v1.1.8

✨ Added

Plugins & Tools

• Official Plugin Distribution: Browse and download official plugins from the website, or install them with one click in the console Plugin Manager (#4482)
• QwenPaw Pet: Desktop pet companion plugin with animated pet window (#4418, #4516)
• CloudPaw — Alibaba Cloud Deployment: New plugin with multi-agent orchestration, IaC-driven cloud provisioning, and A2A streaming integration with Alibaba Cloud Skills Hub (#4362, #4423, #4506, #4524)
• Browser Robustness: Improved browser stability with crash recovery, idle timeout protection, and automatic cleanup on exit (#4306, #4350)
• Browser Tab Metadata: tabs action now returns the URL and title of each open tab (#4438)

Chat & Console

• Inbox Batch Operations: Redesigned Inbox with batch select and batch delete for managing messages more efficiently (#4358, #4493)
• Pinned Chat History Drawer: Pin the session drawer to keep it open alongside the chat (#4414, #4416, #4517)

Models & Providers

• Custom HTTP Headers & Auth Mode: Custom headers editor for all providers with auth mode selection (API Key vs Bearer Token) (#4413)
• Per-Model Token Limits: max_tokens and max_input_length are now configured per model in Settings → Models (#4417)

Agent System

• /make-skill Command: A new magic command for turning the current chat session into a reusable skill (#4282)
• Indonesian Agent Templates: Agent persona markdown templates and Asia/Jakarta timezone (#4287)
• Cron Job Timeout: Configurable timeout for cron jobs (default 120s) (#4425)

Security

• Skill Path Safety: Prevent path traversal attacks in skill directory operations (#4335)
• Backup Trust Controls: Verify backup integrity on import/restore with trust confirmation dialogs, and strengthen remote access controls (#4409, #4429)
• AgentMd Path Traversal Prevention: Prevent path traversal in agent memory file operations (#4511)
• Plugin API Auth: Plugin management APIs now require authentication (#4513)

Channels

• Matrix E2EE Verification: Password and access-token login with E2EE toggle and SAS device verification (#4120)
• Telegram Streaming Output: Real-time streaming replies with reasoning indicator support (#4318)
• DingTalk Streaming Cards: Real-time streaming replies via AI Card (Card message mode only) (#4420)
• Feishu CardKit Streaming: Real-time streaming replies via CardKit (#4480)

🔄 Changed

• Console Header Navigation: Consolidated header links into a Documentation dropdown with Tutorial, Feature Demos, Changelog, and FAQ entries (#3875)
• Feishu/Lark QR Code Domain: QR code API accepts query parameters (#4504)
• Stream Task Timeout: Increased from 300 to 1800 seconds for long-running streamed agent tasks (#4510)

🐛 Fixed

Channels

• WeCom Duplicate Placeholder: Suppress duplicate "Thinking…" stream on rapid consecutive messages (#4427)
• WeChat Poll Shutdown: Fix crash-on-exit and tight error loops in the WeChat polling thread (#4490)
• QQ Reconnect Loop: Prevent high-frequency reconnect on IP whitelist rejection (#4503)

Skills

• QA Agent Docs Packaging: QA agent now works correctly in all install methods (pip, Docker, desktop) — previously some docs might be missing (#4280)
• Skill Hub URL Validation: Fixed skill import failing for URLs with www. prefix (#4359)

Providers & Models

• Per-Model Rate Limiter: A rate limit on one model no longer blocks requests to other models (#4487)
• Per-Model Token Usage: Token usage summaries now include a per-model breakdown with prompt/completion token counts (#4476)

Console & UI

• SSE Connection Leak: Fixed SSE connections not closing on page navigation, which could exhaust browser connection limits (#4488)
• Cron Validation Errors: Cron creation/update returns localized, actionable error messages instead of generic server errors (#4495)
• Session Memory Persistence: /mission and /skill info responses are now persisted to session memory so they survive page reload (#4523)

📝 Documentation

• Website Feature Demos: Docs demo gallery with walkthrough videos for skills, doctor, and mission mode (#4507)

New Contributors

• @Morxi made their first contribution in #4120

Full Changelog: v1.1.7...v1.1.8

v1.1.8-beta.2

What's Changed

• refactor(console): Model performance optimization by @zhaozhuang521 in #4502
• perf(trace): batch append inbox trace events to reduce file I/O by @lalaliat in #4493
• add qwenpaw pet plugin by @Osier-Yi in #4418
• feat(channel): enhance QR code API to accept additional query paramet… by @zhijianma in #4504
• feat(model): add per-model max_tokens and migrate max_input_length from agent config by @qbc2016 in #4417
• fix(cron): return 422 for cron validation and show localized actionab… by @lalaliat in #4495
• plugin(cloudpaw): add automatic iac-code model configuration from QwenPaw by @xuanrui-L in #4506
• feat(skill): /make-skill command, new built-in skills by @Leirunlin in #4282
• fix(WeChat): graceful poll thread shutdown and exponential backoff on failures by @hongxicheng in #4490
• fix(QQ): Fix QQ Channel high-frequency reconnect on IP whitelist rejection by @hongxicheng in #4503
• perf(app): increase stream task timeout from 300 to 1800 seconds for … by @zhijianma in #4510
• chore(version): bumping version to 1.1.8b2 by @qbc2016 in #4508
• feat(feishu): add CardKit streaming card output by @hongxicheng in #4480
• feat(browser): add url and title to tabs action response by @weixizi in #4438
• fix(console): ChatSessionInitializer by @zhaozhuang521 in #4517
• perf(security): prevent path traversal in AgentMdManager file operations by @rayrayraykk in #4511
• perf(auth): close unauthenticated access to all plugin API routes by @rayrayraykk in #4513
• add dist/index.js file in plugin: qwenpaw-pet by @Osier-Yi in #4516
• feat(website):docs add functional demonstration, footer add douyin link by @yuluo1007 in #4507
• add plugin download to website by @yuanxs21 in #4482
• feat(console): add link to demo page in header url by @zhaozhuang521 in #3875
• fix(cli): correct typo in tool_results directory reference by @jinliyl in #4522
• plugin(cloudpaw): bump version to 0.0.2 with toolkit patching fix and i18n docs by @xuanrui-L in #4524
• fix(runner): persist /mission and /skill info responses to session me… by @rayrayraykk in #4523

Full Changelog: v1.1.8-beta.1...v1.1.8-beta.2

v1.1.8-beta.1

What's Changed

• chore(version): bumping version to 1.1.8b1 by @xieyxclack in #4346
• feat(plan mode): Strengthen plan reaffirm from the user message by @yuanxs21 in #4198
• fix(tool): browser implement activity tracking, crash monitoring, and lifecycle management by @weixizi in #4306
• feat(agent): add Indonesian language option by @aqilaziz in #4287
• feat(telegram): add streaming output via editMessageText by @hongxicheng in #4318
• fix(skill): fix skill hub import: fix www, add skill_hub retry by @Leirunlin in #4359
• style(console): inbox by @zhaozhuang521 in #4358
• fix(skill): fix skill path, use safer path normalizer and refactor for function naming by @Leirunlin in #4335
• feat(plugin): add CloudPaw plugin bundle for Alibaba Cloud deployment by @xuanrui-L in #4362
• fix(QA agent): bundle docs as package_data by @xieyxclack in #4280
• fix(tool): add _CDP_CONNECT_TIMEOUT_SECONDS = 30 for connect cdp by @x1n95c in #4350
• feat(console): add pin/unpin functionality for chat session drawer with … by @zhijianma in #4414
• chore(deps): upgrade agentscope to 1.0.20 and remove MCP JSON schema monkey-patch by @qbc2016 in #4419
• docs(roadmap): update roadmap by @cuiyuebing in #4424
• ci: add spam gate to auto-close issues/PRs when open count exceeds 10 by @rayrayraykk in #4422
• refactor(DingTalk): unify message processing to base event loop with streaming card support by @hongxicheng in #4420
• Fix(backup): backup import restore trust controls by @jinglinpeng in #4409
• feat(models): add custom headers editor and Anthropic auth token support by @rayrayraykk in #4413
• feat(cron): add timeout when creating cron job for agent tasks and us… by @zhijianma in #4425
• feat(console): enhance Matrix E2EE verify step and prevent "not encrypted / device not verify by owner" icon by @Morxi in #4120
• fix(WeCom): suppress duplicate "Thinking…" placeholder on rapid messages by @hongxicheng in #4427
• feat(console): implement localStorage for pinned state in chat session d… by @zhijianma in #4416
• fix(plugin): resolve CloudPaw plugin issues and enhance Alibaba Cloud Skills remote hosting integration by @xuanrui-L in #4423
• fix(token_usage): add per-model token usage aggregation by @zhijianma in #4476
• fix(console/chat): upgrade @agentscope-ai/chat to 1.1.63 to fix SSE connection leak on page navigation by @zhijianma in #4488
• fix(openai_provider): increase min max_tokens to 20 to satisfy model API constraints by @qbc2016 in #4489
• fix(providers): replace global LLM rate limiter with per-model instances by @rayrayraykk in #4487
• Fix(backup): backup restore trust follow-up by @jinglinpeng in #4429

New Contributors

• @Morxi made their first contribution in #4120

Full Changelog: v1.1.7...v1.1.8-beta.1

v1.1.7

✨ Added

Tools & MCPs

• Browser Use — Batch Actions: Execute multiple browser steps (navigate, click, type, screenshot, etc.) in a single tool call (#4139)
• Browser Use — File Download: Download files by clicking page elements or fetching URLs directly (#4261)
• GPT Image 2 Reference Images: Support uploading 1–16 reference images via URL or local path in the GPT Image 2 plugin (#4194)
• External Agent Async Execution: delegate_external_agent supports async streaming with task listing and status queries and configurable timeout (#4197)
• Shell Executable Configuration: Choose which shell runs commands via the config option (#4215)
• OAuth 2.1 for Remote MCP Servers: Authenticate remote MCP servers via OAuth 2.1 with PKCE (#4256)

Plugins

• Console Plugin Management: Install and uninstall plugins from the Settings UI via local path, ZIP upload, or URL (#4214, #4266)
• Qwen-Image & Wan 2.7 Plugins: New plugins for image generation/editing and video generation (#4248)
• Plugin HTTP API Router: Plugins can register custom HTTP API endpoints (#4255)

Chat & Console

• Multiple File Attachments: Chat input now supports selecting multiple files in a single message (#4206)
• Indonesian Language: Full Bahasa Indonesia locale support for Console UI and backend (#4219)
• Inbox: New centralized Inbox with Approvals and Push Messages tabs for managing tool-guard approvals and viewing cron execution results with traces (#4210, #4305)
• Cron Job Enhancement: Cron jobs now support one-time scheduled execution, a calendar view for visualizing upcoming runs, built-in templates for quick creation, per-job execution history with detailed run traces, and save-to-inbox delivery (#4210)

Channels

• Feishu Voice Bubbles: Audio files sent via Feishu now render as native voice bubbles (#4202)
• DingTalk Quoted Messages: Replies with quoted messages in DingTalk now include quoted text and media in the agent context (#4209)
• Feishu QR Code Bot Creation: Create a Feishu/Lark bot by scanning a QR code in the Channels setup UI (#4236)
• WeCom Streaming Output: Optional streaming replies for WeCom channel with real-time message delivery and reasoning indicator support (#4271)

🔄 Changed

• Model Selector Redesign: Replaced the hover dropdown with a searchable flat list grouped by provider (#3876)
• Floating Chat Button: Chat navigation moved from sidebar menu to a sticky button next to the agent selector (#4240, #4273)
• Agent Stats Session Discovery: Simplified session file lookup by walking channel subdirectories directly (#4250)

⚡ Performance

• Async FastAPI Dependencies: Model and provider manager dependencies converted to async, eliminating unnecessary thread pool dispatch (#4229)
• File Read Size Limit: Maximum file read size reduced to 200 MB (from 1 GB) with pre-allocation based on actual file size (#4272, #4276)
• Keyring Timeout: Keyring operations now have a 10-second timeout to prevent credential manager hangs from blocking startup (#4263)

🐛 Fixed

Providers & Models

• Volcengine Model IDs: Corrected model IDs to match actual API endpoints and updated capability flags (#4169)
• Provider Meta Preservation: Provider metadata is no longer dropped when retrieving provider info (#4200)
• Malformed Tool Use Filtering: Streaming parser now filters out tool-use blocks with null IDs or empty names (#4234)

Channels

• WeCom Approval Card Operator: Resolved approval cards now display the operator name (#4233)
• Feishu WebSocket Keepalive: Detect and recover from silent WebSocket connection loss (#4241)

Console & UI

• Session History Routing: Fixed session history disappearing and messages being routed to wrong sessions (#4203)
• Plan Panel Dark Mode: Improved text contrast in Plan Panel dark mode (#4190)
• Mobile Sidebar: Sidebar auto-collapses on narrow screens (#4225)
• User Message Newlines: User messages now preserve line breaks (#4231)
• Token Usage Date Labels: Chart labels now show year prefix when the date range crosses a year boundary (#4268)
• Desktop External Links: Links now open correctly in desktop builds (#4270)

New Contributors

• @weixizi made their first contribution in #4139
• @StarTrekking made their first contribution in #4202
• @aqilaziz made their first contribution in #4225
• @suntp made their first contribution in #4272

Full Changelog: v1.1.6...v1.1.7

v1.1.7-beta.2

What's Changed

• feat(plugins): enable register FastAPI APIRouter instances through plugin by @Osier-Yi in #4255
• feat: add timeout for keyring by @rayrayraykk in #4263
• fix(console): TokenUsage by @zhaozhuang521 in #4268
• refactor(console): console/PluginManager by @zhaozhuang521 in #4266
• feat(mcp): add OAuth 2.1 PKCE support for remote MCP servers by @rayrayraykk in #4256
• fix(console): replace window.open calls with openExternalLink utility… by @zhijianma in #4270
• style: sidebar by @zhaozhuang521 in #4273
• feat(channel): add streaming output hooks to BaseChannel with WeCom support by @hongxicheng in #4271
• Fix(tool): read_file_safe allocation size by @suntp in #4272
• perf(tools): reduce maximum file read size to 200MB by @jinliyl in #4276
• fix(QA agent): package website/public/docs into wheel and sdist by @lalaliat in #4275
• Feat(tool): Add action="file_download" for browser use by @x1n95c in #4261
• feat(cron & inbox): add inbox and optimize the cron job by @lalaliat in #4210
• chore(version): bumping version to 1.1.7b2 by @xieyxclack in #4283

New Contributors

• @suntp made their first contribution in #4272

Full Changelog: v1.1.7-beta.1...v1.1.7-beta.2

v1.1.7-beta.1

What's Changed

• Fix(provider): fix models in VOLCENGINE Provider by @Nioolek in #4169
• chore(version): bumping version to 1.1.7b1 by @xieyxclack in #4196
• fix(console): improve text contrast in Plan Panel dark mode by @ltzu929 in #4190
• fix(provider,wecom): preserve provider meta field and update tool_guard docstring in wecom by @zhijianma in #4200
• feat(plugins): add reference image support to gpt-image2 plugin by @rayrayraykk in #4194
• feat(tool): browser_use add batch action support to browser_use tool by @weixizi in #4139
• feat(memory): add auto-memory management features by @jinliyl in #4204
• Fix(session): session history disappearing and messages being routed to a different session by @zhaozhuang521 in #4203
• feat(tool): Add async execution support for delegate_external_agent by @x1n95c in #4197
• feat(chat): enable multiple attachments support in chat page by @zhijianma in #4206
• feat(DingTalk): process quoted messages for user-sent replies by @hongxicheng in #4209
• fix(exception): fix ConfigurationException key passing by @Leirunlin in #4212
• feat(console): user message support newline by @zhaozhuang521 in #4231
• perf(api): optimize async depends to fix thread pool blocking by @zhijianma in #4229
• fix(model): filter out malformed tool_use blocks from OpenAI-compatible model response by @qbc2016 in #4234
• feat(console): Chat floating in the menu by @zhaozhuang521 in #4240
• feat(shell): Add shell_command_executable` configuration to let users choose which shell uses by @xieyxclack in #4215
• fix(feishu): detect silent WebSocket connection loss in Feishu channel by @hongxicheng in #4241
• Refactor(skill): Add skill system by @Leirunlin in #4235
• feat(channels): support native voice bubble in Feishu channel by @StarTrekking in #4202
• fix(WeCom): show operator in resolved approval card by @hongxicheng in #4233
• feat(chat): refactor chat model selector into searchable flat list with provider grouping by @bowenliang123 in #3876
• fix(console): collapse sidebar on mobile by @aqilaziz in #4225
• feat(console): add Indonesian language option by @aqilaziz in #4219
• feat(plugins): support install/uninstall plugins on console by @rayrayraykk in #4214
• feat(feishu): add QR code bot creation via OAuth Device Flow by @zhijianma in #4236
• feat(memory): add pluggable memory manager with adbpg long-term memory by @shaohuaxi in #2308
• fix(mcp): add monkey patch for mcp by @qbc2016 in #4245
• refactor(agent_stats): streamline session file handling and remove un… by @zhijianma in #4250
• feat(plugins): add Qwen-Image, Wan 2.7 plugins by @rayrayraykk in #4248

New Contributors

• @weixizi made their first contribution in #4139
• @StarTrekking made their first contribution in #4202
• @aqilaziz made their first contribution in #4225

Full Changelog: v1.1.6...v1.1.7-beta.1

v1.1.6

✨ Added

Agent System

• Windows Diagnostics: qwenpaw doctor now checks Windows-specific environment issues including long path support, PowerShell language mode, and working directory path length (#4032)
• Agent Status API: New GET /agents/{agentId}/agent-status endpoint reporting agent runtime status, running task count, and task timestamps (#4107)
• Cron Session Isolation: Cron jobs now support a share_session option — when disabled, each scheduled run creates an isolated session context with a cron job ID (#4117)
• GPT Image 2 Plugin: New tool plugin for generating images via OpenAI's GPT Image 2 API (#3911)
• Config-Driven Agent Name: Use the configured agent profile name instead of a hardcoded default (#4140)

Chat & Console

• Whisper Voice Input: Replaced browser-native Web Speech API with server-side Whisper transcription for more reliable, cross-browser voice input (#3574)
• LLM-Generated Session Titles: Chat sessions are now automatically titled by the LLM in the background after the first message. Configurable via the "Auto-generate session titles" toggle in Agent Config (#3829)
• Token Usage Trends: Added per-model and per-token-type trend line charts to the Token Usage settings page for visualizing usage over time (#4080, #4094)
• Batch Skill Operations: Added Enable and Disable buttons to the skill batch operation toolbar with per-skill error reporting (#4091)
• Mermaid Diagram Rendering: Markdown code blocks with mermaid language tag are now rendered as interactive diagrams in chat and file previews (#4146)
• Brazilian Portuguese (pt-BR): Added full pt-BR locale support for both the Console UI and backend language settings (#4009, #4143)

Providers

• Volcano Engine Provider: Added Volcano Engine as a built-in OpenAI-compatible provider with standard and Coding Plan endpoints (#3994)
• DashScope Region Selection: DashScope base URL can now be modified from preset region endpoints (#4074)
• Aliyun Token Plan Provider: Added Aliyun Token Plan as a built-in provider (#4122)
• Anthropic Default Max Tokens: Raised default max_tokens for Anthropic-compatible models to 16,384 (#4054)

Channels

• Feishu Interactive Approval Cards: Tool-guard approval requests in Feishu are now rendered as interactive button cards that update in-place on approve/deny, with a documentation link hint when the card action callback is not subscribed (#3941, #3982)
• WeCom Group Session Sharing: Added share_session_in_group toggle to control whether group chat members share a single session or get per-member isolation (#3948)
• Feishu Sender Context: Feishu sender nickname is now passed to the agent environment context (#4098)
• WeCom Interactive Approval Cards: Tool-guard approval requests in WeCom are now rendered as interactive template cards (#4112)

Security

• Static File Path Traversal Protection: Console static file serving now rejects absolute paths to prevent path traversal bypass (#3973)
• Rule-Level Auto Deny: Individual security rules can now be configured to automatically deny tool calls (#4046)

Skills & CLI

• Skill Test CLI: New qwenpaw skills test command to validate skill content and run security scans (#3999)
• Skill Install/Uninstall CLI: New qwenpaw skills install and qwenpaw skills uninstall commands for managing skills from the command line, supporting both pool-level and per-agent workspace installs (#4053)

⚡ Performance

• Console Rendering: Eliminated duplicate re-renders by stabilizing approval polling state comparisons and memoizing chat runtime options (#4052, #4110, #4153)
• Chat History Navigation: Skip chat history lookup for non-arrow keys and cache user-message lists to avoid repeated scans on every keystroke (#4130)
• QR Polling Cleanup: Immediately stop QR code polling and clear status indicators on auth completion or code expiry (#4148)

🐛 Fixed

Channels

• WeCom Stream Keepalive: Keep the "Thinking..." placeholder stream alive with periodic refreshes to prevent stuck status indicators in WeCom (#3950)
• WeCom Reconnect Race: Fixed double reconnect scheduling and cross-event-loop disconnect in WeCom WebSocket handling (#3963)
• Telegram Network Retry: Added exponential backoff and controlled reconnect for transient Telegram network errors instead of silently dying (#4039)
• WeChat Cron Buffer Flush: Flush WeChat merge buffer immediately for cron/proactive sends that bypass the normal completion path (#4106)
• Markdown Table Splitting: Preserve markdown table structure across message chunks by repeating header and separator rows in each fragment (#4119)

Agent System

• External Agent Timeout: Added safe default timeout (60s) for delegate_external_agent to prevent indefinite hangs (#3928)
• Agent Config Reload: Agent config file changes now trigger a graceful reload with task draining instead of lightweight reinstantiation (#4064)
• Agent Config Persistence: Fixed the console agent config editor dropping nested settings on save by preserving the complete config structure (#4157)

MCP

• MCP Execution Timeout: Use sse_read_timeout as the MCP tool execution timeout instead of the shorter HTTP connect timeout (#4058, #4061)
• MCP Client Lifecycle Leak: Fixed lifecycle-task leak where close() could skip stopping a background reconnect task (#4152)

Console & UI

• SSE Surrogate Safety: Avoid SSE stream crash on malformed surrogate text by sanitizing non-encodable content before serialization (#3553)
• CodeMirror Line Wrapping: Fixed line wrapping in tool call input/output blocks (#3960)
• Default Agent Display Name: Respect custom name for the default agent in all UI surfaces (#4073)
• File Preview Paths: Fixed redundant URL prefix stripping in file preview paths that could cause broken URLs (#4089)

Infrastructure

• Docker Backup Restore: Correctly restore secrets on Docker volume mount points by swapping directory contents instead of renaming (#3916)
• Audio Block Paths: Return resolved filesystem path for file:// URL audio blocks and remove redundant file handling code (#4021, #4048)
• Log Rotation: Use RotatingFileHandler for log rotation on all platforms (#4076)
• Loopback Proxy Bypass: Bypass proxy environment variables for loopback API health checks to prevent connection failures behind corporate proxies (#4092)
• Conda Packaging: Restore conda packaging tools before running conda-pack to prevent broken packaging pipeline (#4093)

📝 Documentation

• WSL2 Timeout FAQ: Added FAQ entry for handling APITimeoutError when running in WSL2 NAT mode (#4005)
• Documentation Update: Updated website documentation to reflect new features (#4013)

🧪 Testing & CI

• Console Unit Tests: Added Vitest setup with unit and component tests covering Chat, API layer, and sh...

v1.1.6-beta.2

What's Changed

• fix(runner): rename channel variable to channel_name in command dispatch by @zhijianma in #4134
• perf(console): skip chat history lookup for non-arrow keys by @YingchaoX in #4130
• fix(tool_schema): add sanitize tool function schemas by @qbc2016 in #4126
• fix(cli): bypass proxies for loopback API checks by @jinglinpeng in #4092
• fix(agent): replace hardcoded agent name with config-driven value by @xieyxclack in #4140
• fix(channels): keep markdown tables renderable across split_text chunks by @hongxicheng in #4119
• fix(agent): emoji example in AGENTS.md by @Keillion in #4142
• fix(backup): restore secrets on Docker volume mount points by @jinglinpeng in #3916
• feat(settings): add pt-BR language support by @zhijianma in #4143
• feat(console): support mermaid graph by @zhaozhuang521 in #4146
• feat(WeCom): tool-guard interactive approval card by @hongxicheng in #4112
• feat(provider): allow Dashscope base URL selection in Console UI by @ekzhu in #4074
• fix(agent-tools): add safe default timeout for delegate_external_agent by @q1023884985 in #3928
• perf(console): Immediately stop polling and clear the status after clo… by @zhaozhuang521 in #4148
• fix(agent-config): preserve complete config on save to prevent nested… by @zhijianma in #4157
• refactor(console): extract QrcodeAuthBlock component and fix polling … by @zhaozhuang521 in #4153
• fix(mcp): fix lifecycle-task leak in stateful clients and refactor shared logic… by @qbc2016 in #4152
• chore(version): bumping version to 1.1.6b2 by @xieyxclack in #4161

New Contributors

• @Keillion made their first contribution in #4142
• @q1023884985 made their first contribution in #3928

Full Changelog: v1.1.6-beta.1...v1.1.6-beta.2

v1.1.6-beta.1

What's Changed

• chore(version): bump version to 1.1.6b1 by @zhijianma in #4082
• test(integration): add app startup and settings/envs smoke tests by @yutai78786 in #4081
• fix(console): avoid SSE crash on malformed surrogate text by @Prince-liu in #3553
• chore(console): Optimize language switching logic and replace with the latest language icon by @zhaozhuang521 in #4085
• feat(chat): replace Web Speech API with Whisper transcription for voice input by @tqjason in #3574
• Feat(provider): add volcengine provider by @Nioolek in #3994
• Feat/add token usage trend by @zhijianma in #4080
• fix(console): respect custom name for default agent by @CA-mambo in #4073
• fix(chat): remove redundant URL prefix stripping in file preview paths by @zhijianma in #4089
• refactor(wechat): centralize legacy weixin → wechat data migrations on workspace startup by @celestialhorse51D in #3605
• refactor(console): TokenUsage by @zhaozhuang521 in #4094
• plugin: add gpt image 2 tool plugin by @rayrayraykk in #3911
• feat(console): Add "Enable" and "Disable" buttons to the batch operation of skills by @zhaozhuang521 in #4091
• fix(pack): restore conda packaging tools before conda-pack by @jinglinpeng in #4093
• feat(skills): add cli skill test command by @JingHou1215 in #3999
• feat(feishu): surface sender nickname to agent env context by @hongxicheng in #4098
• fix(WeChat): flush WeChat merge buffer immediately for cron sends by @hongxicheng in #4106
• chore: fix openai by @rayrayraykk in #4118
• feat(security): add rule level auto deny by @gnipping in #4046
• feat(cron): add channel-based session isolation for session and share option for cron jobs by @zhijianma in #4117
• feat: add agent status endpoint with task tracking by @rayrayraykk in #4107
• perf(console): Chat performance optimization by @zhaozhuang521 in #4110
• fix: use RotatingFileHandler for log rotation on all platforms by @wjt0321 in #4076
• test(console): add Vitest setup + unit/component tests (Chat pilot, API layer, shared components) by @hanson-hex in #3559
• fix(console): fix test by @zhaozhuang521 in #4121
• feat(doctor): add Windows environment diagnostics by @1105623876 in #4032
• fix(reload): route AgentConfigWatcher through reload_agent for graceful task draining by @hongxicheng in #4064
• feat(provider): add aliyun token plan as a built-in provider by @yuanxs21 in #4122

New Contributors

• @yutai78786 made their first contribution in #4081
• @tqjason made their first contribution in #3574
• @JingHou1215 made their first contribution in #3999
• @wjt0321 made their first contribution in #4076
• @1105623876 made their first contribution in #4032

Full Changelog: v1.1.5.post2...v1.1.6-beta.1

v1.1.5.post2

What's Changed

• docs(website): update documentation to v1.1.5 by @xieyxclack in #4013
• feat(chat): generate session titles asynchronously via LLM by @ekzhu in #3829
• fix(message_processing): return resolved path for file:// URL audio blocks by @karls0r in #4021
• Fix(Provider): Increase max_token for anthropic compatible models by @pan-x-c in #4054
• perf(console): Solve duplicate rendering by @zhaozhuang521 in #4052
• fix(mcp): typo fix by @qbc2016 in #4058
• fix(mcp): use sse_read_timeout as MCP tool execution_timeout instead of HTTP connect timeout by @qbc2016 in #4061
• fix(utils): remove redundant codes by @qbc2016 in #4048
• fix(channel): telegram network retry by @Leirunlin in #4039
• feat(i18n): add Brazilian Portuguese (pt-BR) locale support by @Jailtonfonseca in #4009
• fix(skill): resilient loading for migrated or malformed skill & skill pool entries by @Leirunlin in #4016
• fix(approval): /approve shorthand ignores request_id argument by @xieyxclack in #4014
• docs(faq): Docs for handling APITimeoutError when running in WSL2 (NAT mode) by @hllqkb in #4005
• feat(skill): Add skill install/uninstall cli by @Leirunlin in #4053
• chore(version): bumping version to 1.1.5p2 by @xieyxclack in #4071

New Contributors

• @karls0r made their first contribution in #4021
• @Jailtonfonseca made their first contribution in #4009
• @hllqkb made their first contribution in #4005

Full Changelog: v1.1.5.post1...v1.1.5.post2