated": "Lista delle attività aggiornata",
"lobe-agent.actions.add": "Aggiungi",
"lobe-agent.actions.clearCompleted": "Cancella Completati",
"lobe-agent.actions.placeholder": "Inserisci un'attività da fare...",
"lobe-agent.addTodo.placeholder": "Aggiungi un'attività da fare...",
"lobe-agent.clearTodos.cleared": "{{count}} elemento/i cancellato/i",
"lobe-agent.clearTodos.clearedCompleted": "{{count}} elemento/i completato/i cancellato/i",
"lobe-agent.clearTodos.clearedCompleted_one": "{{count}} elemento completato cancellato",
"lobe-agent.clearTodos.clearedCompleted_other": "{{count}} elementi completati cancellati",
"lobe-agent.clearTodos.cleared_one": "{{count}} elemento cancellato",
"lobe-agent.clearTodos.cleared_other": "{{count}} elementi cancellati",
"lobe-agent.clearTodos.header": "Cancella Elementi da Fare",
"lobe-agent.clearTodos.label": "Scegli cosa cancellare:",
"lobe-agent.clearTodos.noItems": "Nessun elemento da cancellare",
"lobe-agent.clearTodos.option.all": "Cancella tutti gli elementi (inclusi quelli in sospeso)",
"lobe-agent.clearTodos.option.completed": "Cancella solo gli elementi completati",
"lobe-agent.clearTodos.remaining": "{{count}} elemento/i rimanente/i",
"lobe-agent.clearTodos.remaining_one": "{{count}} elemento rimanente",
"lobe-agent.clearTodos.remaining_other": "{{count}} elementi rimanenti",
"lobe-agent.completeTodos.completed": "{{count}} elemento/i completato/i",
"lobe-agent.completeTodos.completed_one": "{{count}} elemento completato",
"lobe-agent.completeTodos.completed_other": "{{count}} elementi completati",
"lobe-agent.createPlan.context.label": "Contesto (opzionale)",
"lobe-agent.createPlan.context.placeholder": "Contesto, vincoli, considerazioni...",
"lobe-agent.createPlan.description.label": "Descrizione",
"lobe-agent.createPlan.description.placeholder": "Breve riassunto del piano",
"lobe-agent.createPlan.goal.label": "Obiettivo",
"lobe-agent.createPlan.goal.placeholder": "Cosa vuoi raggiungere?",
"lobe-agent.createTodos.created": "{{count}} attività da fare creata/e",
"lobe-agent.createTodos.created_one": "{{count}} attività da fare creata",
"lobe-agent.createTodos.created_other": "{{count}} attività da fare create",
"lobe-agent.createTodos.total": "Totale: {{count}} elemento/i",
"lobe-agent.createTodos.total_one": "Totale: {{count}} elemento",
"lobe-agent.createTodos.total_other": "Totale: {{count}} elementi",
"lobe-agent.removeTodos.removed": "{{count}} elemento/i rimosso/i",
"lobe-agent.removeTodos.removed_one": "{{count}} elemento rimosso",
"lobe-agent.removeTodos.removed_other": "{{count}} elementi rimossi",
"lobe-agent.status.done": "{{count}} completato/i",
"lobe-agent.status.pending": "{{count}} in sospeso",
"lobe-agent.todoItem.placeholder": "Inserisci un'attività da fare...",
"lobe-agent.todoList.empty": "La lista delle attività è vuota",
"lobe-agent.todoList.items": "{{count}} elemento/i",
"lobe-agent.todoList.items_one": "{{count}} elemento",
"lobe-agent.todoList.items_other": "{{count}} elementi",
"lobe-agent.todoList.title": "Lista delle Attività",
"lobe-agent.updateTodos.updated": "Lista delle attività aggiornata",
"lobe-knowledge-base.readKnowledge.meta.chars": "Conteggio Caratteri",
"lobe-knowledge-base.readKnowledge.meta.lines": "Conteggio Righe",
"localFiles.editFile.newString": "Sostituisci con",
+4
View File
@@ -115,6 +115,10 @@
"channel.line.fetchBotInfoMissingToken": "最初にチャネルアクセストークンを入力し、「LINEから取得」をクリックしてください。",
"channel.line.fetchBotInfoSuccess": "宛先ユーザーIDを取得しました",
"channel.line.webhookManualSetup": "LINEはプログラムによるWebhook登録を許可していません。このURLをLINE Developers ConsoleMessaging API → Webhook URL)にコピーし、「検証」をクリックして「Webhookを使用」を有効にしてください。",
"channel.messengerPromo.action": "Messengerを試す",
"channel.messengerPromo.desc": "ボットの設定は不要です。Slack、Discord、TelegramでLobeHubとチャットしましょう。",
"channel.messengerPromo.dismiss": "閉じる",
"channel.messengerPromo.title": "設定をスキップ",
"channel.openPlatform": "オープンプラットフォーム",
"channel.platforms": "プラットフォーム",
"channel.publicKey": "公開鍵",
+4 -3
View File
@@ -314,7 +314,7 @@
"openInNewWindow": "新しいウィンドウで開く",
"operation.contextCompression": "コンテキストが長すぎるため、履歴を圧縮しています...",
"operation.execAgentRuntime": "応答を準備中",
"operation.execClientTask": "タスクを実行中",
"operation.execClientSubAgent": "サブエージェントを実行中",
"operation.execHeterogeneousAgent": "{{name}} を実行中",
"operation.execServerAgentRuntime": "実行中… タスクは継続するため、別の作業に移ったりページを閉じても問題ありません。",
"operation.heterogeneousAgentFallback": "外部エージェント",
@@ -567,6 +567,7 @@
"taskList.contextMenu.copyLink": "リンクをコピー",
"taskList.contextMenu.copyLinkSuccess": "リンクをコピーしました",
"taskList.contextMenu.priority": "優先度",
"taskList.contextMenu.runNow": "今すぐ実行",
"taskList.contextMenu.status": "ステータス",
"taskList.empty": "まだタスクはありません",
"taskList.emptyHero.greeting": "今日は何に取り組みましょうか?",
@@ -771,6 +772,8 @@
"workflow.toolDisplayName.addPreferenceMemory": "保存済みメモリ",
"workflow.toolDisplayName.calculate": "計算済み",
"workflow.toolDisplayName.callAgent": "エージェントを呼び出しました",
"workflow.toolDisplayName.callSubAgent": "サブエージェントを派遣しました",
"workflow.toolDisplayName.callSubAgents": "複数のサブエージェントを派遣しました",
"workflow.toolDisplayName.clearTodos": "ToDoをクリアしました",
"workflow.toolDisplayName.copyDocument": "ドキュメントをコピーしました",
"workflow.toolDisplayName.crawlMultiPages": "クロールされたページ",
@@ -785,8 +788,6 @@
"workflow.toolDisplayName.editTitle": "編集済みのタイトル",
"workflow.toolDisplayName.evaluate": "式を評価しました",
"workflow.toolDisplayName.execScript": "スクリプトを実行しました",
"workflow.toolDisplayName.execTask": "タスクを実行しました",
"workflow.toolDisplayName.execTasks": "実行済みタスク",
"workflow.toolDisplayName.execute": "計算を実行しました",
"workflow.toolDisplayName.executeCode": "コードを実行しました",
"workflow.toolDisplayName.finishOnboarding": "オンボーディングが完了しました",
+2
View File
@@ -349,6 +349,8 @@
"loading": "読み込み中…",
"mail.business": "ビジネスパートナーシップ",
"mail.support": "メールサポート",
"messengerBanner.dismiss": "閉じる",
"messengerBanner.title": "お好きなメッセージングアプリでLobe AIと話しましょう",
"more": "もっと見る",
"navPanel.agent": "アシスタント",
"navPanel.customizeSidebar": "サイドバーをカスタマイズ",
-1
View File
@@ -35,7 +35,6 @@
"messenger.linkModal.notConfigured": "この接続は現在利用できません。後でもう一度お試しください。",
"messenger.linkModal.openCta": "{{platform}} で開く",
"messenger.linkModal.scanHint": "または、携帯電話でスキャンして {{platform}} を開きます。",
"messenger.linkModal.title": "メッセンジャーを接続",
"messenger.list.discord.description": "任意の Discord サーバーから DM を使用して LobeHub エージェントとチャットできます。",
"messenger.list.slack.description": "任意の Slack ワークスペースから DM または @LobeHub を使用して LobeHub エージェントとチャットできます。",
"messenger.list.telegram.description": "Telegram で LobeHub エージェントとチャットし、どこからでも応答するエージェントを選択できます。",
+15 -22
View File
@@ -106,7 +106,6 @@
"MiniMax-Hailuo-2.3.description": "身体動作、物理的リアリズム、指示追従性において全面的にアップグレードされた新しいビデオ生成モデル。",
"MiniMax-M1.description": "80Kの思考連鎖と1Mの入力を備えた新しい社内推論モデルで、世界トップクラスのモデルに匹敵する性能を発揮します。",
"MiniMax-M2-Stable.description": "効率的なコーディングとエージェントワークフローのために設計され、商用利用における高い同時実行性を実現します。",
"MiniMax-M2.1-Lightning.description": "強力な多言語プログラミング機能を備え、より高速かつ効率的な推論を実現。",
"MiniMax-M2.1-highspeed.description": "強力な多言語プログラミング機能を備え、プログラミング体験を包括的に向上。より高速かつ効率的です。",
"MiniMax-M2.1.description": "MiniMax-M2.1は、MiniMaxが開発したフラッグシップのオープンソース大規模モデルで、複雑な現実世界のタスク解決に特化しています。多言語プログラミング能力とエージェントとしての高度なタスク処理能力が主な強みです。",
"MiniMax-M2.5-highspeed.description": "MiniMax M2.5 Highspeed: M2.5と同等の性能で推論速度が向上。",
@@ -315,13 +314,13 @@
"claude-3-haiku-20240307.description": "Claude 3 Haikuは、Anthropicの最速かつ最小のモデルで、即時応答と高速かつ正確な性能を実現するよう設計されています。",
"claude-3-opus-20240229.description": "Claude 3 Opusは、Anthropicの最も強力なモデルで、非常に複雑なタスクにおいて卓越した性能、知性、流暢さ、理解力を発揮します。",
"claude-3-sonnet-20240229.description": "Claude 3 Sonnetは、知性と速度のバランスを取り、エンタープライズ向けのワークロードにおいて高い実用性とコスト効率、信頼性のある大規模展開を実現します。",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5はAnthropicの最速かつ最も知的なHaikuモデルで、驚異的な速度と拡張された思考能力を備えています。",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5はAnthropicの最速かつ最も賢いHaikuモデルで、驚異的なスピードと高度な推論能力を備えています。",
"claude-haiku-4-5.description": "Claude Haiku 4.5 by Anthropic — 次世代Haikuモデルで、推論能力とビジョンが強化されています。",
"claude-haiku-4.5.description": "Claude Haiku 4.5は、Anthropicの最速かつ最も賢いHaikuモデルで、驚異的なスピードと高度な推論能力を備えています。",
"claude-opus-4-1-20250805-thinking.description": "Claude Opus 4.1 Thinkingは、推論プロセスを可視化できる高度なバリアントです。",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1はAnthropicの最新かつ最も高性能なモデルで、非常に複雑なタスクにおいて卓越した性能、知性、流暢さ、理解力を発揮します。",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1はAnthropicの最新かつ最も高性能なモデルで、非常に複雑なタスクにおいて卓越したパフォーマンス、知性、流暢さ、理解力を発揮します。",
"claude-opus-4-1.description": "Claude Opus 4.1 by Anthropic — 深い分析能力を備えたプレミアム推論モデル。",
"claude-opus-4-20250514.description": "Claude Opus 4はAnthropicの最も強力なモデルで、非常に複雑なタスクにおいて卓越した性能、知性、流暢さ、理解力を発揮します。",
"claude-opus-4-20250514.description": "Claude Opus 4はAnthropicの最も強力なモデルで、非常に複雑なタスクにおいて卓越したパフォーマンス、知性、流暢さ、理解力を発揮します。",
"claude-opus-4-5-20251101.description": "Claude Opus 4.5は、Anthropicのフラッグシップモデルで、卓越した知性とスケーラブルな性能を兼ね備え、最高品質の応答と推論が求められる複雑なタスクに最適です。",
"claude-opus-4-5.description": "Claude Opus 4.5 by Anthropic — 最高レベルの推論とコーディング能力を備えたフラッグシップモデル。",
"claude-opus-4-6.description": "Claude Opus 4.6 by Anthropic — 1Mコンテキストウィンドウを備えたフラッグシップモデルで、高度な推論能力を提供します。",
@@ -330,8 +329,8 @@
"claude-opus-4.6-fast.description": "Claude Opus 4.6は、エージェント構築やコーディングにおいてAnthropicの最も知的なモデルです。",
"claude-opus-4.6.description": "Claude Opus 4.6は、エージェント構築やコーディングにおいてAnthropicの最も知的なモデルです。",
"claude-sonnet-4-20250514-thinking.description": "Claude Sonnet 4 Thinkingは、即時応答または段階的な思考プロセスを可視化しながら出力できます。",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4はAnthropicのこれまでで最も知的なモデルで、APIユーザー向けに即時応答または詳細なステップバイステップ思考を提供し、きめ細かい制御が可能です。",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5はAnthropicのこれまでで最も知的なモデルです。",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4は、瞬時の応答や、プロセスを可視化した段階的な思考を提供できます。",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5はこれまでで最も知的なAnthropicモデルです。",
"claude-sonnet-4-5.description": "Claude Sonnet 4.5 by Anthropic — コーディング性能が向上した改良版Sonnet。",
"claude-sonnet-4-6.description": "Claude Sonnet 4.6 by Anthropic — 最新のSonnetモデルで、優れたコーディングとツール使用能力を備えています。",
"claude-sonnet-4.5.description": "Claude Sonnet 4.5は、これまでで最も知的なAnthropicのモデルです。",
@@ -404,7 +403,7 @@
"deepseek-ai/deepseek-llm-67b-chat.description": "DeepSeek LLM Chat67B)は、深い言語理解と対話能力を提供する革新的なモデルです。",
"deepseek-ai/deepseek-v3.1-terminus.description": "DeepSeek V3.1 は次世代の推論モデルで、複雑な推論と連想思考に優れ、深い分析タスクに対応します。",
"deepseek-ai/deepseek-v3.2.description": "DeepSeek V3.2は次世代推論モデルで、複雑な推論と連鎖的思考能力が強化されています。",
"deepseek-chat.description": "DeepSeek V4 Flash非思考モードの互換性エイリアス。廃止予定—代わりにDeepSeek V4 Flashを使用してください。",
"deepseek-chat.description": "一般的な対話能力とコーディング能力を組み合わせた新しいオープンソースモデルです。チャットモデルの一般的な対話能力と、コーダーモデルの強力なコーディング能力を保持し、より良い嗜好調整を実現しています。DeepSeek-V2.5は、文章作成や指示の追従能力も向上しています。",
"deepseek-coder-33B-instruct.description": "DeepSeek Coder 33B は 2T トークン(コード 87%、中英テキスト 13%)で学習されたコード言語モデルです。16K のコンテキストウィンドウと Fill-in-the-Middle タスクを導入し、プロジェクトレベルのコード補完とスニペット補完を提供します。",
"deepseek-coder-v2.description": "DeepSeek Coder V2 はオープンソースの MoE コードモデルで、コーディングタスクにおいて GPT-4 Turbo に匹敵する性能を発揮します。",
"deepseek-coder-v2:236b.description": "DeepSeek Coder V2 はオープンソースの MoE コードモデルで、コーディングタスクにおいて GPT-4 Turbo に匹敵する性能を発揮します。",
@@ -426,7 +425,7 @@
"deepseek-r1-fast-online.description": "DeepSeek R1 高速フルバージョンは、リアルタイムのウェブ検索を搭載し、671Bスケールの能力と高速応答を両立します。",
"deepseek-r1-online.description": "DeepSeek R1 フルバージョンは、671Bパラメータとリアルタイムのウェブ検索を備え、より強力な理解と生成を提供します。",
"deepseek-r1.description": "DeepSeek-R1は、強化学習前にコールドスタートデータを使用し、数学、コーディング、推論においてOpenAI-o1と同等の性能を発揮します。",
"deepseek-reasoner.description": "DeepSeek V4 Flash思考モードの互換性エイリアス。廃止予定—代わりにDeepSeek V4 Flashを使用してください。",
"deepseek-reasoner.description": "複雑な論理的推論タスクに特化したDeepSeek推論モデルです。",
"deepseek-v2.description": "DeepSeek V2は、コスト効率の高い処理を実現する効率的なMoEモデルです。",
"deepseek-v2:236b.description": "DeepSeek V2 236Bは、コード生成に特化したDeepSeekのモデルで、強力なコード生成能力を持ちます。",
"deepseek-v3-0324.description": "DeepSeek-V3-0324は、671BパラメータのMoEモデルで、プログラミングや技術的能力、文脈理解、長文処理において優れた性能を発揮します。",
@@ -491,8 +490,6 @@
"doubao-seedream-4-0-250828.description": "Seedream 4.0 は ByteDance Seed による画像生成モデルで、テキストと画像入力に対応し、高品質かつ制御性の高い画像生成を実現します。テキストプロンプトから画像を生成します。",
"doubao-seedream-4-5-251128.description": "Seedream 4.5はByteDanceの最新マルチモーダル画像モデルで、テキストから画像生成、画像間変換、バッチ画像生成機能を統合し、常識と推論能力を組み込んでいます。前バージョン4.0と比較して、生成品質が大幅に向上し、編集の一貫性や複数画像の融合が改善されています。視覚的な詳細の制御がより正確になり、小さなテキストや顔を自然に生成し、レイアウトや色彩の調和が向上し、全体的な美観が強化されています。",
"doubao-seedream-5-0-260128.description": "Doubao-Seedream-5.0-liteはByteDanceの最新画像生成モデルです。初めてオンライン検索機能を統合し、リアルタイムのウェブ情報を取り入れることで生成画像のタイムリー性を向上させています。モデルの知能もアップグレードされ、複雑な指示や視覚コンテンツを正確に解釈できるようになりました。また、専門的なシナリオでのグローバルな知識カバレッジ、一貫性、生成品質が向上し、企業レベルの視覚制作ニーズにより適合しています。",
"dreamina-seedance-2-0-260128.description": "ByteDanceのSeedance 2.0は、最も強力なビデオ生成モデルで、マルチモーダル参照ビデオ生成、ビデオ編集、ビデオ拡張、テキストからビデオ、画像からビデオへの同期音声付き生成をサポートします。",
"dreamina-seedance-2-0-fast-260128.description": "ByteDanceのSeedance 2.0 Fastは、Seedance 2.0と同じ機能を提供しながら、より高速な生成速度と競争力のある価格を実現します。",
"emohaa.description": "Emohaa は、専門的なカウンセリング能力を備えたメンタルヘルスモデルで、ユーザーが感情的な問題を理解するのを支援します。",
"ernie-4.5-0.3b.description": "ERNIE 4.5 0.3B は、ローカルおよびカスタマイズ展開に適した軽量なオープンソースモデルです。",
"ernie-4.5-8k-preview.description": "ERNIE 4.5 8K Preview は、ERNIE 4.5 の評価用に設計された 8K コンテキストプレビューモデルです。",
@@ -517,8 +514,7 @@
"ernie-x1-turbo-32k.description": "ERNIE X1 Turbo 32K は、複雑な推論やマルチターン対話に対応した 32K コンテキストの高速思考モデルです。",
"ernie-x1.1-preview.description": "ERNIE X1.1 Preview は、評価およびテスト用の思考モデルプレビューです。",
"ernie-x1.1.description": "ERNIE X1.1は評価とテスト用の思考モデルプレビューです。",
"fal-ai/bytedance/seedream/v4.5.description": "Seedream 4.5はByteDance Seedチームによって構築され、マルチ画像編集と構成をサポートします。被写体の一貫性の向上、正確な指示の遵守、空間論理の理解、美的表現、ポスターのレイアウトおよびロゴデザイン、高精度なテキスト画像レンダリングを特徴とします。",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0はByteDance Seedによって構築され、プロンプトからの高度に制御可能で高品質な画像生成をテキストおよび画像入力でサポートします。",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0は、ByteDance Seedによる画像生成モデルで、テキストと画像入力をサポートし、高度に制御可能で高品質な画像生成を実現します。テキストプロンプトから画像を生成します。",
"fal-ai/flux-kontext/dev.description": "FLUX.1 モデルは画像編集に特化しており、テキストと画像の入力に対応しています。",
"fal-ai/flux-pro/kontext.description": "FLUX.1 Kontext [pro] は、テキストと参照画像を入力として受け取り、局所的な編集や複雑なシーン全体の変換を可能にします。",
"fal-ai/flux/krea.description": "Flux Krea [dev] は、よりリアルで自然な画像を生成する美的バイアスを持つ画像生成モデルです。",
@@ -526,8 +522,8 @@
"fal-ai/hunyuan-image/v3.description": "強力なネイティブマルチモーダル画像生成モデルです。",
"fal-ai/imagen4/preview.description": "Google による高品質な画像生成モデルです。",
"fal-ai/nano-banana.description": "Nano Banana は Google による最新・最速・最も効率的なネイティブマルチモーダルモデルで、会話を通じた画像生成と編集が可能です。",
"fal-ai/qwen-image-edit.description": "Qwenチームによるプロフェッショナルな画像編集モデルで、意味的および外観の編集、正確な中国語/英語テキスト編集、スタイル転送、回転などをサポートします。",
"fal-ai/qwen-image.description": "Qwenチームによる強力な画像生成モデルで、中国語テキストレンダリング多様な視覚スタイルに優れています。",
"fal-ai/qwen-image-edit.description": "Qwenチームによるプロフェッショナルな画像編集モデルで、意味外観の編集をサポートし、中国語英語テキストを正確に編集できます。スタイル変換やオブジェクトの回転など、高品質な編集が可能です。",
"fal-ai/qwen-image.description": "Qwenチームによる強力な画像生成モデルで、中国語テキストレンダリング多様なビジュアルスタイルに優れています。",
"flux-1-schnell.description": "Black Forest Labs による 120 億パラメータのテキストから画像への変換モデルで、潜在敵対的拡散蒸留を用いて 1~4 ステップで高品質な画像を生成します。クローズドな代替モデルに匹敵し、Apache-2.0 ライセンスのもと、個人・研究・商用利用が可能です。",
"flux-dev.description": "非商用の研究開発向けに効率化されたオープンソース画像生成モデルです。",
"flux-kontext-max.description": "最先端のコンテキスト画像生成・編集モデルで、テキストと画像を組み合わせて精密かつ一貫性のある結果を生成します。",
@@ -566,10 +562,10 @@
"gemini-3-flash-preview.description": "Gemini 3 Flash は、最先端の知能と優れた検索基盤を融合し、スピードに特化した最もスマートなモデルです。",
"gemini-3-flash.description": "Gemini 3 Flash by Google — 超高速モデルでマルチモーダル入力をサポートします。",
"gemini-3-pro-image-preview.description": "Gemini 3 Pro ImageNano Banana Pro)は、Googleの画像生成モデルで、マルチモーダル対話もサポートします。",
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro)はGoogleの画像生成モデルで、マルチモーダルチャットもサポートします。",
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro ImageNano Banana Pro)は、Googleの画像生成モデルで、マルチモーダルチャットもサポートしています。",
"gemini-3-pro-preview.description": "Gemini 3 Pro は、Google による最も強力なエージェントおよびバイブコーディングモデルで、最先端の推論に加え、より豊かなビジュアルと深い対話を実現します。",
"gemini-3.1-flash-image-preview.description": "Gemini 3.1 Flash ImageNano Banana 2)は、Googleの最速のネイティブ画像生成モデルで、思考サポート、対話型画像生成および編集を提供します。",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2)は、プロレベルの画像品質をフラッシュ速度で提供し、マルチモーダルチャットをサポートします。",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash ImageNano Banana 2は、Googleの最速のネイティブ画像生成モデルで、思考サポート、会話型画像生成、編集を提供します。",
"gemini-3.1-flash-lite-preview.description": "Gemini 3.1 Flash-Lite PreviewはGoogleの最もコスト効率の高いマルチモーダルモデルで、大量のエージェントタスク、翻訳、データ処理に最適化されています。",
"gemini-3.1-flash-lite.description": "Gemini 3.1 Flash-LiteはGoogleの最もコスト効率の高いマルチモーダルモデルで、大量のエージェントタスク、翻訳、データ処理に最適化されています。",
"gemini-3.1-pro-preview.description": "Gemini 3.1 Pro Previewは、Gemini 3 Proの推論能力を強化し、中程度の思考レベルサポートを追加しています。",
@@ -734,8 +730,6 @@
"grok-4-fast-reasoning.description": "Grok 4 Fast をリリースしました。コスト効率の高い推論モデルにおける最新の進展です。",
"grok-4.20-0309-non-reasoning.description": "単純なユースケース向けの非推論バリアント。",
"grok-4.20-0309-reasoning.description": "応答前に推論する知的で超高速なモデル。",
"grok-4.20-beta-0309-non-reasoning.description": "単純なユースケース向けの非思考型バリアント",
"grok-4.20-beta-0309-reasoning.description": "応答前に推論する知的で超高速なモデル",
"grok-4.20-multi-agent-0309.description": "4または16のエージェントチーム。研究ユースケースに優れています。現在、クライアントサイドツールはサポートしていません。xAIサーバーサイドツール(例:X Search、Web Searchツール)およびリモートMCPツールのみをサポートします。",
"grok-4.3.description": "世界で最も真実を追求する大規模言語モデル",
"grok-4.description": "最新のGrokフラッグシップモデルで、言語、数学、推論において比類のない性能を発揮する真のオールラウンダーです。現在はgrok-4-0709を指しており、リソースの制限により一時的に公式価格より10%高く設定されていますが、後に公式価格に戻る予定です。",
@@ -1220,8 +1214,6 @@
"qwq.description": "QwQは、Qwenファミリーの推論モデルです。標準的な指示調整モデルと比較して、思考と推論能力に優れ、特に難解な問題において下流性能を大幅に向上させます。QwQ-32Bは、DeepSeek-R1やo1-miniと競合する中規模の推論モデルです。",
"qwq_32b.description": "Qwenファミリーの中規模推論モデル。標準的な指示調整モデルと比較して、QwQの思考と推論能力は、特に難解な問題において下流性能を大幅に向上させます。",
"r1-1776.description": "R1-1776は、DeepSeek R1のポストトレーニングバリアントで、検閲のない偏りのない事実情報を提供するよう設計されています。",
"seedance-1-5-pro-251215.description": "ByteDanceのSeedance 1.5 Proは、テキストからビデオ、画像からビデオ(最初のフレーム、最初+最後のフレーム)、視覚と同期した音声生成をサポートします。",
"seedream-5-0-260128.description": "BytePlusによるByteDance-Seedream-5.0-liteは、リアルタイム情報のためのウェブ検索強化生成、複雑なプロンプト解釈の向上、プロフェッショナルな視覚制作のための参照一貫性の改善を特徴とします。",
"solar-mini-ja.description": "Solar Mini (Ja)は、Solar Miniを日本語に特化させたモデルで、英語と韓国語でも効率的かつ高性能な動作を維持します。",
"solar-mini.description": "Solar Miniは、GPT-3.5を上回る性能を持つコンパクトなLLMで、英語と韓国語に対応した多言語機能を備え、効率的な小型ソリューションを提供します。",
"solar-pro.description": "Solar Proは、Upstageが提供する高知能LLMで、単一GPU上での指示追従に特化し、IFEvalスコア80以上を記録しています。現在は英語に対応しており、2024年11月の正式リリースでは対応言語とコンテキスト長が拡張される予定です。",
@@ -1233,7 +1225,9 @@
"sophnet/deepseek-v3.2.description": "DeepSeek V3.2は、高い計算効率と優れた推論およびエージェント性能のバランスを取ったモデルです。",
"sora-2-pro.description": "Sora 2 Proは、最先端の最も高度なメディア生成モデルで、音声と同期したビデオを生成します。自然言語または画像からリッチで詳細な動的クリップを作成できます。",
"sora-2.description": "Sora 2は、新しい強力なメディア生成モデルで、音声と同期したビデオを生成します。自然言語または画像からリッチで詳細な動的クリップを作成できます。",
"spark-x.description": "X2機能概要: 1. `thinking`フィールドを介して推論モードの動的調整を導入。2. コンテキスト長の拡張: 64K入力トークンと128K出力トークン。3. Function Call機能をサポート。",
"spark-x1.5.description": "X1.5の更新内容: (1) `thinking`フィールドで制御可能な動的思考モードを追加。 (2) 64K入力と64Kの出力を持つ拡張コンテキスト長。 (3) FunctionCallをサポート。",
"spark-x2-flash.description": "Spark X2-Flashは、30億の総パラメータを持つMoEMixture of Experts)アーキテクチャを採用し、最大256Kのコンテキストウィンドウをサポートします。エージェント能力とコーディング能力において大幅な改善を主張しており、Ascend 910B AIプロセッサのクラスターでトレーニングされています。",
"spark-x2.description": "X2の機能概要: 1. `thinking`フィールドを介して制御可能な推論モードの動的調整を導入。 2. 拡張されたコンテキスト長: 64Kの入力トークンと128Kの出力トークン。 3. Function Call機能をサポート。",
"stable-diffusion-3-medium.description": "Stability AI による最新のテキストから画像への変換モデルです。画像品質、テキスト理解、スタイルの多様性が大幅に向上し、複雑な自然言語プロンプトをより正確に解釈し、多様で精密な画像を生成します。",
"stable-diffusion-3.5-large-turbo.description": "Stable Diffusion 3.5 Large Turbo は高品質な画像生成に特化し、精密なディテール描写と高いシーン再現性を備えています。",
"stable-diffusion-xl-base-1.0.description": "Stability AI によるオープンソースのテキスト画像変換モデルで、業界最高水準の創造的画像生成を実現します。高度な指示理解と、精密な生成のための逆プロンプト定義に対応しています。",
@@ -1355,7 +1349,6 @@
"x-ai/grok-4.1-fast.description": "Grok 4.1 Fastは、xAIによる高スループット・低コストモデルで、2Mのコンテキストウィンドウをサポートし、高並列性および長文コンテキストのユースケースに最適です。",
"x-ai/grok-4.description": "Grok 4は、xAIのフラッグシップ推論モデルで、強力な推論力とマルチモーダル対応を備えています。",
"x-ai/grok-code-fast-1.description": "Grok Code Fast 1は、xAIによる高速コードモデルで、読みやすくエンジニアに優しい出力を提供します。",
"x1.description": "X1.5の更新内容: (1) `thinking`フィールドで制御される動的思考モードを追加。 (2) 64K入力と64K出力のより大きなコンテキスト長。 (3) FunctionCallをサポート。",
"xai/grok-2-vision.description": "Grok 2 Visionは視覚タスクに優れ、MathVistaによる視覚的数学推論やDocVQAによる文書QAで最先端の性能を発揮します。文書、チャート、グラフ、スクリーンショット、写真を処理可能です。",
"xai/grok-2.description": "Grok 2は、最先端の推論力、優れたチャット、コーディング、推論性能を備えた先進モデルで、LMSYSにおいてClaude 3.5 SonnetやGPT-4 Turboを上回る評価を得ています。",
"xai/grok-3-fast.description": "xAIのフラッグシップモデルで、データ抽出、コーディング、要約などのエンタープライズ用途に優れ、金融、医療、法律、科学分野における深い専門知識を備えています。高速バリアントは高速インフラ上で動作し、より迅速な応答を提供します(トークン単価は高め)。",
+21 -21
View File
@@ -69,9 +69,22 @@
"builtins.lobe-agent-management.render.installPlugin.plugin": "プラグイン",
"builtins.lobe-agent-management.render.installPlugin.success": "インストールが完了しました",
"builtins.lobe-agent-management.title": "エージェントマネージャー",
"builtins.lobe-agent-marketplace.apiName.showAgentMarketplace": "エージェントマーケットプレイスを開く",
"builtins.lobe-agent-marketplace.apiName.submitAgentPick": "エージェントの選択を提出する",
"builtins.lobe-agent-marketplace.title": "エージェントマーケットプレイス",
"builtins.lobe-agent.apiName.callSubAgent": "サブエージェントを呼び出す",
"builtins.lobe-agent.apiName.callSubAgent.completed": "サブエージェントが派遣されました: ",
"builtins.lobe-agent.apiName.callSubAgent.loading": "サブエージェントを派遣中: ",
"builtins.lobe-agent.apiName.callSubAgents": "サブエージェントを呼び出す",
"builtins.lobe-agent.apiName.clearTodos": "ToDoをクリア",
"builtins.lobe-agent.apiName.clearTodos.modeAll": "すべて",
"builtins.lobe-agent.apiName.clearTodos.modeCompleted": "完了済み",
"builtins.lobe-agent.apiName.clearTodos.result": "<mode>{{mode}}</mode> のToDoをクリア",
"builtins.lobe-agent.apiName.createPlan": "計画を作成",
"builtins.lobe-agent.apiName.createPlan.result": "計画を作成: <goal>{{goal}}</goal>",
"builtins.lobe-agent.apiName.createTodos": "ToDoを作成",
"builtins.lobe-agent.apiName.updatePlan": "計画を更新",
"builtins.lobe-agent.apiName.updatePlan.completed": "完了済み",
"builtins.lobe-agent.apiName.updatePlan.modified": "変更済み",
"builtins.lobe-agent.apiName.updateTodos": "ToDoを更新",
"builtins.lobe-agent.title": "ローブエージェント",
"builtins.lobe-claude-code.agent.instruction": "指示",
"builtins.lobe-claude-code.agent.result": "結果",
"builtins.lobe-claude-code.todoWrite.allDone": "すべてのタスクが完了しました",
@@ -139,24 +152,6 @@
"builtins.lobe-group-management.inspector.executeAgentTasks.title": "タスクの割り当て先:",
"builtins.lobe-group-management.inspector.speak.title": "指定されたエージェントが話します:",
"builtins.lobe-group-management.title": "チームの調整",
"builtins.lobe-gtd.apiName.clearTodos": "ToDoをクリア",
"builtins.lobe-gtd.apiName.clearTodos.modeAll": "すべて",
"builtins.lobe-gtd.apiName.clearTodos.modeCompleted": "完了済み",
"builtins.lobe-gtd.apiName.clearTodos.result": "<mode>{{mode}}</mode> のToDoをクリア",
"builtins.lobe-gtd.apiName.completeTodos": "ToDoを完了",
"builtins.lobe-gtd.apiName.createPlan": "プランを作成",
"builtins.lobe-gtd.apiName.createPlan.result": "プランを作成:<goal>{{goal}}</goal>",
"builtins.lobe-gtd.apiName.createTodos": "ToDoを作成",
"builtins.lobe-gtd.apiName.execTask": "タスクを実行",
"builtins.lobe-gtd.apiName.execTask.completed": "タスクが作成されました:",
"builtins.lobe-gtd.apiName.execTask.loading": "タスクを作成中:",
"builtins.lobe-gtd.apiName.execTasks": "タスクを実行",
"builtins.lobe-gtd.apiName.removeTodos": "ToDoを削除",
"builtins.lobe-gtd.apiName.updatePlan": "プランを更新",
"builtins.lobe-gtd.apiName.updatePlan.completed": "完了",
"builtins.lobe-gtd.apiName.updatePlan.modified": "変更済み",
"builtins.lobe-gtd.apiName.updateTodos": "ToDoを更新",
"builtins.lobe-gtd.title": "GTDツール",
"builtins.lobe-knowledge-base.apiName.readKnowledge": "ナレッジベースの内容を読み取る",
"builtins.lobe-knowledge-base.apiName.searchKnowledgeBase": "ナレッジベースを検索する",
"builtins.lobe-knowledge-base.inspector.andMoreFiles": "さらに{{count}}件",
@@ -317,6 +312,8 @@
"builtins.lobe-web-onboarding.apiName.finishOnboarding": "オンボーディングを完了",
"builtins.lobe-web-onboarding.apiName.readDocument": "ドキュメントを読む",
"builtins.lobe-web-onboarding.apiName.saveUserQuestion": "ユーザーの質問を保存",
"builtins.lobe-web-onboarding.apiName.showAgentMarketplace": "エージェントチームを編成",
"builtins.lobe-web-onboarding.apiName.submitAgentPick": "エージェント選択を送信",
"builtins.lobe-web-onboarding.apiName.updateDocument": "ドキュメントを更新",
"builtins.lobe-web-onboarding.apiName.writeDocument": "ドキュメントを作成",
"builtins.lobe-web-onboarding.docType.persona": "ユーザーペルソナ",
@@ -327,6 +324,9 @@
"builtins.lobe-web-onboarding.inspector.hunkCount_other": "{{count}} 変更",
"builtins.lobe-web-onboarding.inspector.interests_one": "{{count}} 興味",
"builtins.lobe-web-onboarding.inspector.interests_other": "{{count}} 興味",
"builtins.lobe-web-onboarding.render.agent": "エージェント",
"builtins.lobe-web-onboarding.render.fullName": "フルネーム",
"builtins.lobe-web-onboarding.render.interests": "興味",
"builtins.lobe-web-onboarding.title": "ユーザーオンボーディング",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.delete": "削除",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.deleteLines": "行を削除",
-1
View File
@@ -33,7 +33,6 @@
"jina.description": "Jina AIは2020年に設立された検索AIのリーディングカンパニーで、ベクトルモデル、リランカー、小型言語モデルを含む検索スタックにより、高品質な生成・マルチモーダル検索アプリを構築できます。",
"kimicodingplan.description": "Moonshot AIのKimi Codeは、K2.5を含むKimiモデルへのアクセスを提供します。",
"lmstudio.description": "LM Studioは、ローカルPC上でLLMの開発と実験ができるデスクトップアプリです。",
"lobehub.description": "LobeHub Cloudは公式APIを使用してAIモデルにアクセスし、モデルトークンに紐づいたクレジットで使用量を測定します。",
"longcat.description": "LongCatは、Meituanが独自に開発した生成AIの大型モデルシリーズです。効率的な計算アーキテクチャと強力なマルチモーダル機能を通じて、企業内部の生産性を向上させ、革新的なアプリケーションを可能にすることを目的としています。",
"minimax.description": "MiniMaxは2021年に設立され、マルチモーダル基盤モデルを用いた汎用AIを開発しています。兆単位パラメータのMoEテキストモデル、音声モデル、ビジョンモデル、Hailuo AIなどのアプリを提供します。",
"minimaxcodingplan.description": "MiniMaxトークンプランは、固定料金のサブスクリプションを通じてM2.7を含むMiniMaxモデルへのアクセスを提供します。",
-2
View File
@@ -913,8 +913,6 @@
"tools.builtins.lobe-agent-documents.title": "ドキュメント",
"tools.builtins.lobe-agent-management.description": "AI エージェントの作成、管理、オーケストレーションを行います",
"tools.builtins.lobe-agent-management.title": "エージェント管理",
"tools.builtins.lobe-agent-marketplace.description": "ユーザーに厳選されたエージェントマーケットプレイスカードを表示し、選択したテンプレートを記録します。",
"tools.builtins.lobe-agent-marketplace.title": "エージェントマーケットプレイス",
"tools.builtins.lobe-artifacts.description": "インタラクティブなUIコンポーネント、データ可視化、チャート、SVGグラフィック、Webアプリケーションを生成し、リアルタイムでプレビューします。ユーザーが直接操作できるリッチなビジュアルコンテンツを作成します。",
"tools.builtins.lobe-artifacts.readme": "インタラクティブなUIコンポーネント、データビジュアライゼーション、チャート、SVGグラフィック、Webアプリケーションを生成し、リアルタイムでプレビューできます。ユーザーが直接操作できるリッチなビジュアルコンテンツを作成しましょう。",
"tools.builtins.lobe-artifacts.title": "アーティファクト",
+45 -45
View File
@@ -56,51 +56,51 @@
"dalle.generating": "生成中...",
"dalle.images": "画像:",
"dalle.prompt": "プロンプト",
"lobe-gtd.actions.add": "追加",
"lobe-gtd.actions.clearCompleted": "完了済みを削除",
"lobe-gtd.actions.placeholder": "タスクを入力してください...",
"lobe-gtd.addTodo.placeholder": "ToDo項目を追加...",
"lobe-gtd.clearTodos.cleared": "{{count}} 件のタスクを削除しました",
"lobe-gtd.clearTodos.clearedCompleted": "{{count}} 件の完了済みタスクを削除しました",
"lobe-gtd.clearTodos.clearedCompleted_one": "{{count}} 件の完了済みタスクを削除しました",
"lobe-gtd.clearTodos.clearedCompleted_other": "{{count}} 件の完了済みタスクを削除しました",
"lobe-gtd.clearTodos.cleared_one": "{{count}} 件のタスクを削除しました",
"lobe-gtd.clearTodos.cleared_other": "{{count}} 件のタスクを削除しました",
"lobe-gtd.clearTodos.header": "ToDo項目のクリア",
"lobe-gtd.clearTodos.label": "クリアする内容を選択してください",
"lobe-gtd.clearTodos.noItems": "削除するタスクがありません",
"lobe-gtd.clearTodos.option.all": "すべての項目をクリア(保留中含む)",
"lobe-gtd.clearTodos.option.completed": "完了した項目のみをクリア",
"lobe-gtd.clearTodos.remaining": "残り {{count}} 件のタスク",
"lobe-gtd.clearTodos.remaining_one": "残り {{count}} 件のタスク",
"lobe-gtd.clearTodos.remaining_other": "残り {{count}} 件のタスク",
"lobe-gtd.completeTodos.completed": "{{count}} 件のタスクを完了しました",
"lobe-gtd.completeTodos.completed_one": "{{count}} 件のタスクを完了しました",
"lobe-gtd.completeTodos.completed_other": "{{count}} 件のタスクを完了しました",
"lobe-gtd.createPlan.context.label": "コンテキスト(任意)",
"lobe-gtd.createPlan.context.placeholder": "背景、制約、考慮事項など...",
"lobe-gtd.createPlan.description.label": "説明",
"lobe-gtd.createPlan.description.placeholder": "計画の簡単な概要",
"lobe-gtd.createPlan.goal.label": "目標",
"lobe-gtd.createPlan.goal.placeholder": "達成したいことは何ですか?",
"lobe-gtd.createTodos.created": "{{count}} 件のタスクを作成しました",
"lobe-gtd.createTodos.created_one": "{{count}} 件のタスクを作成しました",
"lobe-gtd.createTodos.created_other": "{{count}} 件のタスクを作成しました",
"lobe-gtd.createTodos.total": "合計 {{count}} 件のタスク",
"lobe-gtd.createTodos.total_one": "合計 {{count}} 件のタスク",
"lobe-gtd.createTodos.total_other": "合計 {{count}} 件のタスク",
"lobe-gtd.removeTodos.removed": "{{count}} 件のタスクを削除しました",
"lobe-gtd.removeTodos.removed_one": "{{count}} 件のタスクを削除しました",
"lobe-gtd.removeTodos.removed_other": "{{count}} 件のタスクを削除しました",
"lobe-gtd.status.done": "{{count}} 件完了",
"lobe-gtd.status.pending": "{{count}} 件保留中",
"lobe-gtd.todoItem.placeholder": "ToDo項目を入力...",
"lobe-gtd.todoList.empty": "タスクリストは空です",
"lobe-gtd.todoList.items": "{{count}} 件のタスク",
"lobe-gtd.todoList.items_one": "{{count}} 件のタスク",
"lobe-gtd.todoList.items_other": "{{count}} 件のタスク",
"lobe-gtd.todoList.title": "タスクリスト",
"lobe-gtd.updateTodos.updated": "タスクリストを更新しました",
"lobe-agent.actions.add": "追加",
"lobe-agent.actions.clearCompleted": "完了した項目をクリア",
"lobe-agent.actions.placeholder": "やることを入力してください...",
"lobe-agent.addTodo.placeholder": "やることを追加してください...",
"lobe-agent.clearTodos.cleared": "{{count}} 件の項目をクリアしました",
"lobe-agent.clearTodos.clearedCompleted": "{{count}} 件の完了した項目をクリアしました",
"lobe-agent.clearTodos.clearedCompleted_one": "{{count}} 件の完了した項目をクリアしました",
"lobe-agent.clearTodos.clearedCompleted_other": "{{count}} 件の完了した項目をクリアしました",
"lobe-agent.clearTodos.cleared_one": "{{count}} 件の項目をクリアしました",
"lobe-agent.clearTodos.cleared_other": "{{count}} 件の項目をクリアしました",
"lobe-agent.clearTodos.header": "やることをクリア",
"lobe-agent.clearTodos.label": "クリアする項目を選択してください:",
"lobe-agent.clearTodos.noItems": "クリアする項目がありません",
"lobe-agent.clearTodos.option.all": "すべての項目をクリア(保留中の項目を含む)",
"lobe-agent.clearTodos.option.completed": "完了した項目のみをクリア",
"lobe-agent.clearTodos.remaining": "残り {{count}} 件の項目",
"lobe-agent.clearTodos.remaining_one": "残り {{count}} 件の項目",
"lobe-agent.clearTodos.remaining_other": "残り {{count}} 件の項目",
"lobe-agent.completeTodos.completed": "{{count}} 件の項目を完了しました",
"lobe-agent.completeTodos.completed_one": "{{count}} 件の項目を完了しました",
"lobe-agent.completeTodos.completed_other": "{{count}} 件の項目を完了しました",
"lobe-agent.createPlan.context.label": "コンテキスト(任意)",
"lobe-agent.createPlan.context.placeholder": "背景、制約、考慮事項など...",
"lobe-agent.createPlan.description.label": "説明",
"lobe-agent.createPlan.description.placeholder": "計画の簡単な概要",
"lobe-agent.createPlan.goal.label": "目標",
"lobe-agent.createPlan.goal.placeholder": "達成したいことは何ですか?",
"lobe-agent.createTodos.created": "{{count}} 件のやることを作成しました",
"lobe-agent.createTodos.created_one": "{{count}} 件のやることを作成しました",
"lobe-agent.createTodos.created_other": "{{count}} 件のやることを作成しました",
"lobe-agent.createTodos.total": "合計: {{count}} 件",
"lobe-agent.createTodos.total_one": "合計: {{count}} 件",
"lobe-agent.createTodos.total_other": "合計: {{count}} 件",
"lobe-agent.removeTodos.removed": "{{count}} 件の項目を削除しました",
"lobe-agent.removeTodos.removed_one": "{{count}} 件の項目を削除しました",
"lobe-agent.removeTodos.removed_other": "{{count}} 件の項目を削除しました",
"lobe-agent.status.done": "{{count}} 件完了",
"lobe-agent.status.pending": "{{count}} 件保留中",
"lobe-agent.todoItem.placeholder": "やることを入力してください...",
"lobe-agent.todoList.empty": "やることリストは空です",
"lobe-agent.todoList.items": "{{count}} 件の項目",
"lobe-agent.todoList.items_one": "{{count}} 件の項目",
"lobe-agent.todoList.items_other": "{{count}} 件の項目",
"lobe-agent.todoList.title": "やることリスト",
"lobe-agent.updateTodos.updated": "やることリストを更新しました",
"lobe-knowledge-base.readKnowledge.meta.chars": "文字数",
"lobe-knowledge-base.readKnowledge.meta.lines": "行数",
"localFiles.editFile.newString": "置換後の文字列",
+4
View File
@@ -115,6 +115,10 @@
"channel.line.fetchBotInfoMissingToken": "먼저 채널 액세스 토큰을 입력한 후 \"LINE에서 가져오기\"를 클릭하세요.",
"channel.line.fetchBotInfoSuccess": "대상 사용자 ID를 가져왔습니다",
"channel.line.webhookManualSetup": "LINE은 프로그래밍 방식의 웹훅 등록을 허용하지 않습니다. 이 URL을 LINE Developers Console (메시징 API → 웹훅 URL)에 복사한 후 \"확인\"을 클릭하고 \"웹훅 사용\"을 활성화하세요.",
"channel.messengerPromo.action": "메신저 사용해보기",
"channel.messengerPromo.desc": "봇 설정 없이 LobeHub와 Slack, Discord, Telegram에서 채팅하세요.",
"channel.messengerPromo.dismiss": "닫기",
"channel.messengerPromo.title": "설정을 건너뛰세요",
"channel.openPlatform": "오픈 플랫폼",
"channel.platforms": "플랫폼",
"channel.publicKey": "공개 키",
+4 -3
View File
@@ -314,7 +314,7 @@
"openInNewWindow": "새 창에서 열기",
"operation.contextCompression": "컨텍스트가 너무 길어 기록을 압축합니다...",
"operation.execAgentRuntime": "응답 준비 중",
"operation.execClientTask": "작업 실행 중",
"operation.execClientSubAgent": "하위 에이전트 실행 중",
"operation.execHeterogeneousAgent": "{{name}} 실행 중",
"operation.execServerAgentRuntime": "실행 중… 다른 작업으로 이동하거나 페이지를 닫아도 작업은 계속 진행됩니다.",
"operation.heterogeneousAgentFallback": "외부 에이전트",
@@ -567,6 +567,7 @@
"taskList.contextMenu.copyLink": "링크 복사",
"taskList.contextMenu.copyLinkSuccess": "링크가 복사되었습니다",
"taskList.contextMenu.priority": "우선순위",
"taskList.contextMenu.runNow": "지금 실행",
"taskList.contextMenu.status": "상태",
"taskList.empty": "작업이 없습니다",
"taskList.emptyHero.greeting": "오늘 무엇을 해결해볼까요?",
@@ -771,6 +772,8 @@
"workflow.toolDisplayName.addPreferenceMemory": "저장된 메모리",
"workflow.toolDisplayName.calculate": "계산됨",
"workflow.toolDisplayName.callAgent": "에이전트를 호출했습니다",
"workflow.toolDisplayName.callSubAgent": "하위 에이전트가 디스패치되었습니다",
"workflow.toolDisplayName.callSubAgents": "하위 에이전트들이 디스패치되었습니다",
"workflow.toolDisplayName.clearTodos": "할 일 목록이 삭제되었습니다",
"workflow.toolDisplayName.copyDocument": "문서를 복사했습니다",
"workflow.toolDisplayName.crawlMultiPages": "크롤링된 페이지",
@@ -785,8 +788,6 @@
"workflow.toolDisplayName.editTitle": "수정된 제목",
"workflow.toolDisplayName.evaluate": "평가된 표현식",
"workflow.toolDisplayName.execScript": "스크립트를 실행했습니다",
"workflow.toolDisplayName.execTask": "작업을 실행했습니다",
"workflow.toolDisplayName.execTasks": "실행된 작업",
"workflow.toolDisplayName.execute": "계산 실행됨",
"workflow.toolDisplayName.executeCode": "코드 실행됨",
"workflow.toolDisplayName.finishOnboarding": "온보딩 완료",
+2
View File
@@ -349,6 +349,8 @@
"loading": "로딩 중…",
"mail.business": "비즈니스 제휴",
"mail.support": "이메일 지원",
"messengerBanner.dismiss": "닫기",
"messengerBanner.title": "선호하는 메시징 앱에서 Lobe AI와 대화하세요",
"more": "더보기",
"navPanel.agent": "도우미",
"navPanel.customizeSidebar": "사이드바 사용자 지정",
-1
View File
@@ -35,7 +35,6 @@
"messenger.linkModal.notConfigured": "현재 이 연결을 사용할 수 없습니다. 나중에 다시 시도하세요.",
"messenger.linkModal.openCta": "{{platform}}에서 열기",
"messenger.linkModal.scanHint": "또는 휴대폰으로 스캔하여 {{platform}}을(를) 여세요.",
"messenger.linkModal.title": "메신저 연결",
"messenger.list.discord.description": "LobeHub 봇과 DM을 통해 Discord 서버에서 LobeHub 에이전트와 채팅하세요.",
"messenger.list.slack.description": "Slack 워크스페이스에서 DM 또는 @LobeHub를 통해 LobeHub 에이전트와 채팅하세요.",
"messenger.list.telegram.description": "Telegram에서 LobeHub 에이전트와 채팅하고 어디서든 응답할 에이전트를 선택하세요.",
+15 -22
View File
@@ -106,7 +106,6 @@
"MiniMax-Hailuo-2.3.description": "신규 비디오 생성 모델로 신체 움직임, 물리적 사실성, 지침 준수에서 전반적인 업그레이드 제공.",
"MiniMax-M1.description": "80K 체인 오브 싱킹과 100만 입력을 지원하는 새로운 자체 개발 추론 모델로, 세계 최고 수준의 모델과 유사한 성능을 제공합니다.",
"MiniMax-M2-Stable.description": "상업적 사용을 위한 높은 동시성을 제공하며, 효율적인 코딩 및 에이전트 워크플로우에 최적화되어 있습니다.",
"MiniMax-M2.1-Lightning.description": "강력한 다국어 프로그래밍 기능과 더 빠르고 효율적인 추론을 제공합니다.",
"MiniMax-M2.1-highspeed.description": "강력한 다국어 프로그래밍 기능과 종합적으로 업그레이드된 프로그래밍 경험. 더 빠르고 효율적입니다.",
"MiniMax-M2.1.description": "MiniMax-M2.1은 MiniMax에서 개발한 대표적인 오픈소스 대형 모델로, 복잡한 실제 과제를 해결하는 데 중점을 둡니다. 다국어 프로그래밍 능력과 에이전트로서 복잡한 작업을 수행하는 능력이 핵심 강점입니다.",
"MiniMax-M2.5-highspeed.description": "MiniMax M2.5 Highspeed: M2.5와 동일한 성능을 제공하며 추론 속도가 더 빠릅니다.",
@@ -315,13 +314,13 @@
"claude-3-haiku-20240307.description": "Claude 3 Haiku는 Anthropic의 가장 빠르고 컴팩트한 모델로, 빠르고 정확한 성능으로 즉각적인 응답을 위해 설계되었습니다.",
"claude-3-opus-20240229.description": "Claude 3 Opus는 Anthropic의 가장 강력한 모델로, 고난도 작업에서 뛰어난 성능, 지능, 유창성, 이해력을 자랑합니다.",
"claude-3-sonnet-20240229.description": "Claude 3 Sonnet은 엔터프라이즈 워크로드를 위한 지능과 속도의 균형을 제공하며, 낮은 비용으로 높은 효용성과 안정적인 대규모 배포를 지원합니다.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5는 Anthropic의 가장 빠르고 지능적인 Haiku 모델로, 번개 같은 속도와 확장된 사고 능력을 제공합니다.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5는 Anthropic의 가장 빠르고 스마트한 Haiku 모델로, 번개 같은 속도와 확장된 추론 능력을 제공합니다.",
"claude-haiku-4-5.description": "Anthropic의 Claude Haiku 4.5 — 향상된 추론 및 비전을 갖춘 차세대 Haiku.",
"claude-haiku-4.5.description": "Claude Haiku 4.5는 Anthropic의 가장 빠르고 똑똑한 Haiku 모델로, 번개 같은 속도와 확장된 추론 능력을 자랑합니다.",
"claude-opus-4-1-20250805-thinking.description": "Claude Opus 4.1 Thinking은 자신의 추론 과정을 드러낼 수 있는 고급 변형 모델입니다.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1은 Anthropic의 최신 모델로, 매우 복잡한 작업에서 뛰어난 성능, 지능, 유창성 및 이해력을 자랑합니다.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1은 Anthropic의 최신 모델로, 매우 복잡한 작업에서 뛰어난 성능, 지능, 유창함, 이해력을 자랑합니다.",
"claude-opus-4-1.description": "Anthropic의 Claude Opus 4.1 — 심층 분석 기능을 갖춘 프리미엄 추론 모델.",
"claude-opus-4-20250514.description": "Claude Opus 4는 Anthropic의 가장 강력한 모델로, 매우 복잡한 작업에서 뛰어난 성능, 지능, 유창성 및 이해력을 자랑합니다.",
"claude-opus-4-20250514.description": "Claude Opus 4는 Anthropic의 가장 강력한 모델로, 매우 복잡한 작업에서 뛰어난 성능, 지능, 유창함, 이해력을 제공합니다.",
"claude-opus-4-5-20251101.description": "Claude Opus 4.5는 Anthropic의 플래그십 모델로, 탁월한 지능과 확장 가능한 성능을 결합하여 최고 품질의 응답과 추론이 필요한 복잡한 작업에 이상적입니다.",
"claude-opus-4-5.description": "Anthropic의 Claude Opus 4.5 — 최고 수준의 추론 및 코딩을 갖춘 플래그십 모델.",
"claude-opus-4-6.description": "Anthropic의 Claude Opus 4.6 — 고급 추론을 갖춘 1M 컨텍스트 윈도우 플래그십.",
@@ -330,8 +329,8 @@
"claude-opus-4.6-fast.description": "Claude Opus 4.6은 에이전트 구축과 코딩을 위한 Anthropic의 가장 지능적인 모델입니다.",
"claude-opus-4.6.description": "Claude Opus 4.6은 에이전트 구축과 코딩을 위한 Anthropic의 가장 지능적인 모델입니다.",
"claude-sonnet-4-20250514-thinking.description": "Claude Sonnet 4 Thinking은 즉각적인 응답 또는 단계별 사고 과정을 시각적으로 보여주는 확장된 사고를 생성할 수 있습니다.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4는 Anthropic의 가장 지능적인 모델로, API 사용자에게 세밀한 제어를 제공하며 즉각적인 응답 또는 단계별 사고를 제공합니다.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5는 Anthropic의 가장 지능적인 모델입니다.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4는 거의 즉각적인 응답을 생성하거나 가시적인 과정을 통해 단계별 사고를 확장할 수 있습니다.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5는 Anthropic의 현재까지 가장 지능적인 모델입니다.",
"claude-sonnet-4-5.description": "Anthropic의 Claude Sonnet 4.5 — 향상된 코딩 성능을 갖춘 개선된 Sonnet.",
"claude-sonnet-4-6.description": "Anthropic의 Claude Sonnet 4.6 — 우수한 코딩 및 도구 사용을 갖춘 최신 Sonnet.",
"claude-sonnet-4.5.description": "Claude Sonnet 4.5는 지금까지의 Anthropic 모델 중 가장 지능적인 모델입니다.",
@@ -404,7 +403,7 @@
"deepseek-ai/deepseek-llm-67b-chat.description": "DeepSeek LLM Chat (67B)은 심층 언어 이해와 상호작용을 제공하는 혁신적인 모델입니다.",
"deepseek-ai/deepseek-v3.1-terminus.description": "DeepSeek V3.1은 복잡한 추론과 연쇄적 사고(chain-of-thought)에 강한 차세대 추론 모델로, 심층 분석 작업에 적합합니다.",
"deepseek-ai/deepseek-v3.2.description": "DeepSeek V3.2는 복잡한 추론과 연쇄 사고 능력이 강화된 차세대 추론 모델입니다.",
"deepseek-chat.description": "DeepSeek V4 Flash 비사고 모드의 호환성 별칭입니다. 사용 중단 예정 — 대신 DeepSeek V4 Flash를 사용하세요.",
"deepseek-chat.description": "일반 대화 능력과 코드 능력을 결합한 새로운 오픈소스 모델입니다. 이 모델은 대화 모델의 일반적인 대화 능력과 코더 모델의 강력한 코딩 능력을 유지하며, 선호도 정렬을 개선했습니다. DeepSeek-V2.5는 글쓰기와 지침 준수 능력도 향상시켰습니다.",
"deepseek-coder-33B-instruct.description": "DeepSeek Coder 33B는 2T 토큰(코드 87%, 중/영문 텍스트 13%)으로 학습된 코드 언어 모델입니다. 16K 문맥 창과 중간 채우기(fit-in-the-middle) 작업을 도입하여 프로젝트 수준의 코드 완성과 코드 조각 보완을 지원합니다.",
"deepseek-coder-v2.description": "DeepSeek Coder V2는 GPT-4 Turbo에 필적하는 성능을 보이는 오픈소스 MoE 코드 모델입니다.",
"deepseek-coder-v2:236b.description": "DeepSeek Coder V2는 GPT-4 Turbo에 필적하는 성능을 보이는 오픈소스 MoE 코드 모델입니다.",
@@ -426,7 +425,7 @@
"deepseek-r1-fast-online.description": "DeepSeek R1의 빠른 전체 버전으로, 실시간 웹 검색을 지원하며 671B 규모의 성능과 빠른 응답을 결합합니다.",
"deepseek-r1-online.description": "DeepSeek R1 전체 버전은 671B 파라미터와 실시간 웹 검색을 지원하여 더 강력한 이해 및 생성 능력을 제공합니다.",
"deepseek-r1.description": "DeepSeek-R1은 강화 학습 전 콜드 스타트 데이터를 사용하며, 수학, 코딩, 추론에서 OpenAI-o1과 유사한 성능을 보입니다.",
"deepseek-reasoner.description": "DeepSeek V4 Flash 사고 모드의 호환성 별칭입니다. 사용 중단 예정 — 대신 DeepSeek V4 Flash를 사용하세요.",
"deepseek-reasoner.description": "복잡한 논리적 추론 작업에 초점을 맞춘 DeepSeek 추론 모델입니다.",
"deepseek-v2.description": "DeepSeek V2는 비용 효율적인 처리를 위한 고효율 MoE 모델입니다.",
"deepseek-v2:236b.description": "DeepSeek V2 236B는 코드 생성에 강점을 가진 DeepSeek의 코드 특화 모델입니다.",
"deepseek-v3-0324.description": "DeepSeek-V3-0324는 671B 파라미터의 MoE 모델로, 프로그래밍 및 기술 역량, 문맥 이해, 장문 처리에서 뛰어난 성능을 보입니다.",
@@ -491,8 +490,6 @@
"doubao-seedream-4-0-250828.description": "Seedream 4.0은 ByteDance Seed의 이미지 생성 모델로, 텍스트 및 이미지 입력을 지원하며, 고품질의 이미지 생성과 높은 제어력을 제공합니다. 텍스트 프롬프트로부터 이미지를 생성합니다.",
"doubao-seedream-4-5-251128.description": "Seedream 4.5는 ByteDance의 최신 멀티모달 이미지 모델로, 텍스트-이미지, 이미지-이미지, 배치 이미지 생성 기능을 통합하며 상식과 추론 능력을 포함합니다. 이전 4.0 버전에 비해 생성 품질이 크게 향상되었으며, 편집 일관성과 다중 이미지 융합이 개선되었습니다. 시각적 세부 사항에 대한 더 정밀한 제어를 제공하며, 작은 텍스트와 작은 얼굴을 더 자연스럽게 생성하고 레이아웃과 색상이 더 조화롭게 되어 전체적인 미학을 향상시킵니다.",
"doubao-seedream-5-0-260128.description": "Doubao-Seedream-5.0-lite는 ByteDance의 최신 이미지 생성 모델로, 처음으로 온라인 검색 기능을 통합하여 실시간 웹 정보를 포함하고 생성된 이미지의 시의성을 향상시킵니다. 모델의 지능도 업그레이드되어 복잡한 지시와 시각적 콘텐츠를 정확히 해석할 수 있습니다. 또한 전문적인 시나리오에서 글로벌 지식 범위, 참조 일관성, 생성 품질이 개선되어 기업 수준의 시각적 창작 요구를 더 잘 충족시킵니다.",
"dreamina-seedance-2-0-260128.description": "ByteDance의 Seedance 2.0은 가장 강력한 비디오 생성 모델로, 멀티모달 참조 비디오 생성, 비디오 편집, 비디오 확장, 텍스트-비디오 및 이미지-비디오를 동기화된 오디오와 함께 지원합니다.",
"dreamina-seedance-2-0-fast-260128.description": "ByteDance의 Seedance 2.0 Fast는 Seedance 2.0과 동일한 기능을 제공하며, 더 빠른 생성 속도와 경쟁력 있는 가격을 자랑합니다.",
"emohaa.description": "Emohaa는 전문 상담 능력을 갖춘 정신 건강 모델로, 사용자가 감정 문제를 이해하도록 돕습니다.",
"ernie-4.5-0.3b.description": "ERNIE 4.5 0.3B는 로컬 및 맞춤형 배포를 위한 오픈소스 경량 모델입니다.",
"ernie-4.5-8k-preview.description": "ERNIE 4.5 8K Preview는 ERNIE 4.5의 8K 컨텍스트 프리뷰 모델로, 평가용으로 사용됩니다.",
@@ -517,8 +514,7 @@
"ernie-x1-turbo-32k.description": "ERNIE X1 Turbo 32K는 복잡한 추론 및 다중 턴 대화를 위한 32K 컨텍스트의 고속 사고 모델입니다.",
"ernie-x1.1-preview.description": "ERNIE X1.1 Preview는 평가 및 테스트를 위한 사고 모델 프리뷰입니다.",
"ernie-x1.1.description": "ERNIE X1.1은 평가 및 테스트를 위한 사고 모델 프리뷰입니다.",
"fal-ai/bytedance/seedream/v4.5.description": "ByteDance Seed 팀이 개발한 Seedream 4.5는 다중 이미지 편집 및 구성 기능을 지원합니다. 향상된 주제 일관성, 정확한 지침 준수, 공간 논리 이해, 미적 표현, 포스터 레이아웃 및 로고 디자인과 고정밀 텍스트-이미지 렌더링을 제공합니다.",
"fal-ai/bytedance/seedream/v4.description": "ByteDance Seed가 개발한 Seedream 4.0은 텍스트 및 이미지 입력을 지원하며, 프롬프트를 기반으로 고품질 이미지를 생성할 수 있는 높은 제어성을 제공합니다.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0은 ByteDance Seed의 이미지 생성 모델로, 텍스트와 이미지 입력을 지원하며 매우 제어 가능한 고품질 이미지 생성을 제공합니다. 텍스트 프롬프트를 통해 이미지를 생성합니다.",
"fal-ai/flux-kontext/dev.description": "FLUX.1 모델은 이미지 편집에 중점을 두며, 텍스트와 이미지 입력을 지원합니다.",
"fal-ai/flux-pro/kontext.description": "FLUX.1 Kontext [pro]는 텍스트와 참조 이미지를 입력으로 받아, 국소 편집과 복잡한 장면 변환을 정밀하게 수행할 수 있습니다.",
"fal-ai/flux/krea.description": "Flux Krea [dev]는 보다 사실적이고 자연스러운 이미지 스타일에 중점을 둔 이미지 생성 모델입니다.",
@@ -526,8 +522,8 @@
"fal-ai/hunyuan-image/v3.description": "강력한 네이티브 멀티모달 이미지 생성 모델입니다.",
"fal-ai/imagen4/preview.description": "Google에서 개발한 고품질 이미지 생성 모델입니다.",
"fal-ai/nano-banana.description": "Nano Banana는 Google의 최신, 가장 빠르고 효율적인 네이티브 멀티모달 모델로, 대화형 이미지 생성 및 편집을 지원합니다.",
"fal-ai/qwen-image-edit.description": "Qwen 팀의 전문 이미지 편집 모델로, 의미 외형 편집, 정확한 중국어/영어 텍스트 편집, 스타일 전환, 회전 등을 지원합니다.",
"fal-ai/qwen-image.description": "Qwen 팀의 강력한 이미지 생성 모델로, 중국어 텍스트 렌더링과 다양한 시각적 스타일을 제공합니다.",
"fal-ai/qwen-image-edit.description": "Qwen 팀의 전문 이미지 편집 모델로, 의미 외형 편집을 지원하며, 중국어영어 텍스트를 정밀하게 편집하고 스타일 전환 및 객체 회전과 같은 고품질 편집을 가능하게 합니다.",
"fal-ai/qwen-image.description": "Qwen 팀의 강력한 이미지 생성 모델로, 중국어 텍스트 렌더링과 다양한 시각적 스타일에서 뛰어난 성능을 발휘합니다.",
"flux-1-schnell.description": "Black Forest Labs에서 개발한 120억 파라미터 텍스트-이미지 모델로, 잠재 적대 확산 증류를 사용하여 1~4단계 내에 고품질 이미지를 생성합니다. Apache-2.0 라이선스로 개인, 연구, 상업적 사용이 가능합니다.",
"flux-dev.description": "비상업적 혁신 연구를 위해 효율적으로 최적화된 오픈소스 R&D 이미지 생성 모델입니다.",
"flux-kontext-max.description": "최첨단 문맥 기반 이미지 생성 및 편집 모델로, 텍스트와 이미지를 결합하여 정밀하고 일관된 결과를 생성합니다.",
@@ -566,10 +562,10 @@
"gemini-3-flash-preview.description": "Gemini 3 Flash는 속도를 위해 설계된 가장 스마트한 모델로, 최첨단 지능과 뛰어난 검색 기반을 결합합니다.",
"gemini-3-flash.description": "Google의 Gemini 3 Flash — 멀티모달 입력 지원을 갖춘 초고속 모델.",
"gemini-3-pro-image-preview.description": "Gemini 3 Pro Image (Nano Banana Pro)는 구글의 이미지 생성 모델로, 멀티모달 대화도 지원합니다.",
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro)는 Google의 이미지 생성 모델로, 멀티모달 채팅도 지원합니다.",
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro)는 Google의 이미지 생성 모델로, 멀티모달 대화를 지원합니다.",
"gemini-3-pro-preview.description": "Gemini 3 Pro는 Google의 가장 강력한 에이전트 및 바이브 코딩 모델로, 최첨단 추론 위에 풍부한 시각적 표현과 깊은 상호작용을 제공합니다.",
"gemini-3.1-flash-image-preview.description": "Gemini 3.1 Flash Image (Nano Banana 2)는 구글의 가장 빠른 네이티브 이미지 생성 모델로, 사고 지원, 대화형 이미지 생성 및 편집을 제공합니다.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2)는 Flash 속도로 Pro 수준의 이미지 품질을 제공하며, 멀티모달 채팅을 지원합니다.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2)는 Google의 가장 빠른 네이티브 이미지 생성 모델로, 사고 지원, 대화형 이미지 생성 및 편집을 제공합니다.",
"gemini-3.1-flash-lite-preview.description": "Gemini 3.1 Flash-Lite Preview는 Google의 가장 비용 효율적인 다중 모드 모델로, 대량 에이전트 작업, 번역 및 데이터 처리에 최적화되어 있습니다.",
"gemini-3.1-flash-lite.description": "Gemini 3.1 Flash-Lite는 Google의 가장 비용 효율적인 멀티모달 모델로, 대량 에이전트 작업, 번역 및 데이터 처리에 최적화되어 있습니다.",
"gemini-3.1-pro-preview.description": "Gemini 3.1 Pro Preview는 Gemini 3 Pro의 추론 능력을 강화하고 중간 사고 수준 지원을 추가합니다.",
@@ -734,8 +730,6 @@
"grok-4-fast-reasoning.description": "Grok 4 Fast는 비용 효율적인 추론 모델 분야에서의 최신 성과로, 출시를 기쁘게 생각합니다.",
"grok-4.20-0309-non-reasoning.description": "간단한 사용 사례를 위한 비추론 변형",
"grok-4.20-0309-reasoning.description": "응답 전에 추론하는 지능적이고 매우 빠른 모델",
"grok-4.20-beta-0309-non-reasoning.description": "간단한 사용 사례를 위한 비사고 변형 모델",
"grok-4.20-beta-0309-reasoning.description": "응답 전에 사고하는 지능적이고 매우 빠른 모델",
"grok-4.20-multi-agent-0309.description": "4명 또는 16명의 에이전트 팀, 연구 사용 사례에서 뛰어남, 현재 클라이언트 측 도구를 지원하지 않음. xAI 서버 측 도구(예: X Search, Web Search 도구) 및 원격 MCP 도구만 지원.",
"grok-4.3.description": "세계에서 가장 진실을 추구하는 대규모 언어 모델",
"grok-4.description": "언어, 수학, 추론에서 타의 추종을 불허하는 성능을 자랑하는 최신 Grok 플래그십 모델 — 진정한 만능 모델입니다. 현재 grok-4-0709를 가리키며, 제한된 자원으로 인해 공식 가격보다 임시로 10% 높게 책정되었으며, 이후 공식 가격으로 복귀할 예정입니다.",
@@ -1220,8 +1214,6 @@
"qwq.description": "QwQ는 Qwen 계열의 추론 모델입니다. 일반적인 지시 조정 모델과 비교해 사고 및 추론 능력이 뛰어나며, 특히 어려운 문제에서 다운스트림 성능을 크게 향상시킵니다. QwQ-32B는 DeepSeek-R1 및 o1-mini와 경쟁할 수 있는 중형 추론 모델입니다.",
"qwq_32b.description": "Qwen 계열의 중형 추론 모델입니다. 일반적인 지시 조정 모델과 비교해 QwQ의 사고 및 추론 능력은 특히 어려운 문제에서 다운스트림 성능을 크게 향상시킵니다.",
"r1-1776.description": "R1-1776은 DeepSeek R1의 후속 학습 버전으로, 검열되지 않고 편향 없는 사실 정보를 제공합니다.",
"seedance-1-5-pro-251215.description": "ByteDance의 Seedance 1.5 Pro는 텍스트-비디오, 이미지-비디오(첫 프레임, 첫+마지막 프레임) 및 시각과 동기화된 오디오 생성을 지원합니다.",
"seedream-5-0-260128.description": "BytePlus의 ByteDance-Seedream-5.0-lite는 실시간 정보를 위한 웹 검색 증강 생성, 복잡한 프롬프트 해석 강화, 전문적인 시각적 창작을 위한 참조 일관성 개선을 제공합니다.",
"solar-mini-ja.description": "Solar Mini (Ja)는 Solar Mini의 일본어 특화 버전으로, 영어와 한국어에서도 효율적이고 강력한 성능을 유지합니다.",
"solar-mini.description": "Solar Mini는 GPT-3.5를 능가하는 성능을 가진 소형 LLM으로, 영어와 한국어를 지원하는 강력한 다국어 기능을 갖추고 있으며, 효율적인 경량 솔루션을 제공합니다.",
"solar-pro.description": "Solar Pro는 Upstage의 고지능 LLM으로, 단일 GPU에서 지시 수행에 최적화되어 있으며, IFEval 점수 80 이상을 기록합니다. 현재는 영어를 지원하며, 2024년 11월 전체 릴리스 시 더 많은 언어와 긴 컨텍스트를 지원할 예정입니다.",
@@ -1233,7 +1225,9 @@
"sophnet/deepseek-v3.2.description": "DeepSeek V3.2는 높은 계산 효율성과 뛰어난 추론 및 에이전트 성능 간의 균형을 이루는 모델입니다.",
"sora-2-pro.description": "Sora 2 Pro는 최첨단, 가장 진보된 미디어 생성 모델로, 동기화된 오디오와 함께 비디오를 생성합니다. 자연어 또는 이미지를 사용하여 풍부한 세부 사항과 역동적인 클립을 생성할 수 있습니다.",
"sora-2.description": "Sora 2는 새로운 강력한 미디어 생성 모델로, 동기화된 오디오와 함께 비디오를 생성합니다. 자연어 또는 이미지를 사용하여 풍부한 세부 사항과 역동적인 클립을 생성할 수 있습니다.",
"spark-x.description": "X2 기능 개요: 1. `thinking` 필드를 통해 추론 모드의 동적 조정을 도입합니다. 2. 컨텍스트 길이 확장: 64K 입력 토큰 및 128K 출력 토큰. 3. Function Call 기능을 지원합니다.",
"spark-x1.5.description": "X1.5 업데이트: (1) `thinking` 필드를 통해 동적 사고 모드를 추가; (2) 64K 입력 및 64K 출력으로 더 큰 컨텍스트 길이 제공; (3) FunctionCall 지원.",
"spark-x2-flash.description": "Spark X2-Flash는 300억 개의 총 매개변수를 가진 MoE(Mixture of Experts) 아키텍처를 채택하며 최대 256K 컨텍스트 윈도우를 지원합니다. 에이전트 및 코딩 능력에서 상당한 개선을 주장하며 Ascend 910B AI 프로세서 클러스터에서 훈련되었습니다.",
"spark-x2.description": "X2 기능 개요: 1. `thinking` 필드를 통해 추론 모드의 동적 조정을 도입. 2. 확장된 컨텍스트 길이: 64K 입력 토큰 및 128K 출력 토큰. 3. Function Call 기능 지원.",
"stable-diffusion-3-medium.description": "Stability AI의 최신 텍스트-이미지 모델입니다. 이미지 품질, 텍스트 이해, 스타일 다양성이 크게 향상되었으며, 복잡한 자연어 프롬프트를 더 정확하게 해석하고 정밀하고 다양한 이미지를 생성합니다.",
"stable-diffusion-3.5-large-turbo.description": "Stable Diffusion 3.5 Large Turbo는 높은 디테일 표현과 장면 충실도를 갖춘 고품질 이미지 생성에 중점을 둡니다.",
"stable-diffusion-xl-base-1.0.description": "Stability AI의 오픈소스 텍스트-이미지 모델로, 업계 최고 수준의 창의적 이미지 생성을 제공합니다. 지시 이해력이 뛰어나며, 정밀한 생성을 위한 역 프롬프트 정의도 지원합니다.",
@@ -1355,7 +1349,6 @@
"x-ai/grok-4.1-fast.description": "Grok 4 Fast는 xAI의 고처리량, 저비용 모델로, 2M 컨텍스트 윈도우를 지원하며, 동시성 높은 환경과 장문 컨텍스트에 이상적입니다.",
"x-ai/grok-4.description": "Grok 4는 xAI의 대표 추론 모델로, 강력한 추론 능력과 멀티모달 기능을 갖추고 있습니다.",
"x-ai/grok-code-fast-1.description": "Grok Code Fast 1은 xAI의 빠른 코드 모델로, 가독성이 높고 엔지니어 친화적인 출력을 제공합니다.",
"x1.description": "X1.5 업데이트: (1) `thinking` 필드를 통해 동적 사고 모드를 추가합니다; (2) 더 큰 컨텍스트 길이로 64K 입력 및 64K 출력 지원; (3) FunctionCall을 지원합니다.",
"xai/grok-2-vision.description": "Grok 2 Vision은 시각적 작업에 뛰어나며, 시각 수학 추론(MathVista)과 문서 QA(DocVQA)에서 최고 성능을 발휘합니다. 문서, 차트, 그래프, 스크린샷, 사진을 처리할 수 있습니다.",
"xai/grok-2.description": "Grok 2는 최첨단 추론, 강력한 대화, 코딩 성능을 갖춘 프런티어 모델로, LMSYS에서 Claude 3.5 Sonnet 및 GPT-4 Turbo보다 높은 순위를 기록했습니다.",
"xai/grok-3-fast.description": "xAI의 대표 모델로, 데이터 추출, 코딩, 요약 등 기업용 사례에 뛰어나며, 금융, 의료, 법률, 과학 분야에 대한 깊은 전문 지식을 갖추고 있습니다. 빠른 변형은 더 빠른 응답을 위해 고속 인프라에서 실행되며, 토큰당 비용은 더 높습니다.",
+21 -21
View File
@@ -69,9 +69,22 @@
"builtins.lobe-agent-management.render.installPlugin.plugin": "플러그인",
"builtins.lobe-agent-management.render.installPlugin.success": "설치 완료",
"builtins.lobe-agent-management.title": "에이전트 관리자",
"builtins.lobe-agent-marketplace.apiName.showAgentMarketplace": "에이전트 마켓플레이스 열기",
"builtins.lobe-agent-marketplace.apiName.submitAgentPick": "에이전트 추천 제출",
"builtins.lobe-agent-marketplace.title": "에이전트 마켓플레이스",
"builtins.lobe-agent.apiName.callSubAgent": "하위 에이전트 호출",
"builtins.lobe-agent.apiName.callSubAgent.completed": "하위 에이전트 배치 완료: ",
"builtins.lobe-agent.apiName.callSubAgent.loading": "하위 에이전트 배치 중: ",
"builtins.lobe-agent.apiName.callSubAgents": "하위 에이전트 호출",
"builtins.lobe-agent.apiName.clearTodos": "할 일 목록 지우기",
"builtins.lobe-agent.apiName.clearTodos.modeAll": "전체",
"builtins.lobe-agent.apiName.clearTodos.modeCompleted": "완료됨",
"builtins.lobe-agent.apiName.clearTodos.result": "<mode>{{mode}}</mode> 할 일 목록 지우기",
"builtins.lobe-agent.apiName.createPlan": "계획 생성",
"builtins.lobe-agent.apiName.createPlan.result": "계획 생성: <goal>{{goal}}</goal>",
"builtins.lobe-agent.apiName.createTodos": "할 일 생성",
"builtins.lobe-agent.apiName.updatePlan": "계획 업데이트",
"builtins.lobe-agent.apiName.updatePlan.completed": "완료됨",
"builtins.lobe-agent.apiName.updatePlan.modified": "수정됨",
"builtins.lobe-agent.apiName.updateTodos": "할 일 업데이트",
"builtins.lobe-agent.title": "로브 에이전트",
"builtins.lobe-claude-code.agent.instruction": "지시사항",
"builtins.lobe-claude-code.agent.result": "결과",
"builtins.lobe-claude-code.todoWrite.allDone": "모든 작업이 완료되었습니다",
@@ -139,24 +152,6 @@
"builtins.lobe-group-management.inspector.executeAgentTasks.title": "작업 할당 대상:",
"builtins.lobe-group-management.inspector.speak.title": "지정된 에이전트가 말합니다:",
"builtins.lobe-group-management.title": "팀 조율",
"builtins.lobe-gtd.apiName.clearTodos": "할 일 비우기",
"builtins.lobe-gtd.apiName.clearTodos.modeAll": "전체",
"builtins.lobe-gtd.apiName.clearTodos.modeCompleted": "완료됨",
"builtins.lobe-gtd.apiName.clearTodos.result": "<mode>{{mode}}</mode> 할 일 삭제",
"builtins.lobe-gtd.apiName.completeTodos": "할 일 완료",
"builtins.lobe-gtd.apiName.createPlan": "계획 만들기",
"builtins.lobe-gtd.apiName.createPlan.result": "계획 생성: <goal>{{goal}}</goal>",
"builtins.lobe-gtd.apiName.createTodos": "할 일 만들기",
"builtins.lobe-gtd.apiName.execTask": "작업 실행",
"builtins.lobe-gtd.apiName.execTask.completed": "작업이 생성되었습니다: ",
"builtins.lobe-gtd.apiName.execTask.loading": "작업 생성 중: ",
"builtins.lobe-gtd.apiName.execTasks": "작업들 실행",
"builtins.lobe-gtd.apiName.removeTodos": "할 일 삭제",
"builtins.lobe-gtd.apiName.updatePlan": "계획 업데이트",
"builtins.lobe-gtd.apiName.updatePlan.completed": "완료됨",
"builtins.lobe-gtd.apiName.updatePlan.modified": "수정됨",
"builtins.lobe-gtd.apiName.updateTodos": "할 일 업데이트",
"builtins.lobe-gtd.title": "GTD 도구",
"builtins.lobe-knowledge-base.apiName.readKnowledge": "지식 베이스 내용 읽기",
"builtins.lobe-knowledge-base.apiName.searchKnowledgeBase": "지식 베이스 검색",
"builtins.lobe-knowledge-base.inspector.andMoreFiles": "외에 {{count}}개 더",
@@ -317,6 +312,8 @@
"builtins.lobe-web-onboarding.apiName.finishOnboarding": "온보딩 완료",
"builtins.lobe-web-onboarding.apiName.readDocument": "문서 읽기",
"builtins.lobe-web-onboarding.apiName.saveUserQuestion": "사용자 질문 저장",
"builtins.lobe-web-onboarding.apiName.showAgentMarketplace": "에이전트 팀 구성",
"builtins.lobe-web-onboarding.apiName.submitAgentPick": "에이전트 선택 제출",
"builtins.lobe-web-onboarding.apiName.updateDocument": "문서 업데이트",
"builtins.lobe-web-onboarding.apiName.writeDocument": "문서 작성",
"builtins.lobe-web-onboarding.docType.persona": "사용자 페르소나",
@@ -327,6 +324,9 @@
"builtins.lobe-web-onboarding.inspector.hunkCount_other": "{{count}} 변경",
"builtins.lobe-web-onboarding.inspector.interests_one": "{{count}} 관심사",
"builtins.lobe-web-onboarding.inspector.interests_other": "{{count}} 관심사",
"builtins.lobe-web-onboarding.render.agent": "에이전트",
"builtins.lobe-web-onboarding.render.fullName": "전체 이름",
"builtins.lobe-web-onboarding.render.interests": "관심사",
"builtins.lobe-web-onboarding.title": "사용자 온보딩",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.delete": "삭제",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.deleteLines": "줄 삭제",
-1
View File
@@ -33,7 +33,6 @@
"jina.description": "2020년에 설립된 Jina AI는 선도적인 검색 AI 기업으로, 벡터 모델, 재정렬기, 소형 언어 모델을 포함한 검색 스택을 통해 신뢰성 높고 고품질의 생성형 및 멀티모달 검색 앱을 구축합니다.",
"kimicodingplan.description": "문샷 AI의 Kimi Code는 K2.5를 포함한 Kimi 모델에 접근하여 코딩 작업을 수행할 수 있습니다.",
"lmstudio.description": "LM Studio는 데스크탑에서 LLM을 개발하고 실험할 수 있는 애플리케이션입니다.",
"lobehub.description": "LobeHub Cloud는 공식 API를 사용하여 AI 모델에 접근하며, 모델 토큰에 연동된 크레딧으로 사용량을 측정합니다.",
"longcat.description": "LongCat은 Meituan에서 독자적으로 개발한 생성형 AI 대형 모델 시리즈입니다. 이는 효율적인 계산 아키텍처와 강력한 멀티모달 기능을 통해 내부 기업 생산성을 향상시키고 혁신적인 애플리케이션을 가능하게 하기 위해 설계되었습니다.",
"minimax.description": "2021년에 설립된 MiniMax는 텍스트, 음성, 비전 등 멀티모달 기반의 범용 AI를 개발하며, 조 단위 파라미터의 MoE 텍스트 모델과 Hailuo AI와 같은 앱을 제공합니다.",
"minimaxcodingplan.description": "MiniMax 토큰 플랜은 고정 요금 구독을 통해 M2.7을 포함한 MiniMax 모델에 접근하여 코딩 작업을 수행할 수 있습니다.",
-2
View File
@@ -913,8 +913,6 @@
"tools.builtins.lobe-agent-documents.title": "문서",
"tools.builtins.lobe-agent-management.description": "AI 에이전트를 생성, 관리, 오케스트레이션합니다",
"tools.builtins.lobe-agent-management.title": "에이전트 관리",
"tools.builtins.lobe-agent-marketplace.description": "사용자에게 엄선된 에이전트 마켓플레이스 카드를 보여주고, 그들이 선택한 템플릿을 기록합니다.",
"tools.builtins.lobe-agent-marketplace.title": "에이전트 마켓플레이스",
"tools.builtins.lobe-artifacts.description": "인터랙티브 UI 구성 요소, 차트 및 웹 콘텐츠를 생성하고 미리보기",
"tools.builtins.lobe-artifacts.readme": "인터랙티브 UI 구성 요소, 데이터 시각화, 차트, SVG 그래픽 및 웹 애플리케이션을 생성하고 실시간으로 미리보기할 수 있습니다. 사용자가 직접 상호작용할 수 있는 풍부한 시각 콘텐츠를 만들어보세요.",
"tools.builtins.lobe-artifacts.title": "아티팩트",
+45 -45
View File
@@ -56,51 +56,51 @@
"dalle.generating": "생성 중...",
"dalle.images": "이미지:",
"dalle.prompt": "프롬프트",
"lobe-gtd.actions.add": "추가",
"lobe-gtd.actions.clearCompleted": "완료된 항목 삭제",
"lobe-gtd.actions.placeholder": "할 일 항목 입력...",
"lobe-gtd.addTodo.placeholder": "할 일 항목 추가...",
"lobe-gtd.clearTodos.cleared": "{{count}}개 항목 삭제",
"lobe-gtd.clearTodos.clearedCompleted": "완료된 {{count}}개 항목 삭제",
"lobe-gtd.clearTodos.clearedCompleted_one": "완료된 {{count}}개 항목 삭제",
"lobe-gtd.clearTodos.clearedCompleted_other": "완료된 {{count}}개 항목 삭제",
"lobe-gtd.clearTodos.cleared_one": "{{count}}개 항목 삭제",
"lobe-gtd.clearTodos.cleared_other": "{{count}}개 항목 삭제",
"lobe-gtd.clearTodos.header": "할 일 항목 지우기",
"lobe-gtd.clearTodos.label": "지울 항목 선택:",
"lobe-gtd.clearTodos.noItems": "삭제할 항목이 없습니다",
"lobe-gtd.clearTodos.option.all": "모든 항목 지우기 (대기 중인 항목 포함)",
"lobe-gtd.clearTodos.option.completed": "완료된 항목만 지우기",
"lobe-gtd.clearTodos.remaining": "남은 항목 {{count}}개",
"lobe-gtd.clearTodos.remaining_one": "남은 항목 {{count}}개",
"lobe-gtd.clearTodos.remaining_other": "남은 항목 {{count}}개",
"lobe-gtd.completeTodos.completed": "{{count}}개 항목 완료",
"lobe-gtd.completeTodos.completed_one": "{{count}}개 항목 완료",
"lobe-gtd.completeTodos.completed_other": "{{count}}개 항목 완료",
"lobe-gtd.createPlan.context.label": "상황 (선택 사항)",
"lobe-gtd.createPlan.context.placeholder": "배경, 제약 조건, 고려 사항...",
"lobe-gtd.createPlan.description.label": "설명",
"lobe-gtd.createPlan.description.placeholder": "계획에 대한 간단한 요약",
"lobe-gtd.createPlan.goal.label": "목표",
"lobe-gtd.createPlan.goal.placeholder": "달성하고자 하는 것은 무엇인가요?",
"lobe-gtd.createTodos.created": "{{count}}개 할 일 항목 생성됨",
"lobe-gtd.createTodos.created_one": "{{count}}개 할 일 항목 생성됨",
"lobe-gtd.createTodos.created_other": "{{count}}개 할 일 항목 생성됨",
"lobe-gtd.createTodos.total": "총 {{count}}개 항목",
"lobe-gtd.createTodos.total_one": "총 {{count}}개 항목",
"lobe-gtd.createTodos.total_other": "총 {{count}}개 항목",
"lobe-gtd.removeTodos.removed": "{{count}}개 항목 삭제",
"lobe-gtd.removeTodos.removed_one": "{{count}}개 항목 삭제",
"lobe-gtd.removeTodos.removed_other": "{{count}}개 항목 삭제",
"lobe-gtd.status.done": "{{count}}개 완료됨",
"lobe-gtd.status.pending": "{{count}}개 대기 중",
"lobe-gtd.todoItem.placeholder": "할 일 항목 입력...",
"lobe-gtd.todoList.empty": "할 일 목록이 비어 있습니다",
"lobe-gtd.todoList.items": "{{count}}개 항목",
"lobe-gtd.todoList.items_one": "{{count}}개 항목",
"lobe-gtd.todoList.items_other": "{{count}}개 항목",
"lobe-gtd.todoList.title": "할 일 목록",
"lobe-gtd.updateTodos.updated": "할 일 목록이 업데이트되었습니다",
"lobe-agent.actions.add": "추가",
"lobe-agent.actions.clearCompleted": "완료된 항목 지우기",
"lobe-agent.actions.placeholder": "할 일을 입력하세요...",
"lobe-agent.addTodo.placeholder": "할 일을 추가하세요...",
"lobe-agent.clearTodos.cleared": "{{count}}개 항목 삭제되었습니다",
"lobe-agent.clearTodos.clearedCompleted": "{{count}}개 완료된 항목 삭제되었습니다",
"lobe-agent.clearTodos.clearedCompleted_one": "{{count}}개 완료된 항목 삭제되었습니다",
"lobe-agent.clearTodos.clearedCompleted_other": "{{count}}개 완료된 항목 삭제되었습니다",
"lobe-agent.clearTodos.cleared_one": "{{count}}개 항목 삭제되었습니다",
"lobe-agent.clearTodos.cleared_other": "{{count}}개 항목 삭제되었습니다",
"lobe-agent.clearTodos.header": "할 일 항목 삭제",
"lobe-agent.clearTodos.label": "삭제할 항목 선택하세요:",
"lobe-agent.clearTodos.noItems": "삭제할 항목이 없습니다",
"lobe-agent.clearTodos.option.all": "모든 항목 삭제 (대기 중인 항목 포함)",
"lobe-agent.clearTodos.option.completed": "완료된 항목만 삭제",
"lobe-agent.clearTodos.remaining": "{{count}}개 항목 남음",
"lobe-agent.clearTodos.remaining_one": "{{count}}개 항목 남음",
"lobe-agent.clearTodos.remaining_other": "{{count}}개 항목 남음",
"lobe-agent.completeTodos.completed": "{{count}}개 항목 완료되었습니다",
"lobe-agent.completeTodos.completed_one": "{{count}}개 항목 완료되었습니다",
"lobe-agent.completeTodos.completed_other": "{{count}}개 항목 완료되었습니다",
"lobe-agent.createPlan.context.label": "상황 (선택 사항)",
"lobe-agent.createPlan.context.placeholder": "배경, 제약 조건, 고려 사항...",
"lobe-agent.createPlan.description.label": "설명",
"lobe-agent.createPlan.description.placeholder": "계획 간단한 요약",
"lobe-agent.createPlan.goal.label": "목표",
"lobe-agent.createPlan.goal.placeholder": "달성하고자 하는 목표는 무엇인가요?",
"lobe-agent.createTodos.created": "{{count}}개 할 일이 생성되었습니다",
"lobe-agent.createTodos.created_one": "{{count}}개 할 일이 생성되었습니다",
"lobe-agent.createTodos.created_other": "{{count}}개 할 일이 생성되었습니다",
"lobe-agent.createTodos.total": "총: {{count}}개 항목",
"lobe-agent.createTodos.total_one": "총: {{count}}개 항목",
"lobe-agent.createTodos.total_other": "총: {{count}}개 항목",
"lobe-agent.removeTodos.removed": "{{count}}개 항목 삭제되었습니다",
"lobe-agent.removeTodos.removed_one": "{{count}}개 항목 삭제되었습니다",
"lobe-agent.removeTodos.removed_other": "{{count}}개 항목 삭제되었습니다",
"lobe-agent.status.done": "{{count}}개 완료됨",
"lobe-agent.status.pending": "{{count}}개 대기 중",
"lobe-agent.todoItem.placeholder": "할 일을 입력하세요...",
"lobe-agent.todoList.empty": "할 일 목록이 비어 있습니다",
"lobe-agent.todoList.items": "{{count}}개 항목",
"lobe-agent.todoList.items_one": "{{count}}개 항목",
"lobe-agent.todoList.items_other": "{{count}}개 항목",
"lobe-agent.todoList.title": "할 일 목록",
"lobe-agent.updateTodos.updated": "할 일 목록이 업데이트되었습니다",
"lobe-knowledge-base.readKnowledge.meta.chars": "문자 수",
"lobe-knowledge-base.readKnowledge.meta.lines": "줄 수",
"localFiles.editFile.newString": "다음으로 바꾸기",
+4
View File
@@ -115,6 +115,10 @@
"channel.line.fetchBotInfoMissingToken": "Voer eerst het kanaaltoegangstoken in en klik vervolgens op \"Ophalen van LINE\".",
"channel.line.fetchBotInfoSuccess": "Bestemmingsgebruikers-ID opgehaald",
"channel.line.webhookManualSetup": "LINE staat geen programmatische webhookregistratie toe. Kopieer deze URL naar de LINE Developers Console (Messaging API → Webhook-URL), klik op \"Verifiëren\" en schakel \"Webhook gebruiken\" in.",
"channel.messengerPromo.action": "Probeer Messenger",
"channel.messengerPromo.desc": "Geen botconfiguratie nodig. Chat met LobeHub op Slack, Discord, Telegram.",
"channel.messengerPromo.dismiss": "Sluiten",
"channel.messengerPromo.title": "Sla de setup over",
"channel.openPlatform": "Open Platform",
"channel.platforms": "Platformen",
"channel.publicKey": "Publieke sleutel",
+4 -3
View File
@@ -314,7 +314,7 @@
"openInNewWindow": "Openen in nieuw venster",
"operation.contextCompression": "Context te lang, geschiedenis wordt samengevat...",
"operation.execAgentRuntime": "Reactie voorbereiden",
"operation.execClientTask": "Taak wordt uitgevoerd",
"operation.execClientSubAgent": "Sub-agent uitvoeren",
"operation.execHeterogeneousAgent": "{{name}} wordt uitgevoerd",
"operation.execServerAgentRuntime": "Bezig… Je kunt van taak wisselen of de pagina sluiten — de taak blijft doorgaan.",
"operation.heterogeneousAgentFallback": "Externe agent",
@@ -567,6 +567,7 @@
"taskList.contextMenu.copyLink": "Link kopiëren",
"taskList.contextMenu.copyLinkSuccess": "Link gekopieerd",
"taskList.contextMenu.priority": "Prioriteit",
"taskList.contextMenu.runNow": "Nu uitvoeren",
"taskList.contextMenu.status": "Status",
"taskList.empty": "Nog geen taken",
"taskList.emptyHero.greeting": "Wat zullen we vandaag aanpakken?",
@@ -771,6 +772,8 @@
"workflow.toolDisplayName.addPreferenceMemory": "Opgeslagen geheugen",
"workflow.toolDisplayName.calculate": "Berekend",
"workflow.toolDisplayName.callAgent": "Agent aangeroepen",
"workflow.toolDisplayName.callSubAgent": "Een sub-agent verzonden",
"workflow.toolDisplayName.callSubAgents": "Sub-agents verzonden",
"workflow.toolDisplayName.clearTodos": "Taken gewist",
"workflow.toolDisplayName.copyDocument": "Een document gekopieerd",
"workflow.toolDisplayName.crawlMultiPages": "Gecrawlde pagina's",
@@ -785,8 +788,6 @@
"workflow.toolDisplayName.editTitle": "Bewerkte titel",
"workflow.toolDisplayName.evaluate": "Geëvalueerde expressie",
"workflow.toolDisplayName.execScript": "Script uitgevoerd",
"workflow.toolDisplayName.execTask": "Taak uitgevoerd",
"workflow.toolDisplayName.execTasks": "Uitgevoerde taken",
"workflow.toolDisplayName.execute": "Berekening uitgevoerd",
"workflow.toolDisplayName.executeCode": "Code uitgevoerd",
"workflow.toolDisplayName.finishOnboarding": "Onboarding voltooien",
+2
View File
@@ -349,6 +349,8 @@
"loading": "Laden...",
"mail.business": "Zakelijke samenwerking",
"mail.support": "E-mailondersteuning",
"messengerBanner.dismiss": "Sluiten",
"messengerBanner.title": "Praat met Lobe AI via je favoriete berichtenapps",
"more": "Meer",
"navPanel.agent": "Agent",
"navPanel.customizeSidebar": "Zijbalk aanpassen",
-1
View File
@@ -35,7 +35,6 @@
"messenger.linkModal.notConfigured": "Deze verbinding is momenteel niet beschikbaar. Probeer het later opnieuw.",
"messenger.linkModal.openCta": "Open in {{platform}}",
"messenger.linkModal.scanHint": "Of scan met je telefoon om {{platform}} te openen.",
"messenger.linkModal.title": "Messenger verbinden",
"messenger.list.discord.description": "Chat met je LobeHub-agenten vanaf elke Discord-server via DM met de LobeHub-bot.",
"messenger.list.slack.description": "Chat met je LobeHub-agenten vanuit elke Slack-werkruimte via DM of @LobeHub.",
"messenger.list.telegram.description": "Chat met je LobeHub-agenten in Telegram en kies wie er antwoordt, waar je ook bent.",
+15 -22
View File
@@ -106,7 +106,6 @@
"MiniMax-Hailuo-2.3.description": "Gloednieuw videogenereermodel met uitgebreide verbeteringen in lichaamsbeweging, fysieke realisme en instructienaleving.",
"MiniMax-M1.description": "Een nieuw intern redeneermodel met 80K chain-of-thought en 1M input, met prestaties vergelijkbaar met toonaangevende wereldwijde modellen.",
"MiniMax-M2-Stable.description": "Ontworpen voor efficiënte codeer- en agentworkflows, met hogere gelijktijdigheid voor commercieel gebruik.",
"MiniMax-M2.1-Lightning.description": "Krachtige meertalige programmeermogelijkheden met snellere en efficiëntere inferentie.",
"MiniMax-M2.1-highspeed.description": "Krachtige meertalige programmeermogelijkheden, een volledig verbeterde programmeerervaring. Sneller en efficiënter.",
"MiniMax-M2.1.description": "MiniMax-M2.1 is het vlaggenschip open-source grote model van MiniMax, gericht op het oplossen van complexe, realistische taken. De kernkwaliteiten zijn meertalige programmeermogelijkheden en het vermogen om complexe taken als een Agent op te lossen.",
"MiniMax-M2.5-highspeed.description": "MiniMax M2.5 Highspeed: Zelfde prestaties als M2.5 met snellere inferentie.",
@@ -315,13 +314,13 @@
"claude-3-haiku-20240307.description": "Claude 3 Haiku is het snelste en meest compacte model van Anthropic, ontworpen voor vrijwel directe reacties met snelle en nauwkeurige prestaties.",
"claude-3-opus-20240229.description": "Claude 3 Opus is het krachtigste model van Anthropic voor zeer complexe taken, met uitmuntende prestaties, intelligentie, vloeiendheid en begrip.",
"claude-3-sonnet-20240229.description": "Claude 3 Sonnet biedt een balans tussen intelligentie en snelheid voor zakelijke toepassingen, met hoge bruikbaarheid tegen lagere kosten en betrouwbare grootschalige inzet.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 is Anthropic's snelste en meest intelligente Haiku-model, met bliksemsnelle snelheid en uitgebreide denkcapaciteit.",
"claude-haiku-4-5-20251001.description": "Claude Haiku 4.5 is het snelste en slimste Haiku-model van Anthropic, met bliksemsnelle snelheid en uitgebreide redeneervermogen.",
"claude-haiku-4-5.description": "Claude Haiku 4.5 door Anthropic — next-gen Haiku met verbeterde redenering en visie.",
"claude-haiku-4.5.description": "Claude Haiku 4.5 is Anthropic's snelste en slimste Haiku-model, met bliksemsnelle snelheid en uitgebreide redeneervermogen.",
"claude-opus-4-1-20250805-thinking.description": "Claude Opus 4.1 Thinking is een geavanceerde variant die zijn redeneerproces kan onthullen.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 is Anthropic's nieuwste en meest capabele model voor zeer complexe taken, uitblinkend in prestaties, intelligentie, vloeiendheid en begrip.",
"claude-opus-4-1-20250805.description": "Claude Opus 4.1 is het nieuwste en meest capabele model van Anthropic voor zeer complexe taken, uitblinkend in prestaties, intelligentie, vloeiendheid en begrip.",
"claude-opus-4-1.description": "Claude Opus 4.1 door Anthropic — premium redeneermodel met diepgaande analysemogelijkheden.",
"claude-opus-4-20250514.description": "Claude Opus 4 is Anthropic's krachtigste model voor zeer complexe taken, uitblinkend in prestaties, intelligentie, vloeiendheid en begrip.",
"claude-opus-4-20250514.description": "Claude Opus 4 is het krachtigste model van Anthropic voor zeer complexe taken, uitblinkend in prestaties, intelligentie, vloeiendheid en begrip.",
"claude-opus-4-5-20251101.description": "Claude Opus 4.5 is het vlaggenschipmodel van Anthropic, dat uitzonderlijke intelligentie combineert met schaalbare prestaties. Ideaal voor complexe taken die hoogwaardige antwoorden en redenering vereisen.",
"claude-opus-4-5.description": "Claude Opus 4.5 door Anthropic — vlaggenschipmodel met topklasse redenering en codering.",
"claude-opus-4-6.description": "Claude Opus 4.6 door Anthropic — vlaggenschip met 1M contextvenster en geavanceerde redenering.",
@@ -330,8 +329,8 @@
"claude-opus-4.6-fast.description": "Claude Opus 4.6 is Anthropic's meest intelligente model voor het bouwen van agents en coderen.",
"claude-opus-4.6.description": "Claude Opus 4.6 is Anthropic's meest intelligente model voor het bouwen van agents en coderen.",
"claude-sonnet-4-20250514-thinking.description": "Claude Sonnet 4 Thinking kan vrijwel directe antwoorden geven of uitgebreide stapsgewijze redenering tonen met zichtbaar proces.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 is Anthropic's meest intelligente model tot nu toe, met bijna-instant reacties of uitgebreide stapsgewijze denkprocessen met fijnmazige controle voor API-gebruikers.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5 is Anthropic's meest intelligente model tot nu toe.",
"claude-sonnet-4-20250514.description": "Claude Sonnet 4 kan bijna onmiddellijke reacties genereren of uitgebreide stapsgewijze redeneringen met een zichtbaar proces.",
"claude-sonnet-4-5-20250929.description": "Claude Sonnet 4.5 is het meest intelligente model van Anthropic tot nu toe.",
"claude-sonnet-4-5.description": "Claude Sonnet 4.5 door Anthropic — verbeterde Sonnet met verbeterde codeerprestaties.",
"claude-sonnet-4-6.description": "Claude Sonnet 4.6 door Anthropic — nieuwste Sonnet met superieure codering en hulpmiddelengebruik.",
"claude-sonnet-4.5.description": "Claude Sonnet 4.5 is tot nu toe het meest intelligente model van Anthropic.",
@@ -404,7 +403,7 @@
"deepseek-ai/deepseek-llm-67b-chat.description": "DeepSeek LLM Chat (67B) is een innovatief model dat diep taalbegrip en interactie biedt.",
"deepseek-ai/deepseek-v3.1-terminus.description": "DeepSeek V3.1 is een next-gen redeneermodel met sterkere complexe redenering en chain-of-thought voor diepgaande analysetaken.",
"deepseek-ai/deepseek-v3.2.description": "DeepSeek V3.2 is een next-gen redeneermodel met sterkere complexe redeneer- en keten-van-denken-capaciteiten.",
"deepseek-chat.description": "Compatibiliteitsalias voor DeepSeek V4 Flash non-thinking mode. Gepland voor afschaffing — gebruik DeepSeek V4 Flash in plaats daarvan.",
"deepseek-chat.description": "Een nieuw open-source model dat algemene en codeermogelijkheden combineert. Het behoudt de algemene dialoog van het chatmodel en de sterke codeermogelijkheden van het coderingsmodel, met betere voorkeurafstemming. DeepSeek-V2.5 verbetert ook schrijven en het opvolgen van instructies.",
"deepseek-coder-33B-instruct.description": "DeepSeek Coder 33B is een codeertaalmodel getraind op 2 biljoen tokens (87% code, 13% Chinees/Engels tekst). Het introduceert een contextvenster van 16K en 'fill-in-the-middle'-taken, wat projectniveau codeaanvulling en fragmentinvoeging mogelijk maakt.",
"deepseek-coder-v2.description": "DeepSeek Coder V2 is een open-source MoE-codeermodel dat sterk presteert bij programmeertaken, vergelijkbaar met GPT-4 Turbo.",
"deepseek-coder-v2:236b.description": "DeepSeek Coder V2 is een open-source MoE-codeermodel dat sterk presteert bij programmeertaken, vergelijkbaar met GPT-4 Turbo.",
@@ -426,7 +425,7 @@
"deepseek-r1-fast-online.description": "DeepSeek R1 snelle volledige versie met realtime webzoekfunctie, combineert 671B-capaciteit met snellere reacties.",
"deepseek-r1-online.description": "DeepSeek R1 volledige versie met 671B parameters en realtime webzoekfunctie, biedt sterkere begrip- en generatiecapaciteiten.",
"deepseek-r1.description": "DeepSeek-R1 gebruikt cold-start data vóór versterkingsleren en presteert vergelijkbaar met OpenAI-o1 op wiskunde, programmeren en redenering.",
"deepseek-reasoner.description": "Compatibiliteitsalias voor DeepSeek V4 Flash thinking mode. Gepland voor afschaffing — gebruik DeepSeek V4 Flash in plaats daarvan.",
"deepseek-reasoner.description": "Een DeepSeek-redeneermodel gericht op complexe logische redeneertaken.",
"deepseek-v2.description": "DeepSeek V2 is een efficiënt MoE-model voor kosteneffectieve verwerking.",
"deepseek-v2:236b.description": "DeepSeek V2 236B is DeepSeeks codegerichte model met sterke codegeneratie.",
"deepseek-v3-0324.description": "DeepSeek-V3-0324 is een MoE-model met 671B parameters en uitmuntende prestaties in programmeren, technische vaardigheden, contextbegrip en verwerking van lange teksten.",
@@ -491,8 +490,6 @@
"doubao-seedream-4-0-250828.description": "Seedream 4.0 is een beeldgeneratiemodel van ByteDance Seed dat tekst- en afbeeldingsinvoer ondersteunt voor zeer controleerbare, hoogwaardige beeldgeneratie. Het genereert beelden op basis van tekstprompts.",
"doubao-seedream-4-5-251128.description": "Seedream 4.5 is het nieuwste multimodale beeldmodel van ByteDance, dat tekst-naar-beeld, beeld-naar-beeld en batchbeeldgeneratiecapaciteiten integreert, terwijl het gezond verstand en redeneervermogen bevat. Vergeleken met de vorige 4.0-versie levert het aanzienlijk verbeterde generatiekwaliteit, met betere bewerkingsconsistentie en multi-beeldfusie. Het biedt meer precieze controle over visuele details, produceert kleine teksten en gezichten natuurlijker, en bereikt een harmonieuzere lay-out en kleur, wat de algehele esthetiek verbetert.",
"doubao-seedream-5-0-260128.description": "Doubao-Seedream-5.0-lite is het nieuwste beeldgeneratiemodel van ByteDance. Voor het eerst integreert het online zoekmogelijkheden, waardoor het real-time webinformatie kan opnemen en de actualiteit van gegenereerde beelden kan verbeteren. De intelligentie van het model is ook geüpgraded, waardoor het complexe instructies en visuele inhoud nauwkeurig kan interpreteren. Bovendien biedt het verbeterde wereldwijde kennisdekking, referentieconsistentie en generatiekwaliteit in professionele scenario's, waardoor het beter voldoet aan visuele creatiebehoeften op ondernemingsniveau.",
"dreamina-seedance-2-0-260128.description": "Seedance 2.0 van ByteDance is het krachtigste videogeneratiemodel, ondersteunt multimodale referentievideogeneratie, videobewerking, video-uitbreiding, tekst-naar-video en afbeelding-naar-video met gesynchroniseerde audio.",
"dreamina-seedance-2-0-fast-260128.description": "Seedance 2.0 Fast van ByteDance biedt dezelfde mogelijkheden als Seedance 2.0 met snellere generatiesnelheden tegen een concurrerende prijs.",
"emohaa.description": "Emohaa is een mentaal gezondheidsmodel met professionele begeleidingsvaardigheden om gebruikers te helpen emotionele problemen te begrijpen.",
"ernie-4.5-0.3b.description": "ERNIE 4.5 0.3B is een lichtgewicht open-source model voor lokale en aangepaste implementatie.",
"ernie-4.5-8k-preview.description": "ERNIE 4.5 8K Preview is een previewmodel met 8K context voor het evalueren van ERNIE 4.5.",
@@ -517,8 +514,7 @@
"ernie-x1-turbo-32k.description": "ERNIE X1 Turbo 32K is een snel denkend model met 32K context voor complexe redenatie en meerstapsgesprekken.",
"ernie-x1.1-preview.description": "ERNIE X1.1 Preview is een preview van een denkmodel voor evaluatie en testen.",
"ernie-x1.1.description": "ERNIE X1.1 is een preview van een denkmodel voor evaluatie en testen.",
"fal-ai/bytedance/seedream/v4.5.description": "Seedream 4.5, gebouwd door het ByteDance Seed-team, ondersteunt multi-image bewerking en compositie. Kenmerken verbeterde onderwerpconsistentie, nauwkeurige instructievolging, ruimtelijk logisch begrip, esthetische expressie, posterlay-out en logodesign met hoogprecisie tekst-afbeelding rendering.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0, gebouwd door ByteDance Seed, ondersteunt tekst- en afbeeldingsinvoer voor zeer controleerbare, hoogwaardige afbeeldingsgeneratie vanuit prompts.",
"fal-ai/bytedance/seedream/v4.description": "Seedream 4.0 is een beeldgeneratiemodel van ByteDance Seed, dat tekst- en beeldinvoer ondersteunt met zeer controleerbare, hoogwaardige beeldgeneratie. Het genereert beelden op basis van tekstprompts.",
"fal-ai/flux-kontext/dev.description": "FLUX.1-model gericht op beeldbewerking, met ondersteuning voor tekst- en afbeeldingsinvoer.",
"fal-ai/flux-pro/kontext.description": "FLUX.1 Kontext [pro] accepteert tekst en referentieafbeeldingen als invoer, waardoor gerichte lokale bewerkingen en complexe wereldwijde scèneaanpassingen mogelijk zijn.",
"fal-ai/flux/krea.description": "Flux Krea [dev] is een afbeeldingsgeneratiemodel met een esthetische voorkeur voor realistische, natuurlijke beelden.",
@@ -526,8 +522,8 @@
"fal-ai/hunyuan-image/v3.description": "Een krachtig, native multimodaal afbeeldingsgeneratiemodel.",
"fal-ai/imagen4/preview.description": "Hoogwaardig afbeeldingsgeneratiemodel van Google.",
"fal-ai/nano-banana.description": "Nano Banana is het nieuwste, snelste en meest efficiënte native multimodale model van Google, waarmee beeldgeneratie en -bewerking via conversatie mogelijk is.",
"fal-ai/qwen-image-edit.description": "Een professioneel afbeeldingsbewerkingsmodel van het Qwen-team, ondersteunt semantische en uiterlijke bewerkingen, nauwkeurige Chinese/Engelse tekstbewerking, stijltransfer, rotatie en meer.",
"fal-ai/qwen-image.description": "Een krachtig afbeeldingsgeneratiemodel van het Qwen-team met sterke Chinese tekstweergave en diverse visuele stijlen.",
"fal-ai/qwen-image-edit.description": "Een professioneel beeldbewerkingsmodel van het Qwen-team dat semantische en visuele bewerkingen ondersteunt, Chinese en Engelse tekst nauwkeurig bewerkt en hoogwaardige bewerkingen mogelijk maakt, zoals stijltransfer en objectrotatie.",
"fal-ai/qwen-image.description": "Een krachtig beeldgeneratiemodel van het Qwen-team met indrukwekkende Chinese tekstrendering en diverse visuele stijlen.",
"flux-1-schnell.description": "Een tekst-naar-beeldmodel met 12 miljard parameters van Black Forest Labs, dat gebruikmaakt van latente adversariële diffusiedistillatie om hoogwaardige beelden te genereren in 14 stappen. Het evenaart gesloten alternatieven en is uitgebracht onder de Apache-2.0-licentie voor persoonlijk, onderzoeks- en commercieel gebruik.",
"flux-dev.description": "Open-source R&D-beeldgeneratiemodel, efficiënt geoptimaliseerd voor niet-commercieel innovatief onderzoek.",
"flux-kontext-max.description": "State-of-the-art contextuele beeldgeneratie en -bewerking, waarbij tekst en afbeeldingen worden gecombineerd voor nauwkeurige, samenhangende resultaten.",
@@ -566,10 +562,10 @@
"gemini-3-flash-preview.description": "Gemini 3 Flash is het slimste model dat is gebouwd voor snelheid, met geavanceerde intelligentie en uitstekende zoekverankering.",
"gemini-3-flash.description": "Gemini 3 Flash door Google — ultrafast model met ondersteuning voor multimodale invoer.",
"gemini-3-pro-image-preview.description": "Gemini 3 Pro Image (Nano Banana Pro) is het beeldgeneratiemodel van Google dat ook multimodale dialogen ondersteunt.",
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro) is Google's afbeeldingsgeneratiemodel en ondersteunt ook multimodale chat.",
"gemini-3-pro-image-preview:image.description": "Gemini 3 Pro Image (Nano Banana Pro) is het beeldgeneratiemodel van Google en ondersteunt ook multimodale chat.",
"gemini-3-pro-preview.description": "Gemini 3 Pro is het krachtigste agent- en vibe-codingmodel van Google, met rijkere visuele output en diepere interactie bovenop geavanceerde redeneercapaciteiten.",
"gemini-3.1-flash-image-preview.description": "Gemini 3.1 Flash Image (Nano Banana 2) is het snelste native beeldgeneratiemodel van Google met denksupport, conversatiebeeldgeneratie en bewerking.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) levert Pro-niveau beeldkwaliteit op Flash-snelheid met ondersteuning voor multimodale chat.",
"gemini-3.1-flash-image-preview:image.description": "Gemini 3.1 Flash Image (Nano Banana 2) is het snelste native beeldgeneratiemodel van Google met ondersteuning voor denken, conversatiegerichte beeldgeneratie en bewerking.",
"gemini-3.1-flash-lite-preview.description": "Gemini 3.1 Flash-Lite Preview is het meest kostenefficiënte multimodale model van Google, geoptimaliseerd voor grootschalige agenttaken, vertaling en gegevensverwerking.",
"gemini-3.1-flash-lite.description": "Gemini 3.1 Flash-Lite is Google's meest kostenefficiënte multimodale model, geoptimaliseerd voor grootschalige agenttaken, vertaling en gegevensverwerking.",
"gemini-3.1-pro-preview.description": "Gemini 3.1 Pro Preview verbetert Gemini 3 Pro met verbeterde redeneercapaciteiten en voegt ondersteuning toe voor een gemiddeld denkniveau.",
@@ -734,8 +730,6 @@
"grok-4-fast-reasoning.description": "We zijn verheugd Grok 4 Fast uit te brengen, onze nieuwste vooruitgang in kosteneffectieve redeneermodellen.",
"grok-4.20-0309-non-reasoning.description": "Een niet-redenerende variant voor eenvoudige gebruiksscenario's.",
"grok-4.20-0309-reasoning.description": "Intelligent, razendsnel model dat redeneert voordat het reageert.",
"grok-4.20-beta-0309-non-reasoning.description": "Een non-reasoning variant voor eenvoudige gebruiksscenario's.",
"grok-4.20-beta-0309-reasoning.description": "Intelligent, razendsnel model dat redeneert voordat het reageert.",
"grok-4.20-multi-agent-0309.description": "Een team van 4 of 16 agents, uitblinkend in onderzoeksgebruiksscenario's. Ondersteunt momenteel geen client-side tools. Ondersteunt alleen xAI server-side tools (bijv. X Search, Web Search tools) en remote MCP tools.",
"grok-4.3.description": "Het meest waarheidsgetrouwe grote taalmodel ter wereld",
"grok-4.description": "Het nieuwste vlaggenschip van Grok met ongeëvenaarde prestaties in taal, wiskunde en redeneervermogen — een echte alleskunner. Momenteel verwijst het naar grok-4-0709; vanwege beperkte middelen is de prijs tijdelijk 10% hoger dan de officiële prijs en wordt verwacht later terug te keren naar de officiële prijs.",
@@ -1220,8 +1214,6 @@
"qwq.description": "QwQ is een redeneermodel binnen de Qwen-familie. In vergelijking met standaard instructie-getrainde modellen biedt het denk- en redeneervermogen dat de prestaties op complexe problemen aanzienlijk verbetert. QwQ-32B is een middelgroot redeneermodel dat zich kan meten met topmodellen zoals DeepSeek-R1 en o1-mini.",
"qwq_32b.description": "Middelgroot redeneermodel binnen de Qwen-familie. In vergelijking met standaard instructie-getrainde modellen verbeteren QwQs denk- en redeneervermogen de prestaties op complexe problemen aanzienlijk.",
"r1-1776.description": "R1-1776 is een na-getrainde variant van DeepSeek R1, ontworpen om ongecensureerde, onbevooroordeelde feitelijke informatie te bieden.",
"seedance-1-5-pro-251215.description": "Seedance 1.5 Pro van ByteDance ondersteunt tekst-naar-video, afbeelding-naar-video (eerste frame, eerste+laatste frame) en audiogeneratie gesynchroniseerd met visuals.",
"seedream-5-0-260128.description": "ByteDance-Seedream-5.0-lite van BytePlus biedt web-retrieval-augmented generatie voor realtime informatie, verbeterde interpretatie van complexe prompts en verbeterde referentieconsistentie voor professionele visuele creatie.",
"solar-mini-ja.description": "Solar Mini (Ja) breidt Solar Mini uit met focus op Japans, terwijl het efficiënte, sterke prestaties in Engels en Koreaans behoudt.",
"solar-mini.description": "Solar Mini is een compact LLM dat beter presteert dan GPT-3.5, met sterke meertalige ondersteuning voor Engels en Koreaans, en biedt een efficiënte oplossing met een kleine voetafdruk.",
"solar-pro.description": "Solar Pro is een intelligent LLM van Upstage, gericht op instructieopvolging op een enkele GPU, met IFEval-scores boven de 80. Momenteel ondersteunt het Engels; de volledige release stond gepland voor november 2024 met uitgebreidere taalondersteuning en langere context.",
@@ -1233,7 +1225,9 @@
"sophnet/deepseek-v3.2.description": "DeepSeek V3.2 is een model dat een balans vindt tussen hoge rekenefficiëntie en uitstekende redeneer- en agentprestaties.",
"sora-2-pro.description": "Sora 2 Pro is ons state-of-the-art, meest geavanceerde mediagenereermodel, dat video's genereert met gesynchroniseerd geluid. Het kan rijk gedetailleerde, dynamische clips maken vanuit natuurlijke taal of afbeeldingen.",
"sora-2.description": "Sora 2 is ons nieuwe krachtige mediagenereermodel, dat video's genereert met gesynchroniseerd geluid. Het kan rijk gedetailleerde, dynamische clips maken vanuit natuurlijke taal of afbeeldingen.",
"spark-x.description": "X2 Capaciteitenoverzicht: 1. Introduceert dynamische aanpassing van redeneermodus, gecontroleerd via het `thinking` veld. 2. Uitgebreide contextlengte: 64K invoertokens en 128K uitvoertokens. 3. Ondersteunt Function Call-functionaliteit.",
"spark-x1.5.description": "X1.5 updates: (1) voegt een dynamische denkmodus toe die wordt bestuurd door het veld `thinking`; (2) grotere contextlengte met 64K invoer en 64K uitvoer; (3) ondersteunt FunctionCall.",
"spark-x2-flash.description": "Spark X2-Flash maakt gebruik van een MoE (Mixture of Experts) architectuur met in totaal 30 miljard parameters en ondersteunt een contextvenster tot 256K. Het claimt aanzienlijke verbeteringen in agentische en codeermogelijkheden en is getraind op een cluster van Ascend 910B AI-processors.",
"spark-x2.description": "X2 Capaciteiten Overzicht: 1. Introduceert dynamische aanpassing van de redeneermodus, bestuurd via het veld `thinking`. 2. Uitgebreide contextlengte: 64K invoertokens en 128K uitvoertokens. 3. Ondersteunt Function Call-functionaliteit.",
"stable-diffusion-3-medium.description": "Het nieuwste tekst-naar-beeldmodel van Stability AI. Deze versie verbetert de beeldkwaliteit, tekstbegrip en stijlvariatie aanzienlijk, interpreteert complexe natuurlijke taal nauwkeuriger en genereert preciezere, gevarieerdere beelden.",
"stable-diffusion-3.5-large-turbo.description": "Stable Diffusion 3.5 Large Turbo richt zich op hoogwaardige beeldgeneratie met sterke detaillering en nauwkeurige scènes.",
"stable-diffusion-xl-base-1.0.description": "Een open-source tekst-naar-beeldmodel van Stability AI met toonaangevende creatieve beeldgeneratie. Het heeft sterk instructiebegrip en ondersteunt omgekeerde promptdefinities voor nauwkeurige generatie.",
@@ -1355,7 +1349,6 @@
"x-ai/grok-4.1-fast.description": "Grok 4.1 Fast is xAIs model met hoge verwerkingssnelheid en lage kosten (ondersteunt een contextvenster van 2M), ideaal voor toepassingen met hoge gelijktijdigheid en lange contexten.",
"x-ai/grok-4.description": "Grok 4 is xAI's toonaangevende model voor redenering met sterke multimodale capaciteiten.",
"x-ai/grok-code-fast-1.description": "Grok Code Fast 1 is xAI's snelle codemodel met leesbare, gebruiksvriendelijke output voor engineers.",
"x1.description": "X1.5 updates: (1) voegt dynamische denkmodus toe, gecontroleerd door het `thinking` veld; (2) grotere contextlengte met 64K invoer en 64K uitvoer; (3) ondersteunt FunctionCall.",
"xai/grok-2-vision.description": "Grok 2 Vision blinkt uit in visuele taken en levert SOTA-prestaties op visuele wiskundige redenering (MathVista) en documentvragen (DocVQA). Het verwerkt documenten, grafieken, diagrammen, schermafbeeldingen en foto's.",
"xai/grok-2.description": "Grok 2 is een geavanceerd model met state-of-the-art redenering, sterke chat-, codeer- en redeneercapaciteiten, en scoort hoger dan Claude 3.5 Sonnet en GPT-4 Turbo op LMSYS.",
"xai/grok-3-fast.description": "xAIs vlaggenschipmodel blinkt uit in zakelijke toepassingen zoals data-extractie, codering en samenvatting, met diepgaande domeinkennis in financiën, gezondheidszorg, recht en wetenschap. De snelle variant draait op snellere infrastructuur voor veel snellere reacties tegen hogere kosten per token.",
+21 -21
View File
@@ -69,9 +69,22 @@
"builtins.lobe-agent-management.render.installPlugin.plugin": "Plugin",
"builtins.lobe-agent-management.render.installPlugin.success": "Succesvol geïnstalleerd",
"builtins.lobe-agent-management.title": "Agentbeheer",
"builtins.lobe-agent-marketplace.apiName.showAgentMarketplace": "Open agentenmarktplaats",
"builtins.lobe-agent-marketplace.apiName.submitAgentPick": "Dien agentkeuzes in",
"builtins.lobe-agent-marketplace.title": "Agentenmarktplaats",
"builtins.lobe-agent.apiName.callSubAgent": "Roep sub-agent aan",
"builtins.lobe-agent.apiName.callSubAgent.completed": "Sub-agent verzonden: ",
"builtins.lobe-agent.apiName.callSubAgent.loading": "Sub-agent verzenden: ",
"builtins.lobe-agent.apiName.callSubAgents": "Roep sub-agents aan",
"builtins.lobe-agent.apiName.clearTodos": "Wis taken",
"builtins.lobe-agent.apiName.clearTodos.modeAll": "alle",
"builtins.lobe-agent.apiName.clearTodos.modeCompleted": "voltooid",
"builtins.lobe-agent.apiName.clearTodos.result": "Wis <mode>{{mode}}</mode> taken",
"builtins.lobe-agent.apiName.createPlan": "Maak plan",
"builtins.lobe-agent.apiName.createPlan.result": "Maak plan: <goal>{{goal}}</goal>",
"builtins.lobe-agent.apiName.createTodos": "Maak taken",
"builtins.lobe-agent.apiName.updatePlan": "Werk plan bij",
"builtins.lobe-agent.apiName.updatePlan.completed": "Voltooid",
"builtins.lobe-agent.apiName.updatePlan.modified": "Aangepast",
"builtins.lobe-agent.apiName.updateTodos": "Werk taken bij",
"builtins.lobe-agent.title": "Lobe Agent",
"builtins.lobe-claude-code.agent.instruction": "Instructie",
"builtins.lobe-claude-code.agent.result": "Resultaat",
"builtins.lobe-claude-code.todoWrite.allDone": "Alle taken voltooid",
@@ -139,24 +152,6 @@
"builtins.lobe-group-management.inspector.executeAgentTasks.title": "Taken toewijzen aan:",
"builtins.lobe-group-management.inspector.speak.title": "Aangewezen Agent spreekt:",
"builtins.lobe-group-management.title": "Groepscoördinator",
"builtins.lobe-gtd.apiName.clearTodos": "Taken wissen",
"builtins.lobe-gtd.apiName.clearTodos.modeAll": "alle",
"builtins.lobe-gtd.apiName.clearTodos.modeCompleted": "voltooid",
"builtins.lobe-gtd.apiName.clearTodos.result": "<mode>{{mode}}</mode> taken gewist",
"builtins.lobe-gtd.apiName.completeTodos": "Taken voltooien",
"builtins.lobe-gtd.apiName.createPlan": "Plan maken",
"builtins.lobe-gtd.apiName.createPlan.result": "Plan aangemaakt: <goal>{{goal}}</goal>",
"builtins.lobe-gtd.apiName.createTodos": "Taken aanmaken",
"builtins.lobe-gtd.apiName.execTask": "Taak uitvoeren",
"builtins.lobe-gtd.apiName.execTask.completed": "Taak aangemaakt: ",
"builtins.lobe-gtd.apiName.execTask.loading": "Taak wordt aangemaakt: ",
"builtins.lobe-gtd.apiName.execTasks": "Taken uitvoeren",
"builtins.lobe-gtd.apiName.removeTodos": "Taken verwijderen",
"builtins.lobe-gtd.apiName.updatePlan": "Plan bijwerken",
"builtins.lobe-gtd.apiName.updatePlan.completed": "Voltooid",
"builtins.lobe-gtd.apiName.updatePlan.modified": "Aangepast",
"builtins.lobe-gtd.apiName.updateTodos": "Taken bijwerken",
"builtins.lobe-gtd.title": "Taakhulpmiddelen",
"builtins.lobe-knowledge-base.apiName.readKnowledge": "Bibliotheekinhoud lezen",
"builtins.lobe-knowledge-base.apiName.searchKnowledgeBase": "Bibliotheek doorzoeken",
"builtins.lobe-knowledge-base.inspector.andMoreFiles": "en nog {{count}}",
@@ -317,6 +312,8 @@
"builtins.lobe-web-onboarding.apiName.finishOnboarding": "Onboarding voltooien",
"builtins.lobe-web-onboarding.apiName.readDocument": "Document lezen",
"builtins.lobe-web-onboarding.apiName.saveUserQuestion": "Gebruikersvraag opslaan",
"builtins.lobe-web-onboarding.apiName.showAgentMarketplace": "Stel agententeam samen",
"builtins.lobe-web-onboarding.apiName.submitAgentPick": "Dien agentkeuzes in",
"builtins.lobe-web-onboarding.apiName.updateDocument": "Document bijwerken",
"builtins.lobe-web-onboarding.apiName.writeDocument": "Document schrijven",
"builtins.lobe-web-onboarding.docType.persona": "Gebruikerspersona",
@@ -327,6 +324,9 @@
"builtins.lobe-web-onboarding.inspector.hunkCount_other": "{{count}} wijzigingen",
"builtins.lobe-web-onboarding.inspector.interests_one": "{{count}} interesse",
"builtins.lobe-web-onboarding.inspector.interests_other": "{{count}} interesses",
"builtins.lobe-web-onboarding.render.agent": "Agent",
"builtins.lobe-web-onboarding.render.fullName": "Volledige naam",
"builtins.lobe-web-onboarding.render.interests": "Interesses",
"builtins.lobe-web-onboarding.title": "Gebruikersonboarding",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.delete": "Verwijderen",
"builtins.lobe-web-onboarding.updateDocument.hunkMode.deleteLines": "Regels verwijderen",
-1
View File
@@ -33,7 +33,6 @@
"jina.description": "Opgericht in 2020, is Jina AI een toonaangevend zoek-AI-bedrijf. De zoekstack omvat vectormodellen, herordenaars en kleine taalmodellen om betrouwbare, hoogwaardige generatieve en multimodale zoekapps te bouwen.",
"kimicodingplan.description": "Kimi Code van Moonshot AI biedt toegang tot Kimi-modellen, waaronder K2.5, voor coderingstaken.",
"lmstudio.description": "LM Studio is een desktopapplicatie voor het ontwikkelen en experimenteren met LLMs op je eigen computer.",
"lobehub.description": "LobeHub Cloud gebruikt officiële API's om toegang te krijgen tot AI-modellen en meet het gebruik met Credits die gekoppeld zijn aan modeltokens.",
"longcat.description": "LongCat is een reeks generatieve AI-grote modellen die onafhankelijk zijn ontwikkeld door Meituan. Het is ontworpen om de productiviteit binnen ondernemingen te verbeteren en innovatieve toepassingen mogelijk te maken door middel van een efficiënte computationele architectuur en sterke multimodale mogelijkheden.",
"minimax.description": "Opgericht in 2021, bouwt MiniMax algemene AI met multimodale fundamentele modellen, waaronder tekstmodellen met biljoenen parameters, spraakmodellen en visiemodellen, evenals apps zoals Hailuo AI.",
"minimaxcodingplan.description": "MiniMax Token Plan biedt toegang tot MiniMax-modellen, waaronder M2.7, voor coderingstaken via een abonnement met vaste kosten.",

Some files were not shown because too many files have changed in this diff Show More