fix: add no-cache header to SPA HTML entry point
Prevent stale SPA HTML from being served after server upgrades.
JS/CSS assets still cache normally via hashed filenames.
* 🐛 fix(desktop): remove electron-liquid-glass to fix click event blocking
The electron-liquid-glass native addon was blocking all click events in the
Electron desktop app window. Remove the dependency and restore vibrancy-based
transparency with semi-transparent body background via `.desktop` CSS class.
* 🔨 chore(desktop): remove electron-liquid-glass from native modules config
* ♻️ refactor: replace per-message useNewScreen with centralized useConversationSpacer
Replace the old per-message min-height approach with a single spacer element appended to the virtual list, simplifying scroll-to-top UX when user sends a new message.
* 🔧 refactor: streamline handleSendButton logic and enhance editor focus behavior
Removed redundant editor null check and added double requestAnimationFrame calls to ensure the editor is focused after sending a message.
Signed-off-by: Innei <tukon479@gmail.com>
---------
Signed-off-by: Innei <tukon479@gmail.com>
* 🐛 fix: clear input immediately on send to preserve drafts typed during streaming
Move inputMessage reset before the async streaming lifecycle so text
entered while the assistant is responding is not overwritten on completion.
Also normalize null/undefined in operation context matching so that
cancelOperations works correctly in null-topic sessions.
Fixes LOBE-2647
* 🐛 fix: resolve TS2322 null-vs-undefined type error in useOperationState test
* ✨ feat(desktop): Linux window specialization
- Add minimize/maximize/close buttons for Linux (WinControl)
- Linux: no tray, close main window quits app
- Linux: native window shadow and opaque background
- i18n for window control tooltips
Made-with: Cursor
* 🌐 i18n: add window control translations for all locales
Made-with: Cursor
* 🐛 fix(desktop): show WinControl in SimpleTitleBar only on Linux
Made-with: Cursor
* 🐛 fix(desktop): limit custom titlebar controls to Linux
Avoid rendering duplicate window controls on Windows and keep the Linux maximize button in sync with the current window state.
Made-with: Cursor
---------
Co-authored-by: LiJian <onlyyoulove3@gmail.com>
* style: update claude 4.6 series 1M contextWindow
* chore: cleanup bedrock search tag
chore: cleanup bedrock retired model
chore: cleanup bedrock retired model
chore: cleanup bedrock retired model
* fix: fix ci test
* 💄 style: remove platform-specific Spotlight reference from searchLocalFiles
Replace "using Spotlight (macOS) or native search" with "using native search"
since the actual search implementation is platform-dependent and the LLM
doesn't need to know the specific backend.
Fixes LOBE-5778
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ⚡️ perf: remove duplicate API descriptions from tool system prompt
API identifiers and descriptions are already in the tools schema passed
via the API tools parameter. Repeating them in the system prompt wastes
tokens. Now only tools with systemRole (usage instructions) are injected.
Also rename XML tags: plugins→tools, collection→tool,
collection.instructions→tool.instructions
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* 💄 style: inject tool description when no systemRole instead of skipping
Tools without systemRole now show their description as <tool> children.
Tools with systemRole use <tool.instructions> wrapper as before.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* 💄 style: always emit <tool> tag, fallback to "no description"
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* update tools
* fix
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ✨ feat: inject all installed skills into <available_skills> for AI discovery
Previously, only skills explicitly added to the agent's plugins list appeared
in <available_skills>. Now all installed skills are exposed so the AI can
discover and activate them via activateSkill.
Changes:
- Frontend: use getAllSkills() instead of getEnabledSkills(plugins)
- Backend: pass skillMetas through createOperation → RuntimeExecutors → serverMessagesEngine
- Add skillsConfig support to serverMessagesEngine
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* 🐛 fix: use DB + builtin skills for available_skills instead of provider manifests
lobehubSkillManifests are tool provider manifests (per-provider, containing
tool APIs), not skill metadata. Using them for <available_skills> incorrectly
showed provider names (e.g. "Arvin Xu") as skills.
Now fetches actual skills from AgentSkillModel (DB) + builtinSkills for correct
<available_skills> injection.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* 💄 style: use XML structure for online-devices in system prompt
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ♻️ refactor: extract online-devices prompt to @lobechat/prompts package
Move device XML prompt generation from builtin-tool-remote-device into
the shared prompts package for reusability and consistency.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ✅ test: add failing tests for Remote Device suppression when auto-activated
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ⚡️ perf: suppress Remote Device tool when device is auto-activated
When a device is auto-activated (single device in IM/Bot or bound device),
the Remote Device management tool (listOnlineDevices, activateDevice) is
unnecessary — saves ~500 tokens of system prompt + 2 tool functions.
- Add autoActivated flag to deviceContext
- Move activeDeviceId computation before tool engine creation
- Disable Remote Device in enableChecker when autoActivated
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* update system role
* update system role
* ♻️ refactor: use agentId instead of slug for OpenAPI responses model field
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* 🐛 fix: use JSON round-trip instead of structuredClone in InMemoryAgentStateManager
structuredClone fails with DataCloneError when state contains non-cloneable
objects like DOM ErrorEvent (from Neon DB WebSocket errors).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* 🐛 fix: only inject available_skills when tools are enabled
Restore plugins guard to prevent skills injection when tool use is
disabled (plugins is undefined), fixing 28 test failures.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ✅ test: update system message assertions for skills injection
Use stringContaining instead of exact match for system message content,
since available_skills may now be appended after the date.
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: use jsonb ? operator instead of ->> to avoid Neon rt_fetch bug
The ->> operator in WHERE clauses triggers a Neon-specific
`rt_fetch used out-of-bounds` error. Switch to the ? operator
which is semantically equivalent for checking key existence.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* ♻️ refactor: centralize NavBar dev mode logic into useNavLayout hook
Extract scattered isDevMode checks from Nav, BottomMenu, Footer, and
UserPanel into a single useNavLayout hook with declarative devOnly
metadata. Also restore dev-mode-gated home page modules and fix
LangButton visual alignment in UserPanel.
* ✅ test: update PanelContent test to match LangButton Menu removal
When a builtin tool executor is not found, invokeBuiltinTool now returns
a structured error object instead of silently returning undefined. Also
adds a fallback in call_tool executor for undefined results to prevent
agent loop from terminating abnormally.
Fixes LOBE-5318
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* 🐛 fix(desktop): update bundled agent-browser to v0.20.1 and align native-mode docs
Upgrade desktop bundled agent-browser to 0.20.1 and remove obsolete AGENT_BROWSER_NATIVE runtime override since native mode is now default. Update builtin agent-browser skill descriptions to reflect the new default behavior.
Made-with: Cursor
* ✨ feat: enable agent-browser skill on Windows desktop
Made-with: Cursor
* 🔧 refactor: remove isWindows from ToolAvailabilityContext interface
Updated the ToolAvailabilityContext interface to remove the isWindows property, simplifying the context checks in the isBuiltinSkillAvailableInCurrentEnv function.
Signed-off-by: Innei <tukon479@gmail.com>
---------
Signed-off-by: Innei <tukon479@gmail.com>
* update skills
* 🐛 fix: respect agent-level memory config priority over user settings
Agent chatConfig.memory.enabled now takes priority. Falls back to user-level
memory setting when agent config is absent.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* 🐛 fix: resolve tsgo type error in memory integration test
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* 🌐 i18n: add auto top-up payment method hint translations
* ♻️ refactor: split Stats into separate settings tab and rename Subscription group to Plans
* 🌐 i18n: update auto top-up payment method hint copy
* 🌐 i18n: add auto top-up payment method hint translations for all locales
* 🌐 i18n: rename Subscription Plans tab to Plans
* 🌐 i18n: add high usage FAQ, rename Text Generation to Chat Message, rename tab.plans
