agentscope-ai/QwenPaw v1.1.1 on GitHub

✨ Added

Providers and Models

OpenRouter Provider: Built-in OpenRouter provider with model discovery, series browsing, and filtering by modality and pricing (#1192)
OpenCode Provider: Built-in OpenAI-compatible OpenCode (Zen) provider with free models (#2463)
Model ID Autocomplete: Autocomplete dropdown for model ID selection when adding models, with model discovery enabled by default for all providers (#3175, #3341)

Multi-Agent System

Built-in Agent Collaboration Tools: New list_agents and chat_with_agent built-in tools with a dedicated skill and streamlined CLI agent commands for inter-agent communication (#3292)

Channels

Matrix Channel Rewrite: End-to-end encryption (E2EE), mention handling, message history support, and markdown rendering (#2509)
Feishu Quoted Messages: Reply-chain message handling with text, post, image, and file content extraction (#3207)
DingTalk QR Authentication: QR code device-flow authentication for DingTalk channel setup in console (#3315)

Security

Extended Shell Command Guards: New guard rules covering $IFS injection, control characters, Unicode whitespace, /proc/*/environ access, dangerous jq flags, and Zsh-specific risky builtins (#3303)

Tools & Skills

ClawHub Skill Requirements: Support for skill requirements in ClawHub format with multiple metadata namespace resolution (#3310)
Media URL Viewing: view_image and view_video tools now accept HTTP/HTTPS URLs for direct media viewing without download (#3358)

Providers and Models

Multimodal Probe Unification: Image support probing across Anthropic, Gemini, and OpenAI providers now shares a single evaluation path with improved false-positive detection (#3367)
Message Normalization for Model Switching: Messages are normalized at request time so media attachments are preserved in memory when switching between model providers (#3359)
Anthropic Media Deduplication: Duplicate base64 media in tool results is replaced with text placeholders to prevent exceeding Anthropic's message size limit (#3372)

Channels

DingTalk SDK Migration: Channel migrated to the official Alibaba Cloud SDK with emoji reaction feedback during processing and media delivery in AI Card mode (#3236, #3337, #3374)
Feishu WebSocket Stability: Event loop handling refactored for improved cross-thread reliability during reconnections (#3360)
WeChat Reply Limit Warning: Channel settings now display a warning about the context_token reply limit for WeChat iLink (#3376)

Tools & Skills

Browser Managed CDP: Default browser start strategy changed to managed CDP with automatic Chromium detection, port allocation, and process lifecycle management (#3164)

Console & UI

Model Management Redesign: Provider model management modal redesigned with capability tags, model searching, and simplified card layout (#3273, #3294)
Agent Config Tabs: Agent configuration page refactored from stacked cards to a tabbed interface (#3354)
Skill Selection UI: Improved skill selection with tag suggestions, tooltips for long names, refined loading behavior, and bulk select actions (#3320, #3362, #3373)
Downloads Page: Website downloads page reworked with stable and preview version grouping (#3353)

Channels

QQ WebSocket Shutdown: stop() no longer blocks for 8 seconds by force-closing the WebSocket on shutdown (#3188)

Console & UI

Fixed chat session pin button contrast in dark mode (#3267)
Markdown links in header now navigate in-app instead of opening new tabs (#3186)
Website contributors layout alignment for Chinese locale (#3332)

Providers

Fixed local model download failure on Windows ([Errno 22] Invalid argument) (#3321)
Omit tool_choice=auto for vLLM compatibility to avoid 400 errors on deployments without --enable-auto-tool-choice (#3295)

RESTful API Tutorial: Comprehensive REST API tutorial covering chat endpoints, authentication, multi-turn sessions, streaming, and agent switching (#3335)
Skill Chat Commands: Added skill chat command reference to commands documentation (#3330)

Full Changelog: v1.1.0...v1.1.1