Qwenpaw

What's Changed

✨ Added

**Console & Workspaces**

- Add six theme palettes and custom colors and corner radii, with live preview and saved preferences ([7741](https://github.com/agentscope-ai/QwenPaw/pull/7741))
- Add an authenticated, multi-tab terminal inside Chat, with a working directory for each conversation ([7861](https://github.com/agentscope-ai/QwenPaw/pull/7861))
- Allow Console font size to be adjusted from 12 to 20 pixels across chat and settings ([8005](https://github.com/agentscope-ai/QwenPaw/pull/8005))
- Save multi-folder workspaces as an Agent’s default for future tasks ([7789](https://github.com/agentscope-ai/QwenPaw/pull/7789))
- Show files delivered by the Agent directly below its reply for easier preview and download ([7750](https://github.com/agentscope-ai/QwenPaw/pull/7750))

**QwenPaw-Flash**

- Recommend QwenPaw-Flash 9B, 27B, and 35B-A3B locally: update the 9B recommendation and add 27B and 35B-A3B options ([8155](https://github.com/agentscope-ai/QwenPaw/pull/8155))

**PawPort**

- Add PawPort to import supported conversations, memory, Skills, plugins, MCP settings, projects, and scheduled tasks from Codex and Qoder, with compatibility checks and selective retries ([6960](https://github.com/agentscope-ai/QwenPaw/pull/6960))

**QwenPaw Creator & Data**

- Upgrade Creator to 2.0.1: review scripts before media production, keep manual regenerations from triggering paid downstream steps, and recover stalled projects ([8121](https://github.com/agentscope-ai/QwenPaw/pull/8121))
- Upgrade QwenPaw Data to 0.3.0 with an integrated analysis workspace, interactive clarification, inline HTML reports, and `/data` and `/datasource` commands in chat channels ([7637](https://github.com/agentscope-ai/QwenPaw/pull/7637))

**Models & Memory**

- Unify model discovery, pricing, and selection, with a candidate model pool and per-conversation model and thinking controls ([7899](https://github.com/agentscope-ai/QwenPaw/pull/7899))
- Configure a custom provider’s name, endpoint, protocol, and API key in one dialog ([7826](https://github.com/agentscope-ai/QwenPaw/pull/7826))
- Configure ReMe search reranking in the Console, including the model, endpoint, candidate multiplier, and timeout ([6399](https://github.com/agentscope-ai/QwenPaw/pull/6399))

**Hub**

- Add a Hub model gateway with centrally managed organization models, member token budgets, usage dashboards, and invitation-based registration ([7779](https://github.com/agentscope-ai/QwenPaw/pull/7779))
- Support initializing the first Hub administrator from the command line, including Local-only deployments without the Docker SDK ([7696](https://github.com/agentscope-ai/QwenPaw/pull/7696))

**Skills, Tools, Automation & Channels**

- Add a `view_audio` tool so Agents can understand audio files through the existing transcription pipeline ([8083](https://github.com/agentscope-ai/QwenPaw/pull/8083))
- Configure scheduled tasks with plain-text instructions and a chosen model, preserve history after interruptions, and inspect timeout results and sessions from the Inbox ([7776](https://github.com/agentscope-ai/QwenPaw/pull/7776))
- Distribute selected Skills from the Skill pool to workspaces in batches ([7852](https://github.com/agentscope-ai/QwenPaw/pull/7852))
- Allow Skills to be assigned to custom channels as well as built-in channels ([7782](https://github.com/agentscope-ai/QwenPaw/pull/7782))
- Install or remove Skill Market sources as plugins, including QwenPaw, ClawHub, ModelScope, and Aliyun ([8128](https://github.com/agentscope-ai/QwenPaw/pull/8128))
- Add collapsible thinking panels in Feishu, with optional automatic collapse after generation ([7685](https://github.com/agentscope-ai/QwenPaw/pull/7685))
- Render Markdown tables as native Telegram Rich Messages in replies and completed streams, with fallback when unsupported ([7713](https://github.com/agentscope-ai/QwenPaw/pull/7713))

🔄 Changed

- Improve model settings and selection interactions in the Console ([8017](https://github.com/agentscope-ai/QwenPaw/pull/8017))
- Improve Settings navigation and search, add clearer runtime configuration tabs, and smooth conversation switching ([7956](https://github.com/agentscope-ai/QwenPaw/pull/7956))
- Unify memory commands under `/reme <action> key=value`, replacing `/dream`, `/memorize`, and `/reme_status` ([7444](https://github.com/agentscope-ai/QwenPaw/pull/7444))
- Limit visual compaction to older conversation history, preserve the latest two user turns, and retrieve original passages with `recall_context` ([7703](https://github.com/agentscope-ai/QwenPaw/pull/7703))
- Reduce delays in long conversations by avoiding repeated full history-database checks on every request ([7639](https://github.com/agentscope-ai/QwenPaw/pull/7639))
- Redesign conversation history with time, source, or ungrouped views, more room on small screens, richer session details, and conversation ID copying ([7665](https://github.com/agentscope-ai/QwenPaw/pull/7665), [#7688](https://github.com/agentscope-ai/QwenPaw/pull/7688), [#7788](https://github.com/agentscope-ai/QwenPaw/pull/7788), [#7846](https://github.com/agentscope-ai/QwenPaw/pull/7846))
- Use source grouping by default for the conversation list ([7972](https://github.com/agentscope-ai/QwenPaw/pull/7972))
- Move the chat file drawer to the right side ([7704](https://github.com/agentscope-ai/QwenPaw/pull/7704))
- Reduce initial Console downloads by loading chat dependencies and language resources on demand ([7829](https://github.com/agentscope-ai/QwenPaw/pull/7829))
- Stream background tool output only while its task panel is expanded, reducing idle connections ([7831](https://github.com/agentscope-ai/QwenPaw/pull/7831))
- Upgrade Make Skill to 2.1 with more reliable planning, argument validation, and evaluation guidance ([7753](https://github.com/agentscope-ai/QwenPaw/pull/7753))
- Report daily runtime activity when Agents execute, including scheduled tasks, while honoring existing telemetry consent and opt-out settings ([7802](https://github.com/agentscope-ai/QwenPaw/pull/7802))

🐛 Fixed

**PawPort**

- Show the exact asset and cause when a PawPort import fails so failed items can be retried ([7953](https://github.com/agentscope-ai/QwenPaw/pull/7953))

**Console, Chat & Files**

- Keep chat terminal tabs working on HTTP deployments that assign UUID session IDs ([8144](https://github.com/agentscope-ai/QwenPaw/pull/8144), [#8146](https://github.com/agentscope-ai/QwenPaw/pull/8146))
- Keep chat input controls usable when the window is narrow ([8145](https://github.com/agentscope-ai/QwenPaw/pull/8145))
- Keep files sent by the Agent visible after a conversation is restored from history ([7949](https://github.com/agentscope-ai/QwenPaw/pull/7949))
- Allow users to interrupt navigation between conversations while messages are loading ([8214](https://github.com/agentscope-ai/QwenPaw/pull/8214))
- Ignore replayed QQ gateway events to prevent duplicate handling of messages ([8006](https://github.com/agentscope-ai/QwenPaw/pull/8006))
- Keep queued messages bound to their original Agent and conversation, and prevent delayed chat creation or history loading from disrupting navigation and cancellation ([7382](https://github.com/agentscope-ai/QwenPaw/pull/7382))
- Preserve unsent drafts when pasting long text into Chat ([8119](https://github.com/agentscope-ai/QwenPaw/pull/8119))
- Mark interrupted tool calls correctly after stopping a reply instead of leaving them stuck in a running state ([7345](https://github.com/agentscope-ai/QwenPaw/pull/7345))
- Restore assistant reply timestamps and the correct visibility of response actions ([7851](https://github.com/agentscope-ai/QwenPaw/pull/7851))
- Run `/compact` in the current conversation instead of opening a new session ([7834](https://github.com/agentscope-ai/QwenPaw/pull/7834))
- Refresh cached text and CSV tabs when reopened or activated while preserving unsaved edits ([7902](https://github.com/agentscope-ai/QwenPaw/pull/7902))
- Move Skill pool downloads off the request path and clear unfinished temporary files ([8055](https://github.com/agentscope-ai/QwenPaw/pull/8055))
- Refresh expanded file directories without losing the current pagination state ([8149](https://github.com/agentscope-ai/QwenPaw/pull/8149))
- Render LaTeX formulas in Console release notes and Markdown file previews ([7909](https://github.com/agentscope-ai/QwenPaw/pull/7909))
- Recover from failed Console code downloads after the local service is available again, without exhausting reload attempts too early ([8154](https://github.com/agentscope-ai/QwenPaw/pull/8154), [#8219](https://github.com/agentscope-ai/QwenPaw/pull/8219))
- Make project directory selection clearer and allow applying a directory directly from the browser ([7897](https://github.com/agentscope-ai/QwenPaw/pull/7897))
- Improve loading on slow networks with smaller API responses and more resilient Skill list requests ([7917](https://github.com/agentscope-ai/QwenPaw/pull/7917))
- Limit background polling and keep the model picker responsive during slow requests ([8221](https://github.com/agentscope-ai/QwenPaw/pull/8221))
- Save model-routing changes together with other Agent settings ([7747](https://github.com/agentscope-ai/QwenPaw/pull/7747))
- Show inherited thinking settings correctly, allow direct model selection from an empty model pool, and provide Kilo free-model defaults for fresh installations ([7920](https://github.com/agentscope-ai/QwenPaw/pull/7920))
- Restore Vietnamese and Brazilian Portuguese language selection ([7752](https://github.com/agentscope-ai/QwenPaw/pull/7752))
- Preserve the sidebar’s collapsed state across reloads ([7681](https://github.com/agentscope-ai/QwenPaw/pull/7681))
- Keep Settings colors and menu typography consistent with the rest of the Console ([7682](https://github.com/agentscope-ai/QwenPaw/pull/7682), [#7805](https://github.com/agentscope-ai/QwenPaw/pull/7805))
- Restore visible keyboard-focus indicators on links ([7759](https://github.com/agentscope-ai/QwenPaw/pull/7759))
- Restore the PawPort entry in Agent configuration ([7770](https://github.com/agentscope-ai/QwenPaw/pull/7770))

**Models, Runtime & Security**

- Preserve photo orientation when resizing images that contain EXIF rotation data ([8136](https://github.com/agentscope-ai/QwenPaw/pull/8136))
- Validate Hub model settings against the model’s resolved context limit ([8168](https://github.com/agentscope-ai/QwenPaw/pull/8168))
- Keep cancellation reasons visible and continue the Agent loop when a tool is stopped ([8183](https://github.com/agentscope-ai/QwenPaw/pull/8183))
- Respect provider-resolved context windows to avoid premature conversation compaction ([7652](https://github.com/agentscope-ai/QwenPaw/pull/7652))
- Use daylight-saving-aware time zones when displaying conversation transcript timestamps ([8050](https://github.com/agentscope-ai/QwenPaw/pull/8050))
- Prevent PDFs returned by tools from breaking subsequent requests to Chat Completions models, including multimodal models ([7636](https://github.com/agentscope-ai/QwenPaw/pull/7636))
- Recover when a provider rejects unsupported `input_audio` content in conversation history ([7886](https://github.com/agentscope-ai/QwenPaw/pull/7886))
- Recover conversations after a model rejects an image or other media payload instead of replaying the rejected block on every turn ([8010](https://github.com/agentscope-ai/QwenPaw/pull/8010))
- Filter historical images according to the selected model’s resolved capabilities, including text-only models ([8190](https://github.com/agentscope-ai/QwenPaw/pull/8190))
- Keep optional tool parameters optional for Responses API models unless strict validation is explicitly enabled ([7915](https://github.com/agentscope-ai/QwenPaw/pull/7915))
- Accept newer GPT token-limit parameters used by model providers ([8090](https://github.com/agentscope-ai/QwenPaw/pull/8090))
- Correct Agent token-budget accounting and loop warnings, and recover from context overflow at the start of a streamed reply ([7748](https://github.com/agentscope-ai/QwenPaw/pull/7748))
- Reclaim older media and tool results earlier so long conversations stay within the model context window ([7965](https://github.com/agentscope-ai/QwenPaw/pull/7965), [#8193](https://github.com/agentscope-ai/QwenPaw/pull/8193))
- Prevent loop protection from terminating a task without new repeated tool calls ([7919](https://github.com/agentscope-ai/QwenPaw/pull/7919))
- Prevent duplicate or fragmented ACP replies and enforce workspace protections for external runners with different tool argument formats ([7783](https://github.com/agentscope-ai/QwenPaw/pull/7783))
- Recognize ACP permission choices by their protocol-defined kind to avoid unnecessary prompts in trusted sessions ([7732](https://github.com/agentscope-ai/QwenPaw/pull/7732))
- Find user-installed command-line tools when running as a service or inside a container ([7057](https://github.com/agentscope-ai/QwenPaw/pull/7057))
- Recover model responses after a provider stalls while closing a stream ([7960](https://github.com/agentscope-ai/QwenPaw/pull/7960))
- Prevent Windows shell commands from propagating console control events that terminate the QwenPaw server ([7910](https://github.com/agentscope-ai/QwenPaw/pull/7910))
- Reduce command-line startup time by loading initialization code only when needed ([8004](https://github.com/agentscope-ai/QwenPaw/pull/8004))
- Handle compressed MCP error responses without breaking connection negotiation ([7787](https://github.com/agentscope-ai/QwenPaw/pull/7787))
- Restrict overly broad master-key file permissions when reading existing keys on Unix systems ([7699](https://github.com/agentscope-ai/QwenPaw/pull/7699))
- Validate Skill names before using them as installation paths ([8065](https://github.com/agentscope-ai/QwenPaw/pull/8065))
- Return a validation error instead of a server error for NaN and infinite numeric inputs ([7677](https://github.com/agentscope-ai/QwenPaw/pull/7677))

**Memory, Hub & Deployment**

- Show the specific reason when redeeming a Hub invitation fails ([7952](https://github.com/agentscope-ai/QwenPaw/pull/7952))
- Close Hub database connections after transactions to avoid exhausting connections ([8038](https://github.com/agentscope-ai/QwenPaw/pull/8038))
- Allow pending memory jobs to finish during graceful shutdown, including Windows desktop shutdown ([7760](https://github.com/agentscope-ai/QwenPaw/pull/7760))
- Repair damaged history search indexes and recover retention cleanup without discarding conversation history ([7655](https://github.com/agentscope-ai/QwenPaw/pull/7655))
- Strengthen history database writes, backups, and restores to reduce data loss after interrupted or failed operations ([6459](https://github.com/agentscope-ai/QwenPaw/pull/6459))
- Distinguish failed memory jobs with empty error details from successful empty results in Inbox notifications ([7756](https://github.com/agentscope-ai/QwenPaw/pull/7756))
- Restore the memory runtime after rolling back a failed backend change ([7893](https://github.com/agentscope-ai/QwenPaw/pull/7893))
- Validate embedding-service timeouts consistently when saving settings or testing the connection ([7758](https://github.com/agentscope-ai/QwenPaw/pull/7758))
- Require confirmation before processing more than 50 pending emails and pause after three consecutive failures, with resume controls in the Inbox ([7690](https://github.com/agentscope-ai/QwenPaw/pull/7690))
- Keep approval decisions through timeout races so pending tool requests resolve consistently ([8188](https://github.com/agentscope-ai/QwenPaw/pull/8188))
- Fix Hub Local runtime initialization, CLI access, and persistent workspaces, and restore authenticated PawApp access with correct model limits ([7833](https://github.com/agentscope-ai/QwenPaw/pull/7833))
- Honor administrator overrides when checking member token permissions in Hub ([8169](https://github.com/agentscope-ai/QwenPaw/pull/8169))
- Restore file previews through the Hub personal-runtime proxy ([7766](https://github.com/agentscope-ai/QwenPaw/pull/7766))
- Record login attempts and denied runtime creation in Hub audit logs ([7683](https://github.com/agentscope-ai/QwenPaw/pull/7683))
- Handle interrupted plugin catalog downloads without returning an internal server error ([7763](https://github.com/agentscope-ai/QwenPaw/pull/7763))
- Restore loading of the bundled omp-roles Skill when it appears installed but cannot be used ([7922](https://github.com/agentscope-ai/QwenPaw/pull/7922))
- Release PawApp streaming resources reliably and prevent cancellation from leaving tasks waiting indefinitely ([7488](https://github.com/agentscope-ai/QwenPaw/pull/7488))
- Include the Console channel in desktop packages so the application can start correctly ([7816](https://github.com/agentscope-ai/QwenPaw/pull/7816))
- Restore approval and denial of tool requests when the desktop pet is enabled ([7933](https://github.com/agentscope-ai/QwenPaw/pull/7933))
- Use the same pinned application Python runtime in Docker and desktop builds ([7751](https://github.com/agentscope-ai/QwenPaw/pull/7751))
- Stop repeated output errors after the terminal that launched QwenPaw has closed ([6569](https://github.com/agentscope-ai/QwenPaw/pull/6569))

New Contributors

- [Wiziechen](https://github.com/Wiziechen)
- [TerebiSAMA](https://github.com/TerebiSAMA)
- [yang0228](https://github.com/yang0228)
- [lorenzozanee](https://github.com/lorenzozanee)
- [BeiMu-new](https://github.com/BeiMu-new)
- [fanghua-ai](https://github.com/fanghua-ai)
- [iluv7](https://github.com/iluv7)
- [shuziP](https://github.com/shuziP)
- [sdxwmlyl](https://github.com/sdxwmlyl)
- [Xinji-Mai](https://github.com/Xinji-Mai)
- [96loveslife](https://github.com/96loveslife)

**Full Changelog**: [v2.2.1...v2.2.2](https://github.com/agentscope-ai/QwenPaw/compare/v2.2.1...v2.2.2)

What's Changed
* fix(e2e): align selectors with current console ui by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/8247
* fix(history): support external database paths and portable backups by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/8246
* chore: bump the version to 2.2.2b6 by cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/8250


**Full Changelog**: https://github.com/agentscope-ai/QwenPaw/compare/v2.2.2-beta.5...v2.2.2-beta.6

What's Changed
* fix(console): preserve drafts when pasting long text (7948) by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8119
* fix(providers): recognize newer GPT token limit parameters by iluv7 in https://github.com/agentscope-ai/QwenPaw/pull/8090
* fix(console): refine desktop settings UI by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8127
* fix(chats): resolve a DST-aware process timezone for transcript timestamps by BeiMu-new in https://github.com/agentscope-ai/QwenPaw/pull/8050
* fix(console): support terminal UUIDs on HTTP origins by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8144
* feat(tools): add view_audio tool for audio understanding by shuziP in https://github.com/agentscope-ai/QwenPaw/pull/8083
* fix(console): support terminal UUIDs on HTTP origins by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8146
* fix(qwenpaw-data): keep UI host types package-local by cyruszhang in https://github.com/agentscope-ai/QwenPaw/pull/8141
* fix(providers): carry the session header on connection checks by wananing in https://github.com/agentscope-ai/QwenPaw/pull/7869
* fix(console): keep only the page title in settings headers by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8130
* fix(agents): recover from media payload rejections instead of failing by sdxwmlyl in https://github.com/agentscope-ai/QwenPaw/pull/8010
* fix(media): preserve EXIF orientation during image resizing by qbc2016 in https://github.com/agentscope-ai/QwenPaw/pull/8136
* feat(local-models): update QwenPaw-Flash 9B, 27B and 35B-A3B by Xinji-Mai in https://github.com/agentscope-ai/QwenPaw/pull/8155
* fix(skills): offload pool download copy and sweep orphan stages by BeiMu-new in https://github.com/agentscope-ai/QwenPaw/pull/8055
* fix(console): wrap composer controls when space is limited by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/8145
* fix(console): skip empty text messages in response grouping by lorenzozanee in https://github.com/agentscope-ai/QwenPaw/pull/8159
* fix(chat): prevent invalid copy icon size by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/8157
* fix(console): refresh expanded file directories and preserve pagination by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8149
* fix(console): use resolved model context limits in Hub validation by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/8168
* fix(console): improve chunk error recovery and diagnostics by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8154
* fix(hub): respect administrator token capability overrides by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/8169
* fix(approval): preserve decisions and handle timeout races by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8188
* fix(context): reclaim active results earlier and verify overflow recovery by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/8193
* feat(creator): release 2.0.1 with controlled media production by xuanrui-L in https://github.com/agentscope-ai/QwenPaw/pull/8121
* fix(task_tracker): register run only after the producer task exists by BeiMu-new in https://github.com/agentscope-ai/QwenPaw/pull/8007
* fix(console): allow users to interrupt message navigation by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/8214
* fix(tools): preserve cancellation reasons and continue agent loop by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/8183
* fix(skills): sanitize skill_name before building staging paths by BeiMu-new in https://github.com/agentscope-ai/QwenPaw/pull/8065
* fix: finish tool streams without yielding during GeneratorExit by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/8212
* fix(observability): Langfuse tool observation never records tool output by 96loveslife in https://github.com/agentscope-ai/QwenPaw/pull/7964
* feat(skill): Move hub to plugins by Leirunlin in https://github.com/agentscope-ai/QwenPaw/pull/8128
* feat(console): establish UIUX foundation by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/8217
* chore(deps): bumping version of agentscope to 2.0.10 by qbc2016 in https://github.com/agentscope-ai/QwenPaw/pull/8220
* fix(agents): resolve model capabilities before filtering history media by niceIrene in https://github.com/agentscope-ai/QwenPaw/pull/8190
* fix(console): bound background polling and unblock model picker by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/8221
* fix(history): harden SQLite persistence, backup, and restore by niceIrene in https://github.com/agentscope-ai/QwenPaw/pull/6459
* fix(console): stabilize chunk recovery and reload allowance by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8219
* fix(website): update blog by yuluo1007 in https://github.com/agentscope-ai/QwenPaw/pull/8208
* chore: bump the version to 2.2.2b5 by cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/8238

New Contributors
* iluv7 made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/8090
* shuziP made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/8083
* sdxwmlyl made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/8010
* Xinji-Mai made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/8155
* 96loveslife made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/7964

**Full Changelog**: https://github.com/agentscope-ai/QwenPaw/compare/v2.2.2-beta.4...v2.2.2-beta.5

What's Changed
* feat: add reranker UI config panel to ReMeLightMemoryCard by lecheng2018 in https://github.com/agentscope-ai/QwenPaw/pull/6399
* chore: bump the version to 2.2.2b4 by cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/7892
* perf(console): split chat dependencies and lazy-load locales by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/7829
* fix(console): improve session project directory picker by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/7897
* Fix/tool card stuck calling after stop by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/7345
* test(console): raise frontend statement coverage by +1027 statements (+543 cases, tests only) by yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/7894
* ci(release): unfreeze merges as soon as the release finishes instead of waiting for cron by yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/7901
* fix(agents): handle unknown input_audio rejections by axelray-dev in https://github.com/agentscope-ai/QwenPaw/pull/7886
* fix(console): refresh cached file tabs on activation by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/7902
* fix(console): render LaTeX math with KaTeX by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/7909
* feat: improve session list details and grouping by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/7846
* test(unit): coverage sprint batch 3 — 2720 cases across agents, routers, CLI, portability and config (+3.28pp) by yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/7911
* docs: remove accidentally committed design documents by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/7918
* chore(deps): bumping version of agentscope to 2.0.8 by qbc2016 in https://github.com/agentscope-ai/QwenPaw/pull/7913
* fix: require new tool-call evidence for doom loop escalation by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/7919
* feat(providers): unify model discovery, pricing, selection and thinking controls by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/7899
* fix(responses): default function tools to non-strict mode by qbc2016 in https://github.com/agentscope-ai/QwenPaw/pull/7915
* fix(console): improve API loading on slow networks by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/7917
* fix: resolve default thinking and streamline model onboarding by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/7920
* feat(telegram): use Rich Messages for Markdown tables by hongxicheng in https://github.com/agentscope-ai/QwenPaw/pull/7713
* perf(scroll): avoid repeated history integrity scans (Aone) by niceIrene in https://github.com/agentscope-ai/QwenPaw/pull/7639
* fix(omp): add missing SKILL.md frontmatter to omp-roles skill by yang0228 in https://github.com/agentscope-ai/QwenPaw/pull/7922
* fix(shell): isolate Windows command consoles by axelray-dev in https://github.com/agentscope-ai/QwenPaw/pull/7910
* fix(history): repair FTS corruption and retention cleanup (7596) by niceIrene in https://github.com/agentscope-ai/QwenPaw/pull/7655
* fix(desktop): validate sharded model catalog after packaging by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/7932
* fix(pet): preserve caller identity when resolving approvals by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/7933
* fix(console): show sent files from serialized chat history by fancyboi999 in https://github.com/agentscope-ai/QwenPaw/pull/7949
* fix(agents): drop empty assistant text blocks by wananing in https://github.com/agentscope-ai/QwenPaw/pull/7409
* test(unit): make the batch-3 lock and portability tests cross-platform by yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/7941
* fix(hub): distinguish invitation redemption failure reasons by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/7952
* docs(website): add download provenance and usage policy by jinglinpeng in https://github.com/agentscope-ai/QwenPaw/pull/7955
* fix(providers): recover after stalled stream cleanup by lorenzozanee in https://github.com/agentscope-ai/QwenPaw/pull/7960
* fix(console): gate tool-call lifecycle queries on execution start by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/7971
* fix(console): default session list grouping to source by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/7972
* feat(console): add authenticated multi-tab chat terminal by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/7861
* fix(portability): preserve actionable per-asset import failures by Luohh5 in https://github.com/agentscope-ai/QwenPaw/pull/7953
* fix(context): reclaim historical media in Scroll and align thinking omission with token counting by Leirunlin in https://github.com/agentscope-ai/QwenPaw/pull/7965
* feat(console): unify settings UX and smooth conversation transitions by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/7956
* feat(console): unify interface font scaling by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8005
* fix(qq): drop replayed gateway events by id and sequence by BeiMu-new in https://github.com/agentscope-ai/QwenPaw/pull/8006
* fix(console): stabilize modal and tool config transitions by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8016
* chore(deps): bumping version of agentscope to 2.0.9 by qbc2016 in https://github.com/agentscope-ai/QwenPaw/pull/8008
* fix: include provider and error details in model discovery warnings by qbc2016 in https://github.com/agentscope-ai/QwenPaw/pull/8014
* fix(console): restore chat icons and truncate project labels by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8019
* perf(cli): lazy-import init_cmd in app_cmd startup path by fanghua-ai in https://github.com/agentscope-ai/QwenPaw/pull/8004
* fix(website): update qwenpaw-developer-day-collection blog by yuluo1007 in https://github.com/agentscope-ai/QwenPaw/pull/7806
* fix(ci): resolve cross-platform path handling and test failures by cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/8003
* feat(console): polish model settings and navigation interactions by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/8017
* fix(chat): restore compact copy action icons by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/8021
* fix(ci): address cross-platform paths, sandbox cleanup, and Windows terminal interrupts by cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/8026
* fix(desktop): disable NSIS solid compression by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/8025
* fix(terminal): support high posix descriptors by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/8032
* fix(console): align e2e tests with redesigned UI by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/8037
* fix(memory): restore runtime after backend rollback by jinliyl in https://github.com/agentscope-ai/QwenPaw/pull/7893
* fix(ci): correct first-time PR detection and add automatic size labels by cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/8039
* fix(hub): close database connections after transactions by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/8038
* fix(ci): change permission by cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/8043
* fix(e2e): stop stalled session cleanup by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/8041

New Contributors
* yang0228 made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/7922
* lorenzozanee made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/7960
* BeiMu-new made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/8006
* fanghua-ai made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/8004

**Full Changelog**: https://github.com/agentscope-ai/QwenPaw/compare/v2.2.2-beta.3...v2.2.2-beta.4

What's Changed
* fix(console): restore assistant response actions by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/7851
* fix(e2e): re-anchor console selectors broken by the 7502 redesign and harden session-list assertions by yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/7860
* chore: bump the version to v2.2.2b3 by cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/7855
* ci(release): gate artifact publishing on the test gate and make the E2E watch set blocking by yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/7862
* feat(feishu): collapsible reasoning panel with opt-in auto-collapse by hongxicheng in https://github.com/agentscope-ai/QwenPaw/pull/7685
* fix(console): send /compact on the current chat instead of opening a new session by yuanxs21 in https://github.com/agentscope-ai/QwenPaw/pull/7834
* feat(skill): Add skill batch broadcast by Leirunlin in https://github.com/agentscope-ai/QwenPaw/pull/7852
* fix(hub): correct local runtime CLI, PawApp access and model defaults by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/7833
* fix(ci): stabilize Windows reload and snapshot tests by jinliyl in https://github.com/agentscope-ai/QwenPaw/pull/7863


**Full Changelog**: https://github.com/agentscope-ai/QwenPaw/compare/v2.2.2-beta.1...v2.2.2-beta.3

What's Changed
* feat(console): improve grouped chat history by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/7665
* feat(memory): unify ReMe slash commands by jinliyl in https://github.com/agentscope-ai/QwenPaw/pull/7444
* chore: bump the version to 2.2.2b1 by cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/7695
* test(unit): coverage sprint batch 2 — 2475 cases across channels, visual compression, routers, runtime and CLI (+5.02pp) by yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/7653
* feat(pawport): an import flow to bring instructions, settings, skill, plugins, projects, and recent work from another agent into QwenPaw by Luohh5 in https://github.com/agentscope-ai/QwenPaw/pull/6960
* fix(models): preserve provider-resolved context windows by wangfei010313 in https://github.com/agentscope-ai/QwenPaw/pull/7652
* fix(console): simplify grouped session pagination by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/7688
* fix(api): return 422 for non-finite validation inputs by jinliyl in https://github.com/agentscope-ai/QwenPaw/pull/7677
* docs(multi-agent): drop nonexistent `qwenpaw providers` command by c020627 in https://github.com/agentscope-ai/QwenPaw/pull/7706
* docs(mcp): fix wrong agent.json field name in Chinese MCP page by c020627 in https://github.com/agentscope-ai/QwenPaw/pull/7675
* test(unit): repair the approval command handler stub after 7444 by yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/7701
* fix(mailbox): add safeguards against unexpectedly large mail-processing batches and repeated failed agent calls by Luohh5 in https://github.com/agentscope-ai/QwenPaw/pull/7690
* ci: slim the PR gate to Ubuntu-only backend tiers and add a release-time full test gate by yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/7697
* test(console): add regression coverage for embedding verification persistence and the toDisplayUrl twin (+18 cases) by yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/7669
* fix(console): persist model routing when saving agent edits by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/7747
* fix(governance): harden master key file permissions on read by cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/7699
* fix(skill): update make-skill to v2.1 for better robustness by Leirunlin in https://github.com/agentscope-ai/QwenPaw/pull/7753
* feat(context): Improving visual compaction by Leirunlin in https://github.com/agentscope-ai/QwenPaw/pull/7703
* feat(cron): Improve cron task configuration, preserve execution history, and enhance inbox results by lalaliat in https://github.com/agentscope-ai/QwenPaw/pull/7776
* feat(hub): support local administrator bootstrap by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/7696
* fix(hub): authenticate native file preview requests by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/7766
* fix: preserve loop warnings and correct budget and overflow recovery by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/7748
* docs(pawport): add docs and blog for pawport by Luohh5 in https://github.com/agentscope-ai/QwenPaw/pull/7781
* fix(pawport): restore the missing PawPort entry in More settings → Agent configuration by Luohh5 in https://github.com/agentscope-ai/QwenPaw/pull/7770
* fix(skill): Enable customized channel for skill selection by Leirunlin in https://github.com/agentscope-ai/QwenPaw/pull/7782
* fix(console): persist sidebar collapsed state across reloads by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/7681
* fix(console): use semantic tokens in SettingsCenter by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/7682
* feat(console): move chat files drawer to the right by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/7704
* feat(console): show send_file_to_user files in response artifact list by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/7750
* fix(hub): audit login attempts and denied runtime creation by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/7683
* fix(mcp): avoid double-decompressing gzip 4xx MCP responses by yuanxs21 in https://github.com/agentscope-ai/QwenPaw/pull/7787
* fix(memory): distinguish empty error notifications by jinliyl in https://github.com/agentscope-ai/QwenPaw/pull/7756
* fix(console): align embedding timeout validation by jinliyl in https://github.com/agentscope-ai/QwenPaw/pull/7758
* fix(console): restore visible link focus indicators by jinliyl in https://github.com/agentscope-ai/QwenPaw/pull/7759
* fix(agents): strip tool-result PDF document blocks for OpenAI chat-completions requests regardless of multimodal support by Wiziechen in https://github.com/agentscope-ai/QwenPaw/pull/7636
* feat(console): add customizable theme colors by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/7741
* fix(plugins): handle catalog response read failures by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/7763
* feat(proj dir): support configurable multi-folder default workspaces by x1n95c in https://github.com/agentscope-ai/QwenPaw/pull/7789
* fix(acp): select permission options by protocol kind by axelray-dev in https://github.com/agentscope-ai/QwenPaw/pull/7732
* fix: match settings menu font weight by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/7805
* fix(console): suppress EIO/EPIPE print errors after detached TTY by hehuang139 in https://github.com/agentscope-ai/QwenPaw/pull/6569
* fix(ACP): Improves the experience of delegating work to external ACP runners by x1n95c in https://github.com/agentscope-ai/QwenPaw/pull/7783
* feat(chat): adapt AgentScopeRuntimeWebUI 1.2 and stabilize queues by sanfran1068 in https://github.com/agentscope-ai/QwenPaw/pull/7382
* fix(pack): force-include console channel in PyInstaller bundle by TerebiSAMA in https://github.com/agentscope-ai/QwenPaw/pull/7816
* ci(e2e): enable the declared pytest-timeout and raise the per-shard job timeout to 60 minutes by yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/7803
* fix(shell): add user-local bin dirs to subprocess PATH by lcq225 in https://github.com/agentscope-ai/QwenPaw/pull/7057
* feat(console): redesign sidebar session list for small screens by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/7788
* test(console): wait for chat ownership before submit by zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/7819
* feat(console): configure custom providers in one dialog by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/7826
* fix(console): make vi and pt-BR language selection work by zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/7752
* feat(creator) 1.3.0: OpenCode Zen/Go endpoints, parallel asset understanding with upload failure recovery, style-anchor versioning, overlay/subtitle timeline correction, prompt-sync gate recovery, and multi-episode production hardening by xuanrui-L in https://github.com/agentscope-ai/QwenPaw/pull/7823
* fix(docker): align app Python runtime with desktop by jinglinpeng in https://github.com/agentscope-ai/QwenPaw/pull/7751
* feat(telemetry): report daily Runtime activity on Agent execution by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/7802
* feat(hub): add model gateway, member governance and usage dashboard by rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/7779

New Contributors
* Wiziechen made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/7636
* TerebiSAMA made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/7816

**Full Changelog**: https://github.com/agentscope-ai/QwenPaw/compare/v2.2.1-beta.2...v2.2.2-beta.1