v2.0.0-beta.1

⚠️ This is an early beta release for QwenPaw 2.0.0 (v2.0.0-beta.1), which is currently undergoing active development — it may contain breaking changes and instability. Intended for developers and early adopters only; not recommended for production use.

What's Changed

• refactor: migrate agentscope from version 1.x to 2.0.0 by @qbc2016 in #4846
• Add uninstall hooks and expose skill provider API by @wangfei010313 in #5008
• fix: propagate ModelInfo.max_input_length to AgentScope context_size for auto-compaction by @qbc2016 in #5018
• feat(tui): bundle the terminal chat UI into qwenpaw (Phase 1) by @ekzhu in #5032
• feat(runtime): Runtime 2.0 modular architecture with enhanced tool-call coordination by @XiuShenAl in #5078
• feat(driver): introduce Agent OS Driver — unified abstraction for external capabilities (MCP/A2A/ACP/...) by @xiaoming-qxm in #5067
• feat: initial governance & sandbox interface disscussion by @weidankong in #5088
• bump: version to 2.0.0a1 by @rayrayraykk in #5281
• feat(context): migrate context management from LightContextManager to AgentScope 2.0 native compression by @qbc2016 in #5309
• feat(memory): migrate QwenPaw memory runtime to ReMe4 by @jinliyl in #5349
• Merge/2.0 into main by @rayrayraykk in #5412
• docs(roadmap): update roadmap for QwenPaw 2.0.0 by @cuiyuebing in #5461
• fix: macos sandbox missing close bracket by @weidankong in #5454
• refactor(memory): restructure auto-memory lifecycle, enhance /compact and add /system_prompt command by @jinliyl in #5450
• revert(upload_file): replace manual file size check with utility func… by @zhijianma in #5467
• perf: parallelize shutdown to reduce close time by @rayrayraykk in #5469
• feat(coding): expand chat panel to 50% and shrink editor area by @zhaozhuang521 in #5473
• Revert/relative path file preiview by @zhijianma in #5478
• feat(ci): end-to-end UI verification for desktop releases by @yutai78786 in #5428
• fix(cron): restore cron session compatibility and sanitize malformed tool_call history by @qbc2016 in #5475
• fix(cron): allow editing and deleting enabled cron jobs by @lalaliat in #5483
• fix(dashscope): honour extra_body generate_kwargs and avoid sending default enable_thinking by @qbc2016 in #5491
• fix(token_usage): restore chat token/context usage ring & popover under agentscope 2.0 by @yuanxs21 in #5493
• feat(dingtalk): support custom API endpoint for private deployments by @hongxicheng in #5111
• feat(discord): download attachments locally and add media_dir config by @hongxicheng in #5468
• fix(channel): restore streaming path and split multi-segment reply into separate streaming boxes by @hongxicheng in #5487
• feat(memory): Enhance memory search functionality and simplify metadata display by @jinliyl in #5482
• Feat/channel page dual layout by @zhaozhuang521 in #5504
• style(chat): remove max-width constraints in wide mode styles by @zhijianma in #5502
• feat(tools): redesign Tools page with enabled/available split layout by @zhaozhuang521 in #5509
• fix(WeCom): WeCom QR code fetch fails due to greedy regex in settings parsing by @hongxicheng in #5460
• fix(cron): cron session visibility, memory isolation and hot-reload stability by @lalaliat in #5494
• test(integration): stabilise flaky integration tests + remove dead /api/agent code by @yutai78786 in #5507
• fix(runtime): align envelope event translation with v1 streaming protocol by @XiuShenAl in #5495
• docs(locales): update "tools" translations for consistency across mul… by @zhijianma in #5516
• feat(console): mobile adaptation for sidebar, header, and page header by @yaozy2020 in #5444
• fix(chat): prevent ModelSelector dropdown overflow and marquee long model names on mobile by @yaozy2020 in #5445
• fix(chat): mobile header actions, session dropdown, and unified right drawers by @yaozy2020 in #5446
• feat(console): mobile adaptation for Debug page by @yaozy2020 in #5449
• feat(console): mobile adaptation for Security page by @yaozy2020 in #5451
• feat(console): mobile adaptation for Agent Skills page by @yaozy2020 in #5458
• feat(console): mobile adaptation for Skill Market page by @yaozy2020 in #5459
• feat(console): make TokenUsage tables horizontally scrollable on mobile by @yaozy2020 in #5463
• feat(console): mobile adaptation for Skill Pool page by @yaozy2020 in #5464
• feat(console): mobile adaptation for Voice Transcription settings page by @yaozy2020 in #5470
• fix(pack): repair desktop packaging builds by @jinglinpeng in #5518
• feat(skills): split Skills page into enabled/disabled sections with d… by @zhaozhuang521 in #5521
• fix: override format_tools for gemini by @qbc2016 in #5517
• fix: add DashScopeChatModel to ChatModelName literal type by @qbc2016 in #5513
• fix(console): improve MCP access policy layout by @xiaoming-qxm in #5213
• fix: inline $ref/$defs in tool schemas for GLM model compatibility by @qbc2016 in #5496
• feat: add OpenAI Response API provider by @qbc2016 in #5519
• fix: fix tool input json decode by @qbc2016 in #5486
• fix: refine mcp tool name to pase openai api by @qbc2016 in #5485
• fix(matrix): use nio client.download for encrypted media by @Morxi in #5059
• feat(inbox): add source type filter for push messages by @lalaliat in #5522
• fix(skillpool): restore SkillPool styles after PR #5521 by @zhaozhuang521 in #5532
• refactor(readme): add trending badge by @lalaliat in #5534
• fix(tui): restore ACP commands and inline approvals by @ekzhu in #5443
• Document Langfuse Docker deployment by @totoyang in #5380
• fix: add missing emptyState and emptyIcon styles for TokenUsage page by @zhaozhuang521 in #5544
• fix(chat): preserve assistant markdown newlines by @wananing in #5538
• fix: cap the file size of send_file_to_user by @weidankong in #5457
• fix(skill): zip metadata error handling by @Leirunlin in #5481
• feat(memory): refactor auto memory system with turn-based tracking by @jinliyl in #5540
• feat(tui): support project-scoped code sessions by @ekzhu in #5448
• fix(models): count only configured providers online by @wananing in #5537
• fix(skill): remove enable all during init by @Leirunlin in #5477
• test(e2e): adapt for agentscope 2.0 — drop Plan Mode, fix selectors and fixtures by @yutai78786 in #5542
• feat(desktop): add tauri auto updater by @jinglinpeng in #4669
• test(integration): parallelize with pytest-xdist and harden coverage pipeline by @yutai78786 in #5531
• fix: standalone "type": "null" in functionDeclaration schema breaks third-party proxies by @NotFoundOvO in #5545
• fix(hooks): inject user_id and channel into ContextVarsSetupHook by @XiuShenAl in #5552
• feat(channel): add Slack channel with fu...

v1.1.12.post2

What's Changed

• fix: navigate to new chat after deleting the current session by @zhaozhuang521 in #5376
• feat(console, chat): enhance file preview to support relative path by @zhijianma in #5377
• fix(queue): bind agent ID at enqueue time to prevent cross-agent deli… by @zhaozhuang521 in #5371
• Context with model by @yuanxs21 in #5386
• fix(console): use QueueItem userId/channel in background queue sender by @zhaozhuang521 in #5389
• fix(#5354): release session switch lock on embedded mode completion by @yaozy2020 in #5357
• fix(console): improve ModelSelector dropdown mobile responsiveness by @yaozy2020 in #5355
• feat(console): mobile adaptation for Inbox page by @yaozy2020 in #5383
• feat(console): mobile adaptation for ACP page by @yaozy2020 in #5382
• feat(console): mobile responsive layout for Agent Config page by @lecheng2018 in #5366
• feat(console): mobile adaptation for CronJobs page and PageHeader by @yaozy2020 in #5362
• feat(console): mobile card layout for Backups page by @yaozy2020 in #5391
• feat(console): mobile adaptation for Sessions page by @yaozy2020 in #5364
• feat(console): adapt Settings-Models page for mobile view by @lecheng2018 in #5397
• feat(console): mobile adaptation for MCP page by @yaozy2020 in #5381
• feat(console): mobile adaptation for Channels page by @yaozy2020 in #5369
• feat(console): mobile adaptation for Environments page by @yaozy2020 in #5385
• feat(console): mobile adaptation for Workspace page by @yaozy2020 in #5384
• fix(cron): record APScheduler misfires in history and raise default misfire grace to 600s by @lalaliat in #5418
• refactor(chat): centralize session-id resolution and navigation state tracking by @zhijianma in #5388
• feat(auth): improve login error handling and add rate limiting by @zhijianma in #5424
• test(e2e): add UI coverage for 6 modules + infrastructure hardening by @yutai78786 in #5372
• feat(discord): add streaming responses via message edit and typing indicator by @hongxicheng in #5314
• fix(dream): set the default misfire time to 600s for dream. by @lalaliat in #5426
• chore(version): bump version to 1.1.12.post2 by @zhijianma in #5429

New Contributors

• @yaozy2020 made their first contribution in #5357
• @lecheng2018 made their first contribution in #5366

Full Changelog: v1.1.12.post1...v1.1.12.post2

v1.1.12.post1

What's Changed

• fix(scripts): correct prerelease arguments expansion and bump version to 1.1.12.post1 by @zhijianma in #5288
• fix(memory): rename ChromaDB probe collection to 'probe-test' by @zhijianma in #5289
• fix(proactive): prevent cache pollution of load_agent_config() by @imrewce in #5275
• fix(console,provider): improve model readiness check for local providers by @zhijianma in #5305
• Feat/chat history right panel by @zhaozhuang521 in #5293
• fix(token_usage): use active model's max_input_length for context usage display by @nguyenthanhthe in #5303
• fix: handle Windows certificate store SSL errors in build verification by @wangfei010313 in #5298
• fix: explicitly configure SSL certificates for DingTalk channel HTTP client by @wangfei010313 in #5291
• test(integration): Sprint 3.1-3.4 — ACP / Plugin / Security / cross-cutting (64 cases) by @yutai78786 in #5270

Full Changelog: v1.1.12...v1.1.12.post1

v1.1.12

What's Changed

✨ Added

Console

• Models Page Overhaul: Provider Aggregation, Unified Card UI & Layout Redesign (#5203)
• Simple Mode: Add simple mode with flat nav and sorted session list by updated time (#5222)
• Wide Mode Toggle: Add wide mode toggle for expanded chat layout (#5212)
• Per-Turn Token Usage: Add per-turn token and context usage popover (#5130)
• User Input Queue: Add user input queue (#5158)
• Session Filter by Title: Add session filter by title (#5178)
• Syntax Highlighting: Add syntax highlighting for code blocks across all views (#5219)
• Vietnamese Language: Add complete Vietnamese (vi) interface language support (#5186)
• Fallback Message: Show fallback message when response output is empty (#5232)

Skills

• Skill Market Update: Update skill-market, include QwenPaw platform, improve UI (#5123)
• Skill Slash Inject: Improve skill-slash-inject and display (#5146)

Channels

• Yuanbao Quoted Messages: Support quoted messages and unify media download pipeline (#5160)
• Yuanbao Bot Filtering: Add bot message filtering and environment variable support (#5150)
• Non-blocking Flush: Non-blocking flush with adaptive throttling for all channels (#5215)
• DingTalk Liveness Watchdog: Add liveness watchdog to recover stream after system sleep (#5224)

Desktop

• Port Persistence: Persist backend port across restarts to preserve localStorage (#5051)
• Port Config: Desktop port configuration support (#5272)

Files

• File Preview: Improve file preview error handling and use FileResponse (#5115)

CI

• Release Verification Gate: Add release verification gate between build and publish (#5121)

Observability

• Langfuse Agent Loop: Group langfuse observations by agent loop (#5128)

🔄 Changed

• Request Payload Transforms: Request payload transforms (#5188)
• Memory Search Style: Refactor the result style of the memory search tool (#5154)
• Xiaoyi Dual WebSocket: Refactor connection to dual WebSocket & fix unusable channel (#5274)
• Calendar Date Grouping: Use calendar dates for session list date grouping (#5257)

🐛 Fixed

Security

• Keychain Master Key: Isolate keychain master key per install (#5028)

Desktop

• Windows Console Crash: Guard against Windows console crash and self-kill commands (#5192)
• Tauri Windows CI: Harden Tauri Windows CI against crates.io fetch failures (#5125)
• Plugin Dependency: Repair plugin dependency installs in Tauri sidecar (#5260)
• Session Filename: Resolve session filename duplication and Desktop inter-agent call failures (#5036)

Console

• Session Redirection: Fixed session redirection when switching code mode (#5147)
• Collapse Panel Render: Force render Collapse panels to prevent memory config loss (#5144)
• Approval Command Overflow: Wrap approval command text with word-break to prevent horizontal overflow (#5176)
• Tool Card Loading: Tool card loading spinner for shell commands and unregistered tools (#5141)
• Browser Autocomplete: Disable browser autocomplete on provider search input (#5112)
• Dream Cron: Keep empty dream_cron empty to disable dream job (#5256)

Providers & Config

• Local Providers in PRO Tab: Show local providers (ollama/lmstudio) in PRO tab of ModelSelector (#5113)
• Deep Copy Cache: Ensure deep copy of cached agent configurations (#5229)

Context & Agent

• Empty Msg Guard: Guard empty msg list in LightContextManager.pre_reply (#5038)
• Mission Crash: Prevent agent crash on corrupted loop_config.json / prd.json (#5000)

Local Models

• Llama.cpp Version: Parse llama.cpp server version without fixed-width slice (#5035)

MCP

• OAuth IndexError: Avoid IndexError on empty authorization_servers in OAuth discovery (#5194)

Memory

• Chromadb Async Probe: Add async runtime probe for chromadb Rust bindings (#5271)

Gemini

• Tool Schema Sanitize: Sanitize tool schemas to prevent 400 INVALID_ARGUMENT on function calling (#5226)

Tools

• Raw Decode: Use raw_decode to silence spurious "Extra data" warnings on no-param tool calls (#5220)
• Title Generation: Use formatter for title generation and skill optimization to support all model providers (#5228)

Install

• Stable PyPI Default: Default to stable PyPI releases only (#5269)

Pack

• OpenSSL Pin: Pin openssl<3.5.7 to fix desktop startup failure (#5100)

⚡ Performance

• Remove Unnecessary Copy: Remove unnecessary deep copy operations in agent config (#5240)

🏗️ Infrastructure

• Release Duty Checklist: Chore release duty checklist (#5105)
• Tool Card Title Truncate: Truncate tool card titles to single line with ellipsis (#5119)
• Datapaw Agent Menu: Refresh Datapaw agent menu on agent switch (#5114)

🧪 Testing

• Sprint 2.4 Tests: Add Sprint 2.4 cron execution and tool API tests (#5201)

📖 Docs

• Vietnamese README: Add Vietnamese README (README_vi.md) (#5245)
• Roadmap Update: Update roadmap (#5277)

New Contributors

• @ly-wang19 made their first contribution in #5038
• @biencuong made their first contribution in #5186
• @nguyenthanhthe made their first contribution in #5178
• @totoyang made their first contribution in #5128

Full Changelog: v1.1.11...v1.1.12

v1.1.12-beta.2

What's Changed

• perf(config): remove unnecessary deep copy operations in agent config… by @jinliyl in #5240
• feat(console): add session filter by title (#4999) by @nguyenthanhthe in #5178
• chore: bump version 1.1.12b2 by @rayrayraykk in #5255
• feat(console): add user input queue by @zhijianma in #5158
• fix(sidebar): use calendar dates for session list date grouping by @zhijianma in #5257
• fix(console): keep empty dream_cron empty to disable dream job by @ployts in #5256
• docs: add Vietnamese README (README_vi.md) by @nguyenthanhthe in #5245
• fix(mcp): avoid IndexError on empty authorization_servers in OAuth discovery by @ly-wang19 in #5194
• fix(install): default to stable PyPI releases only by @rayrayraykk in #5269
• group langfuse observations by agent loop by @totoyang in #5128
• fix(memory): add async runtime probe for chromadb Rust bindings (#5243) by @rayrayraykk in #5271
• fix(console): wrap approval command text with word-break to prevent horizontal overflow (#4985) by @nguyenthanhthe in #5176
• fix(desktop): repair plugin dependency installs in Tauri sidecar by @jinglinpeng in #5260
• Feature/desktop port config by @wangfei010313 in #5272
• docs(roadmap): update roadmap by @cuiyuebing in #5277
• refactor(xiaoyi): refactor connection to dual WebSocket & fix unusable channel by @hongxicheng in #5274

New Contributors

• @nguyenthanhthe made their first contribution in #5178
• @totoyang made their first contribution in #5128

Full Changelog: v1.1.12-beta.1...v1.1.12-beta.2

v1.1.12-beta.1

What's Changed

• fix(security): isolate keychain master key per install by @ekzhu in #5028
• fix(desktop): harden Tauri Windows CI against crates.io fetch failures by @jinglinpeng in #5125
• refactor(console): Refactor the result style of the memory search tool. by @zhaozhuang521 in #5154
• fix(console): fixed session redirection when switching code mode by @zhaozhuang521 in #5147
• feat(ci): add release verification gate between build and publish by @yutai78786 in #5121
• fix(console): force render Collapse panels to prevent memory config loss by @zhaozhuang521 in #5144
• chore(release): bump version to 1.1.12.beta1 by @rayrayraykk in #5157
• fix(release): switch version to 1.1.12b1 by @rayrayraykk in #5159
• fix(context): guard empty msg list in LightContextManager.pre_reply by @ly-wang19 in #5038
• fix(local_models): parse llama.cpp server version without fixed-width slice by @ly-wang19 in #5035
• fix(desktop): persist backend port across restarts to preserve localStorage (#4733) by @wangfei010313 in #5051
• Request payload transforms by @sanfran1068 in #5188
• feat(yuanbao): support quoted messages and unify media download pipeline by @hongxicheng in #5160
• feat(yuanbao): add bot message filtering and environment variable support by @hongxicheng in #5150
• fix(desktop): guard against Windows console crash and self-kill commands by @wangfei010313 in #5192
• feat(chat): add per-turn token and context usage popover by @yuanxs21 in #5130
• fix(skill): Improve skill-slash-inject and display by @Leirunlin in #5146
• feat(skill): Update skill-market, include qwenpaw platform, improve UI by @Leirunlin in #5123
• feat(chat): add wide mode toggle for expanded chat layout by @zhijianma in #5212
• fix: tool card loading spinner for shell commands and unregistered tools by @zhaozhuang521 in #5141
• feat: Models Page Overhaul — Provider Aggregation, Unified Card UI & Layout Redesign by @rayrayraykk in #5203
• fix(mission): prevent agent crash on corrupted loop_config.json / prd.json (#4970) by @rayrayraykk in #5000
• test(integration): add Sprint 2.4 cron execution and tool API tests by @yutai78786 in #5201
• feat(console): add complete Vietnamese (vi) interface language support by @biencuong in #5186
• fix(dingtalk): add liveness watchdog to recover stream after system sleep by @hongxicheng in #5224
• feat: add syntax highlighting for code blocks across all views (#5191) by @zhaozhuang521 in #5219
• feat(channel): non-blocking flush with adaptive throttling for all channels by @hongxicheng in #5215
• fix: resolve session filename duplication and Desktop inter-agent call failures (#4988) by @wangfei010313 in #5036
• fix: use raw_decode to silence spurious "Extra data" warnings on no-param tool calls by @qbc2016 in #5220
• feat(chat): show fallback message when response output is empty by @zhijianma in #5232
• fix(config): ensure deep copy of cached agent configurations by @jinliyl in #5229
• fix: use formatter for title generation and skill optimization to support all model providers by @qbc2016 in #5228
• fix(gemini): sanitize tool schemas to prevent 400 INVALID_ARGUMENT on function calling by @qbc2016 in #5226
• feat(console): add simple mode with flat nav and sorted session list by updated time by @zhijianma in #5222

New Contributors

• @ly-wang19 made their first contribution in #5038
• @biencuong made their first contribution in #5186

Full Changelog: v1.1.11.post2...v1.1.12-beta.1

v1.1.11.post2

What's Changed

• style: truncate tool card titles to single line with ellipsis by @zhaozhuang521 in #5119
• chore: bump version to 1.1.11post2 by @rayrayraykk in #5124

Full Changelog: v1.1.11.post1...v1.1.11.post2

v1.1.11.post1

What's Changed

• chore: bump version to 1.1.11.post1 by @rayrayraykk in #5093
• Revert "fix(pack): compile-check discord after conda-unpack" by @rayrayraykk in #5092
• Chore: release duty checklist by @rayrayraykk in #5105
• fix(pack): pin openssl<3.5.7 to fix desktop startup failure (#5086) by @jinglinpeng in #5100
• fix: disable browser autocomplete on provider search input by @zhaozhuang521 in #5112
• [codex] refresh Datapaw agent menu on agent switch by @sanfran1068 in #5114
• fix: show local providers (ollama/lmstudio) in PRO tab of ModelSelector by @rayrayraykk in #5113
• feat(files): improve file preview error handling and use FileResponse by @zhijianma in #5115
• chore: add news for agentscope platform by @rayrayraykk in #5118

Full Changelog: v1.1.11...v1.1.11.post1

v1.1.11

What's Changed

✨ Added

Providers

• Free Model OAuth: Zero-config free models with one-click OAuth authentication (#5049)
• Xiaomi MiMo Provider: Add Xiaomi MiMo Token Plan as built-in provider (#4722)
• Extra Body Routing: Route non-standard generate_kwargs into extra_body (#4689)

Console

• Plugin Market: Add Plugin Market tab with AgentScope Platform integration (#5023)
• Plugin Extension Infrastructure: Plugin extension infrastructure for console (#4997)
• Tool Cards Plugin System: Tool cards plugin system (#5046)
• Slash Command Suggestions: Add current-agent skills to slash command suggestions with UI optimizations (#4810)
• External URL Navigation: Support href field on MenuItem for external URL navigation (#5071)

MCP

• Tool Whitelisting: Add per-server MCP tool whitelisting with frontend toggle UI (#5002)

Plugins

• Prompt Section Registry: Allow plugins to inject system prompt blocks at defined anchor points (#4804)
• Uninstall Hooks: Add uninstall hooks, fix validator imports, expose skill provider API (#4794)
• CloudPaw Agent Import: Support importing agents from AgentHub and enhance A2A capabilities (#5033)

Skills

• Self-Evolving Skill Creation: Enhanced make-skill flow to support self-evolving skill creation (#4857)
• Skill Tag Batch Download: Add skill tag batch download (#4969)
• Multi-Path Skill Pool: Add multi-path support for skill pool (#4891)

Channels

• Telegram Tool Guard: Interactive tool approval via inline keyboard (#4737)
• Feishu Group Sharing: Add group session sharing mode (#4821)
• Feishu Interactive Cards: Support interactive card content extraction and refactor message parsing (#4879)
• QQ QR Code Auth: Add QR code authorization for QQ channel (#4848)
• DingTalk Inline Media: Enable inline image preview and video playback card via webhook (#5073)
• Yuanbao Typing Indicator: Add typing indicator via heartbeat API (#5020)
• Access Control Username: Add sender username to access control with unified user info structure (#4897)

Browser

• Page Coordinate Click: Add page coordinate click support to browser_control (#4905)

ACP

• ACP Enhancements: Advertise commands, surface errors, tool params, agent/model meta, file links (#4949)

Runner

• Stream Query Timestamp: Override stream_query to set current timestamp on responses (#4892)

🔄 Changed

• Cron Push Bubbles: Disable push bubbles for cron jobs of type 'agent' (#4803)
• Console Media Handling: Simplify media message handling in console channel (#5077)
• Revert Session Panel: Revert "embed history session list as right-side panel" (#5076)

🐛 Fixed

Providers & Config

• ProviderManager Fallback: Add ProviderManager fallback to get_model_max_input_length (#4827)
• Compaction Fix: Resolve /compact ignoring model's max_input_length when active_model is unset (#5021)

Coding Mode

• Windows Drive Browsing: Support browsing all drives on Windows (#4906)
• Session Switch & Header: Fix coding mode session switch failure and header overflow (#5011)

Console

• Session List Spinner: Fix session list kept spinning (#4929)
• Scrollbar Flickering: Remove hover transform to prevent scrollbar flickering (#4766)
• Shield Icon & Table: Center shield icon and adjust rule table column widths (#4765)
• Theme Toggle Icon: Change system theme toggle icon from computer to sun (#5050)

Desktop

• Tauri External Links: Fix Tauri desktop external links (#4683)

Agent & Memory

• Broadcast Coroutine: Await unawaited coroutine in _broadcast_to_subscribers (#5048)
• Skip Auto Memory: Skip automation auto memory (#4348)
• Dream Workspace: Dream should use cron runner's workspace, not stale instance dir (#4936)
• Media Block Processing: Handle non-dict source objects in media block processing (#4933)

MCP

• Tool Name Regex: Alias-rewrite tool names rejected by OpenAI-style regex (#4958)
• Subprocess Accumulation: Prevent subprocess accumulation across restarts (#5014)

Channels

• DingTalk Message Merging: Prevent cross-user message merging when conversation_id suffix collides (#4932)
• OneBot Port Conflict: Graceful degradation on port conflict during reload (#5010)
• ACL Sender ID: Preserve acl_sender_id during native payload merge across all channels (#4925)

Browser

• CDP Timeout & Profile: Add CDP timeout param and browser profile isolation for cross-browser switching (#4944)

File & Session

• Async File Writes: Use aiofiles for non-blocking file writes (#4954)
• Atomic State Write: Write session state atomically (#4706)
• Upload Size & Timeout: Upload size limit + plugin loader timeout resilience (#4940)
• Zip Download Size: Increase zip download file size (#4941)

Security

• File Preview Restriction: Restrict file preview to WORKING_DIR and block sensitive files (#4981)

Packages

• Yuanbao Proto JSON: Include yuanbao proto JSON files in package-data (#4899)

⚡ Performance

• Backend Startup: Unblock event loop and parallelize startup (#5074)
• CI Coverage: Switch coverage collection from py3.10 to py3.13 (#4952)

🏗️ Infrastructure

• E2E CI Pipeline: Complete E2E integration CI pipeline — backend startup, coverage, test fixes (#5054)
• CI Cleanup: Remove redundant channel-tests workflow (#5056)
• Dependencies: Update reme-ai dependency to version 0.3.1.10 (#4935)
• Chat Component: Update @agentscope-ai/chat to 1.1.68 (#5072)

🧪 Testing

• Frontend Unit Tests: Complete frontend unit test milestone — constants, contexts, layouts, api-types, components (#4332)
• Runner & Router Tests: Add unit + contract tests for runner & routers (#4852)
• Agent-Scoped P0 Tests: Agent-scoped P0 contract coverage (+55 cases) (#4945)
• Agent Page Tests: Agent page + API modules unit tests + coverage ratchet (#5012)
• Provider & Utils Tests: Add unit tests for local_models, providers, tunnel, and utils (#4973)
• Channel Layer Tests: Channel layer + multi-agent management integration tests (#5058)
• E2E Token Usage: Fix token usage test empty state detection in clean environment ([#5068](https://github.com/agentscope-a...

v1.1.11-beta.3

What's Changed

• ci: remove redundant channel-tests workflow by @yutai78786 in #5056
• feat(skills): enhanced make-skill flow to support self-evolving skill creation by @x1n95c in #4857
• feat(skill): Add skill tag batch download by @Leirunlin in #4969
• fix(mcp): prevent subprocess accumulation across restarts (#4834) by @rayrayraykk in #5014
• feat(plugin/cloudpaw): support importing agents from AgentHub and enhance A2A capabilities by @Saint-Yin in #5033
• fix(security): restrict file preview to WORKING_DIR and block sensiti… by @zhijianma in #4981
• feat(chat): embed history session list as right-side panel by @zhaozhuang521 in #5070
• test(phase5): add unit tests for local_models, providers, tunnel, and utils by @EaveLuo in #4973
• docs(website): consolidate frontend plugin docs into website pages by @zhijianma in #5066
• Add multi-path support for skill pool by @Leirunlin in #4891
• fix(e2e): fix token usage test empty state detection in clean environment by @yutai78786 in #5068
• feat(console): support href field on MenuItem for external URL navigation by @sanfran1068 in #5071
• fix(session): write session state atomically by @JasonBuildAI in #4706
• test(integration): Sprint 2.1–2.2 channel layer + multi-agent management by @yutai78786 in #5058
• chore(console): update @agentscope-ai/chat to 1.1.68 version by @zhijianma in #5072
• Feat/tool cards plugin system clean by @zhaozhuang521 in #5046
• chore: bump version to 1.1.11b3 by @rayrayraykk in #5075
• feat(plugins): add Plugin Market tab with AgentScope Platform integration by @Osier-Yi in #5023
• feat(dingtalk): enable inline image preview and video playback card via webhook by @hongxicheng in #5073
• perf(backend): Unblock Event Loop & Parallelize Startup by @rayrayraykk in #5074
• Revert "feat(chat): embed history session list as right-side panel (#… by @zhijianma in #5076
• refactor(console): simplify media message handling in console channel by @zhijianma in #5077

New Contributors

• @Saint-Yin made their first contribution in #5033
• @EaveLuo made their first contribution in #4973

Full Changelog: 1.1.11-beta.2...v1.1.11-beta.3