Open
Conversation
…hared UI (#13470) * ♻️ refactor: unify tool content formatting with ComputerRuntime and shared UI components Introduce `@lobechat/tool-runtime` with `ComputerRuntime` abstract class to ensure consistent content formatting (via `formatCommandResult`, `formatFileContent`, etc.) across local-system, cloud-sandbox, and skills packages. Create `@lobechat/shared-tool-ui` to share Render and Inspector components, eliminating duplicated UI code across tool packages. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix: address review issues — state mapping for renders and IPC param denormalization - Add legacy state field mappings in local-system executor (listResults, fileContent, searchResults) for backward compatibility with existing render components - Add denormalizeParams in LocalSystemExecutionRuntime to map ComputerRuntime params back to IPC-expected field names (file_path, items, shell_id, etc.) - Fix i18n type casting for dynamic translation keys in shared-tool-ui inspectors Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ♻️ refactor: inject render capabilities via context, unify state shape for cross-package render reuse - Add ToolRenderContext with injectable capabilities (openFile, openFolder, isLoading, displayRelativePath) to shared-tool-ui - Update local-system render components (ReadLocalFile, ListFiles, SearchFiles, MoveLocalFiles, FileItem) to use context instead of direct Electron imports - Enrich ReadFileState with render-compatible fields (filename, fileType, charCount, loc, totalCharCount) - Cloud-sandbox now fully reuses local-system renders — renders degrade gracefully when capabilities are not provided (no open file buttons in sandbox) - Remove executor-level state mapping hacks Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix: fix sandbox render bugs — SearchFiles, GrepContent, MoveFiles, GlobFiles - SearchFiles: ensure results is always an array (not object passthrough) - GrepContent: update formatGrepResults to support object matches `{path, content, lineNumber}` alongside string matches - MoveFiles: render now handles both IPC format (items/oldPath/newPath) and ComputerRuntime format (operations/source/destination) - GlobFiles: fallback totalCount to files.length when API returns 0 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix: unify SearchLocalFiles inspector with shared factory SearchLocalFiles inspector now supports all keyword field variants (keyword, keywords, query) and reads from unified state (results/totalCount). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix: handle missing path in grep matches to avoid undefined display Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix: improve render field compatibility for sandbox - EditLocalFile render: support both file_path (IPC) and path (sandbox) args - SearchFiles render: support keyword/keywords/query arg variants - FileItem: derive name from path when not provided Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix: add missing cloud-sandbox i18n key for noResults Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…buttons (#13495) 🐛 fix(electron): add nodrag to userinfo dropdown menus Add `-webkit-app-region: no-drag` to ThemeButton and LangButton dropdown popups to prevent Electron from capturing click events when the dropdown appears in the titlebar drag region. https://claude.ai/code/session_01K6FLLJ4PMhKWqbRmrGEZkS Co-authored-by: Claude <noreply@anthropic.com>
…ed builtin models (#13514)
Co-authored-by: YuTengjing <ytj2713151713@gmail.com>
* ♻️ refactor: remove @lobehub/chat-plugin-sdk dependency Plugins have been deprecated. This removes the SDK entirely: - Define built-in ToolManifest, ToolManifestSettings, ToolErrorType types - Delete src/features/PluginsUI/ (plugin iframe rendering) - Delete src/store/tool/slices/oldStore/ (deprecated plugin store) - Delete src/server/services/pluginGateway/ (plugin gateway) - Delete src/app/(backend)/webapi/plugin/gateway/ (plugin API route) - Migrate all ~50 files from SDK imports to @lobechat/types - Remove @lobehub/chat-plugin-sdk, @lobehub/chat-plugins-gateway deps - Remove @swagger-api/apidom-reference override and patch Fixes LOBE-6655 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix: add missing getInstalledPlugins mock in customPlugin test Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🔧 chore: increase Vercel build memory limit to 8192MB The 6144MB limit was causing OOM during Vite SPA chunk rendering. Aligned with other build commands that already use 8192MB. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ♻️ refactor: unify default tool type to builtin and fix CustomRender - Remove `invokeDefaultTypePlugin` — default type now falls through to builtin in both server and client execution paths - Fix `CustomRender` to actually render builtin tool components via `getBuiltinRender` instead of always returning null - Increase SPA build memory limit from 7168MB to 8192MB to fix OOM Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ♻️ refactor: remove legacy plugin gateway and type-specific invocations - Delete `runPluginApi`, `internal_callPluginApi`, `invokeMarkdownTypePlugin`, `invokeStandaloneTypePlugin` - Remove plugin gateway endpoint (`/webapi/plugin/gateway`) from URL config - Remove special `builtin → default` runtimeType mapping in plugin model - Clean up unused imports and related tests Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix: add 'builtin' to runtimeType union to fix type error Use ToolManifestType instead of inline union for runtimeType fields so that 'builtin' is included as a valid type. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ✨ feat(cli): register task command and add kanban board view Register the missing `registerTaskCommand` in program.ts so `lh task` commands are accessible. Add `--board` flag to `task list` that renders a kanban-style view grouping tasks by status columns (backlog, running, paused, completed, etc.) with color-coded borders. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * update --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* 🐛 fix: stream tool call arguments incrementally in Response API The tool_calling stream chunks contain accumulated arguments (not deltas), but the Response API was treating each chunk as a complete independent output_item — creating a new lifecycle (added → delta → done) per token and incrementing output_index to 90+. Fix: track active tool calls by call_id and compute true incremental deltas by slicing off previously-seen content. Each tool call now gets a single stable output_item with proper streaming deltas, finalized only when the stream ends or tool execution begins. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix: clear stale tool-call state on LLM stream retry When call_llm retries after a failed attempt, activeToolCalls may contain entries from the failed stream that never received a tool_end. Without clearing, finishActiveToolCalls would emit phantom function_call done events and misalign output_index for the successful attempt. Reset the map on stream_retry. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…lable tools (#13417) ♻️ refactor: extract server tool discovery config builder
* ✨ feat: implement AI input auto-completion with ReactAutoCompletePlugin Adds GitHub Copilot-style ghost text completion to the chat input, powered by a configurable system agent (disabled by default). Key changes: - Add `inputCompletion` system agent config (type, default, selector, i18n) - Create `chainInputCompletion` prompt chain (V2 few-shot, benchmarked) - Mount `ReactAutoCompletePlugin` in InputEditor when enabled - Wire `getMessages` through ChatInput store for conversation context - Add settings UI in Service Model page with enable toggle Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ✅ test: update systemAgent snapshot for inputCompletion Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix: restrict auto-complete context to visible user/assistant turns Filter getMessages to use displayMessages (active visible thread) instead of dbMessages (raw DB records including tool messages and inactive branches). Also limit to last 10 user/assistant turns to keep payload small and relevant. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ✨ feat: enable input completion by default Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ⚡️ perf: use non-streaming for input completion requests Autocomplete needs the full result before displaying ghost text, so streaming adds unnecessary overhead. Setting stream: false reduces latency by avoiding SSE chunking. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix: revert stream:false for input completion fetchPresetTaskResult uses fetchSSE internally which cannot handle non-streaming JSON responses, causing the editor to freeze after receiving the completion result. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ⚡️ perf: use non-streaming for input completion requests Autocomplete waits for the full result before displaying ghost text. fetchSSE handles non-streaming responses via its fallback path (response.clone().text()), avoiding SSE chunking overhead. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ⚡️ perf: skip contextEngineering for input completion Call getChatCompletion directly instead of fetchPresetTaskResult to avoid triggering agentDocument.getDocuments on every autocomplete request. Input completion only needs a simple LLM call with the prompt chain, not the full context engineering pipeline. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ♻️ refactor: revert to fetchPresetTaskResult for input completion Use the standard contextEngineering pipeline. The agentDocument overhead will be addressed separately. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
📝 docs: add SECURITY.md with vulnerability reporting policy Define supported versions, reporting guidelines, response timeline, scope (in/out), and disclosure policy for security vulnerabilities. Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
) ✨ feat: add Task store with service layer, selectors, and 4 slices (LOBE-6597) Implement frontend Task system state management: - Service layer wrapping all TRPC task/brief endpoints - List slice: SWR fetch by agent, list/kanban view mode - Detail slice: CRUD with optimistic updates, immer reducer - Lifecycle slice: run/pause/cancel/complete/resume, heartbeat ping - Config slice: checkpoint, review, brief ops (model config deferred to LOBE-6634) - Selectors: list (kanban columns, display status), detail (field accessors, operation guards), activity (sorted/filtered) - Types derived from TRPC inference (TaskListItem, TaskStatus) - 118 tests across 9 test files Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…SS-to-RCE (#13529) * 🔒 fix: sanitize HTML artifact content and sandbox iframe to prevent XSS-to-RCE - Add sanitizeHTMLContent() using DOMPurify to strip dangerous tags (script, embed, object, etc.) and all on* event handler attributes - Add sandbox="" attribute to HTML artifact iframe to block all script execution and parent frame access - Replace doc.write() with srcDoc for cleaner rendering - Extract shared FORBID_EVENT_HANDLERS list to DRY up SVG and HTML sanitization Ref: GHSA-xq4x-622m-q8fq Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix: correct import path from @lobehub/utils to @lobechat/utils The package name is @lobechat/utils, not @lobehub/utils. This caused a build failure in Electron desktop app. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…fig incompatibility (#13524) * 🐛 fix(model-runtime): resolve Vertex AI $ref schema error and toolConfig incompatibility 1. Dereference $ref in JSON Schema before sending to Google/Vertex AI — the memory tool manifest (from neko's recent refactor) uses $ref which Vertex AI rejects. 2. Skip includeServerSideToolInvocations for Vertex AI — only Google AI supports it. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix(model-runtime): preserve sibling schema fields when resolving $ref When a schema node has $ref plus sibling keys (e.g. description from allOf unwrapping), the resolved definition now merges with those siblings instead of dropping them. This preserves argument-level descriptions for fields like timeIntent, improving tool-call quality. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ♻️ refactor: support minimal execAgent resume flow * ♻️ refactor execAgent resume to caller-owned continuation context * 📝 fix execAgent topic metadata comment * 🚚 revert non-essential public execAgent resume changes * 🚚 narrow execAgent resume changes to internal service scope * 🚚 keep execAgent resume scoped to internal service * 📝 restore taskId in execAgent runtime appContext * ✨ add agent eval trajectory resume * ♻️ route agent eval resume through workflow * 🩹 tighten eval resume workflow semantics * ♻️ refine agent eval resume semantics * ♻️ simplify resume workflow dispatch * wip: rm redundancy interfaces * wip: trim code * wip: remove unuse * wip: add eval detail resume btn * 🐛 fix: message chains * 🐛 fix: incorrect steps & cost count * 🐛 fix: should allow start from non-zero step * 🐛 fix: batch resume * 🐛 fix: import * ♻️ restore retry visibility guard in eval case table * 🐛 fix: should not check run status * 🐛 fix agent eval resume test regressions * 🐛 fix: allow retry pass@k trajectory * 🐛 fix eval case thread messages during run * 🐛 fix pass@k batch resume target resolution * 🐛 fix eval resume thread state handling * ♻️ simplify eval resume validation * 🚑 fix lint:ts interface order * wip: fix lint * 🐛 enforce max steps per resumed eval thread * 🐛 avoid topic-level max steps check for pass@k resumes
fix: slove the lobehub skill cant use activator to active
* ✨ support device binding in lh agent run * ✅ align device binding tests with current behavior
* fix: add the cronjob tools executiors * fix: should use mutate to refresh the cronjob when it changes && add it into backend runtime * fix: add the lost deps * fix: should await the delete servers
…#13525) Bumps [electron](https://github.com/electron/electron) from 41.0.2 to 41.0.3. - [Release notes](https://github.com/electron/electron/releases) - [Commits](electron/electron@v41.0.2...v41.0.3) --- updated-dependencies: - dependency-name: electron dependency-version: 41.0.3 dependency-type: direct:development ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
…is pending (#13847) * 🐛 fix(conversation): improve workflow display when user intervention is pending Made-with: Cursor * 🐛 fix(builtin-tool-activator): add ActivatedToolInfo typing to requestedTools for tsgo compat requestedTools was inferred as `{ identifier, name }[]` which lacks the `avatar` property required by `ActivatedToolInfo`, causing tsgo errors.
💄 style(chat): tighten `execServerAgentRuntime` loading copy Current text was trying to do too much in one line — status + two separate user affordances — and read as an explanation, not a status. Replaces it with a status-first line that mentions where the work is happening and the single reassurance users actually need. - EN: "Task is running in the server. You are safe to leave this page." - zh-CN: "任务正在服务器运行，您可以放心离开此页面。" Only en-US and zh-CN are edited; CI translates the rest from the default file. Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…ests (#13838) 🌐 chore: translate non-English comments to English in lambda router tests Translated all Chinese/CJK comments to English in 6 test files under src/server/routers/lambda/__tests__/. Code logic and string literals are unchanged; only explanatory comments were translated. Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* ✨ feat(builtin-tool-gtd): add server runtime for GTD tool
Implement server-side execution runtime so the GTD tool works when
agents run in a pure server context (bot platforms, async task workers,
QStash workflows). Previously only the client executor existed, which
relied on `useNotebookStore` and `notebookService` and would break on
the server.
- `packages/builtin-tool-gtd/src/ExecutionRuntime/index.ts`: pure
`GTDExecutionRuntime` class with an injected service interface,
covering createPlan/updatePlan/createTodos/updateTodos/clearTodos
and execTask/execTasks. Since server runtime has no stepContext,
todo state is read from / written back to the Plan document's
`metadata.todos` field.
- `src/server/services/toolExecution/serverRuntimes/gtd.ts`: factory
wiring `DocumentModel` + `TopicDocumentModel` into the runtime and
registering under `GTDIdentifier`.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ♻️ refactor(builtin-tool-gtd): share runtime logic between executor and server
Make the client executor a thin adapter over `GTDExecutionRuntime` so
all processing logic (todo reducer, plan CRUD flow, execTask state
builder, output formatting) lives in one place. Previously the server
runtime was a near-duplicate of the client executor.
- Expand `GTDRuntimeContext` with `currentTodos`, `messageId`, `signal`
so both callers can thread their environment through:
- client supplies `currentTodos` from stepContext / pluginState via
`getTodosFromContext`, and `messageId` for execTask parentMessageId
- server lets the runtime resolve todos from the plan document's
metadata when `currentTodos` is not supplied
- Split service surface into `updatePlan` (user-facing: goal / desc /
context — client routes through `useNotebookStore` to refresh SWR)
vs `updatePlanMetadata` (silent todos sync — client stays on the
raw `notebookService`)
- Runtime methods now return `BuiltinToolResult` (superset of
`BuiltinServerRuntimeOutput`), so `stop: true` on execTask /
execTasks is typed cleanly without `@ts-expect-error`
Net effect: `executor/index.ts` shrinks from 510 → 134 lines; the
server factory just maps models to the service interface.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
🐛 fix(toolEngineering): drop manifests missing `api` before feeding ToolsEngine `ToolsEngine.convertManifestsToTools` calls `manifest.api.map(...)` without a null check, so any manifest that is truthy but lacks a valid `api` array crashes the entire tools build with "Cannot read properties of undefined (reading 'map')". This takes down anything that touches the tools pipeline on that agent — including TokenTag in ChatInput, which is why users see the crash on the chat page load path. Manifests are merged from 5 sources (installed plugins, builtin tools, Klavis, LobeHub skills, caller-supplied extras), only some of which filter falsy entries, and none validate `api`. Guard defensively at the merge point and log the offending source + identifier so the underlying bad data can be traced. Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* improve style * improve style
…13860) * 🐛 fix(gateway): clean up paused server op after human approve/reject In Gateway mode with userInterventionConfig.approvalMode='ask', the paused execServerAgentRuntime op was never released — the loading spinner kept spinning after the user approved, rejected, or reject-and-continued, and reject-only silently did nothing on the server. - ToolAction.rejectToolCall now delegates to chatStore.rejectToolCalling so the Gateway resume op actually fires with decision='rejected'; previously it only mutated local intervention state and the server's paused op waited forever. - AgentRuntimeCoordinator treats waiting_for_human as end-of-stream so the coordinator emits agent_runtime_end when request_human_approve flips state, letting the client close the paused op via the normal terminal-event path. - conversationControl adds #completeRunningServerOps as a fallback guard in the approve/reject/reject-continue Gateway branches — if the server-side signal is delayed or missing, the client still clears the orphan op before starting the resume op. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix(gateway): defer paused-op cleanup until resume starts successfully If `executeGatewayAgent` failed (transient network/auth/server error), the paused `execServerAgentRuntime` op was already marked completed locally by the pre-call `#completeRunningServerOps`. Retries would then see no running server op, miss `#hasRunningServerOp`, and fall through to the non-Gateway client-mode path — while the backend was still paused awaiting human input. Snapshot the paused op IDs before the resume call and retire them only inside the try block after `executeGatewayAgent` resolves. On failure the running marker stays intact so a retry still lands on the Gateway branch and can re-issue the resume. The helper was renamed from `#completeRunningServerOps(context)` to `#completeOpsById(ids)` to reflect the new contract: callers must snapshot beforehand, not re-query at completion time (which would incorrectly match the new resume op too). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix(gateway): avoid double reject dispatch in reject-and-continue Now that `rejectToolCall` delegates to `chatStore.rejectToolCalling`, the chained `await get().rejectToolCall(...)` inside `rejectAndContinueToolCall` fired a full halting reject before the continue call. In Gateway mode that meant two resume ops on the same tool_call_id (`decision='rejected'` followed by `decision='rejected_continue'`) racing server-side; in client mode it duplicated reject bookkeeping that `chatStore.rejectAndContinueToolCalling` already handles internally. Drop the chained call and fire `onToolRejected` inline so hook semantics are preserved. `chatStore.rejectAndContinueToolCalling` is now the single entry point for both the rejection persist and the continue dispatch. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
🐛 fix(gateway): route approve/reject via lab flag, not transient server op state After the coordinator fix for `waiting_for_human` (#13860) the paused `execServerAgentRuntime` op is marked `completed` client-side as soon as the server emits `agent_runtime_end`. `startOperation` then runs `cleanupCompletedOperations(30_000)`, which deletes any op completed more than 30 seconds ago — so by the time the user sees the InterventionBar and clicks approve/reject, the running (or recently completed) server op is gone. The previous `#hasRunningServerOp` check therefore kept returning false against a live Gateway backend, flipping approve/reject into the client-mode `internal_execAgentRuntime` branch and stranding the server-side paused conversation. Switch the helper to `#shouldUseGatewayResume`, which checks the same `isGatewayModeEnabled()` lab flag used to route the initial send. The signal now mirrors how the conversation was dispatched and survives the op-cleanup window. New regression test exercises the post-coordinator-fix state: the paused `execServerAgentRuntime` op is explicitly `completed` before the approve call runs, and we still expect the Gateway branch to fire with `decision='approved'`. Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…nue (#13865) * ♻️ refactor(chat): remove reject-only button, unify to rejected_continue Server-side `decision='rejected'` and `decision='rejected_continue'` share the exact same code path — both surface the rejection to the LLM as user feedback. Having a separate "reject only" button added UI complexity without behavioural difference. - Remove the "仅拒绝" button from InterventionBar popover; the single "拒绝" button now calls `rejectAndContinueToolCall` directly - `rejectToolCalling` Gateway branch sends `rejected_continue` instead of `rejected` so all rejection paths use one decision value Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Update ApprovalActions.tsx * ✨ feat(tool): add executors field to BuiltinToolManifest and dispatch page-agent to client Add `executors?: ('client' | 'server')[]` to `BuiltinToolManifest` so each builtin tool declares where it can run. The server-side dispatch logic in `aiAgent/index.ts` now reads this field instead of hardcoding per-identifier checks. - `lobe-local-system`: `executors: ['client', 'server']` — runs on client via Electron IPC or server via Remote Device proxy - `lobe-page-agent`: `executors: ['client']` — requires EditorRuntime, client-only - Stdio MCP plugins still use the `customParams.mcp.type` heuristic (not manifest-driven) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…t` package (#13866) * ♻️ refactor: extract agent-stream into @lobechat/agent-gateway-client package Move the Agent Gateway WebSocket client from src/libs/agent-stream/ into a standalone workspace package at packages/agent-gateway-client/. This eliminates the duplicate AgentStreamEvent type in apps/cli and provides a single source of truth for the Gateway WS protocol types shared by SPA, server, and CLI consumers. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * add agent-gateway-client --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
fix: improve the skill execution error body back
…ler-tests (#13867) Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* ♻️ refactor: createAgent uses agentModel.create directly The createAgent router was still going through sessionModel.create, which is a legacy path that doesn't pass all agent fields (like agencyConfig) to the agents table. Switch to agentModel.create which directly inserts into the agents table with full field support. - Add CreateAgentSchema in types package for proper input validation - Remove dependency on insertAgentSchema from database package - Remove sessionId from CreateAgentResult Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🏷️ chore: mark session-based agent creation as deprecated Add @deprecated JSDoc tags to the legacy session-based agent creation path (session router, SessionService, SessionModel.create, session store, insertAgentSchema). New code should use agent.createAgent / agentModel.create directly. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix: honor groupId when creating agents Pass input.groupId as sessionGroupId to agentModel.create so that agents created from a sidebar folder are correctly assigned to that group. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * 🐛 fix: resolve type errors from createAgent refactor - Remove sessionId fallback in AddAgent.tsx and ForkAndChat.tsx - Use z.custom<T>() for agencyConfig and tts in CreateAgentSchema to match agentModel.create parameter types Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* 🐛 fix: default execAgent approval mode to headless Backend execAgent calls should run headlessly by default since only frontend scenarios require manual human approval. This prevents cron jobs and other server-side triggers from unexpectedly waiting for human intervention. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ✅ test: add regression test for headless approval default Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…mpt (#13872) Update `pageEditor.editorPlaceholder` from `Start writing your page. Press / to open the command menu` to `Press "/" for AI and commands.` across all supported locales and the default locale source.
…-pdf/svg Picked from canary commit 9f61b58. - Bump @react-pdf/renderer from ^4.3.2 to 4.4.1 - Pin @react-pdf/image to 3.0.4 via pnpm.overrides
* chore: update skills dir * chore: remove unused recent fetch actions and components * fix: recent delete functions * chore: update comments
…o title (#13877) * ♻️ refactor: add backgroundColor to TaskParticipant and rename name to title Add backgroundColor field and rename name→title in TaskParticipant interface to match agent avatar data. Add LobeAI fallback for inbox agent in getAgentAvatarsByIds when avatar/title are missing.
* feat: add some lost lobe-kb builtin tools * feat: add the list files and get file detail * feat: add the list files and get file detail * fix: update the search limit
* chore: add ENABLE_BOT_IN_DEV swtich * chore: add explicit judge
* update * update * 🔧 chore: update CLI build command in electron-builder and ensure proper newline in package.json * Changed the CLI build command from 'npm run build' to 'npm run build:cli' in electron-builder.mjs. * Added a newline at the end of package.json for consistency. Signed-off-by: Innei <tukon479@gmail.com> --------- Signed-off-by: Innei <tukon479@gmail.com> Co-authored-by: Innei <tukon479@gmail.com>
#### 💻 Change Type - [ ] ✨ feat - [ ] 🐛 fix - [ ] ♻️ refactor - [ ] 💄 style - [x] 👷 build - [ ] ⚡️ perf - [ ] ✅ test - [ ] 📝 docs - [ ] 🔨 chore #### 🔗 Related Issue - None #### 🔀 Description of Change - Extract the document history database changes from the feature branch onto a branch based on main. - Add the document history migration, schema, relations, model, and database tests only. - Exclude UI, router, and service-layer changes so the PR stays focused on the database layer. #### 🧪 How to Test - Run: cd packages/database && bunx vitest run --silent=passed-only src/models/__tests__/document.test.ts src/models/__tests__/documentHistory.test.ts - [x] Tested locally - [x] Added or updated tests - [ ] No tests needed #### 📸 Screenshots / Videos | Before | After | | ------ | ----- | | N/A | N/A | #### 📝 Additional Information - This PR intentionally targets main because the database migration needs to land on the release branch first.
* 🔨 chore: update .vscode/settings.json (#13894) * 🐛 fix(builtin-tool-local-system): honor glob scope in local system tool (#13875) Made-with: Cursor * 📝 docs: Update changelog docs and release skills (#13897) - Update changelog documentation format across all historical changelog files - Merge release-changelog-style skill into version-release skill - Update changelog examples with improved formatting and structure Made-with: Cursor --------- Co-authored-by: YuTengjing <ytj2713151713@gmail.com> Co-authored-by: Innei <i@innei.in>
# 🚀 LobeHub v2.1.50 (20260416) **Release Date:** April 16, 2026\ **Since v2.1.49:** 107 commits · 101 merged PRs · 13 contributors > This weekly release focuses on improving runtime stability and gateway execution consistency, while making Home/Recents workflows faster to navigate and easier to manage in daily use. --- ## ✨ Highlights - **Server-side Human Approval Flow** — Agent runtime now supports more reliable approve/reject/reject-continue handling in gateway mode, reducing stalled execution paths in long-running tasks. (#13829, #13863, #13873) - **Message Gateway End-to-End Hardening** — Gateway message flow, queue handling, tool callback routing, and stop interruption behavior were strengthened for better execution continuity. (#13761, #13816, #13820, #13815) - **Client Tool Execution in Gateway Mode** — Client-executor tools now run more predictably across gateway and desktop callers, with improved executor dispatch behavior. (#13792, #13790) - **Home / Recents / Sidebar Upgrade** — Sidebar layout, custom sort, recents operations, and profile actions were improved to reduce navigation friction in active sessions. (#13719, #13812, #13723, #13739, #13878, #13734) - **Agent Workspace and Documents Expansion** — Working panel and agent document workflows were expanded and polished for better day-to-day agent operations. (#13766, #13857) - **Provider and Model Compatibility Improvements** — Added GLM-5.1 support and refined model/provider edge-case handling, including schema and error-path fixes. (#13757, #13806, #13736, #13740) --- ## 🏗️ Core Agent & Architecture ### Agent runtime and intervention lifecycle - Added server-side human approval and improved runtime coordination across approve/reject decision paths. (#13829, #13863) - Improved interrupted-task handling and operation lifecycle consistency to reduce half-finished runtime states. (#13714) - Refined error classification and payload propagation so downstream surfaces receive clearer actionable errors. (#13736, #13740) ### Execution model and dispatch behavior - Introduced executor-aware runtime behavior to better separate client/server tool execution semantics. (#13758) - Improved tool/plugin resolution and manifest handling to avoid runtime failures on malformed inputs. (#13856, #13840, #13807) --- ## 📱 Gateway & Platform Integrations - Added message gateway support and strengthened queue/error behavior for more stable cross-channel execution. (#13761, #13816, #13820) - Improved gateway callback pipeline with protocol and API additions for `tool_execute` / `tool_result`. (#13762, #13764, #13765) - Improved bot/channel reliability and DM/slash handling in Discord-related paths. (#13805, #13724) --- ## 🖥️ CLI & User Experience - Improved CLI reliability across message/topic operations and build/minify-related paths. (#13731, #13888) - Added image-to-video options and improved command behavior for generation workflows. (#13788) - Improved desktop runtime behavior for remote fetch and Linux notification urgency handling. (#13789, #13782) --- ## 🔧 Tooling - Extracted gateway stream client into `@lobechat/agent-gateway-client` to centralize protocol usage and reduce duplication. (#13866) - Improved built-in tool coverage and runtime support, including GTD server runtime and missing lobe-kb tools. (#13854, #13876) - Updated skill and frontmatter consistency in workflow tooling. (#13730) --- ## 🔒 Security & Reliability - **Security:** Strengthened API key WS auth behavior and safer serverUrl forwarding in gateway-related auth paths. (#13824) - **Reliability:** Reduced runtime stalls by improving gateway stop/interrupt and approval-state routing behavior. (#13815, #13863, #13873) - **Reliability:** Added defensive guards for malformed tool manifests and non-string content edge cases. (#13856, #13753) --- ## 👥 Contributors **101 merged PRs** from **13 contributors** across **107 commits**. ### Community Contributors - @arvinxx - Runtime, gateway, and execution reliability improvements - @Innei - Navigation, workflow UX, and desktop/CLI refinements - @rdmclin2 - Sidebar, recents, and channel behavior updates - @ONLY-yours - Tooling/runtime fixes and model execution compatibility - @tjx666 - Model support and release/tooling maintenance - @nekomeowww - Memory and search-path stability fixes - @cy948 - CLI indexing and command flow fixes - @octo-patch - Local system runtime edge-case fixes - @djthread - Desktop runtime request reliability improvements - @rivertwilight - Documentation and changelog updates - @sudongyuer - Subscription/mobile support improvements - @Zhouguanyang - Provider/model configuration correctness fixes - @lobehubbot - Translation and maintenance automation support --- **Full Changelog**: v2.1.49...v2.1.50
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
20 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
See Commits and Changes for more details.
Created by
pull[bot] (v2.0.0-alpha.4)
Can you help keep this open source service alive? 💖 Please sponsor : )