Starstruk Logo MarkStarstruk

v2.0.0.post1

agentscope-ai/QwenPawv2.0.0.post1Jul 13, 2026by xieyxclack

AI Summary

This release implements critical infrastructure changes including trusted proxy verification, governance auto-sync, and various UI and runtime fixes to prepare for the v2.0.0 launch.

Key Highlights

  • Implemented trusted proxy verification and client IP resolution.
  • Governance auto-sync for DEFAULT_USER_RULES.
  • Added `/api/healthz` readiness probe endpoint.
  • Improved dark mode text contrast.
  • Fixed Telegram polling against conflict loops.

New Features

  • Trusted proxy authentication.
  • Governance auto-sync functionality.
  • Health probe endpoint.
  • Governance relaxations (no-finding fallback).
  • Desktop improvements (Autofill fix).

Full Release Notes

## What's Changed
* chore: bump version to 2.0.0.post1 by @rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/6007
* fix(models): prevent browser autofill on provider search input (#5981) by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/6011
* fix: fix legacy session loading for file content blocks by @qbc2016 in https://github.com/agentscope-ai/QwenPaw/pull/6010
* ci: add real-behavior-proof gate + wire pr-spam-gate into tests.yml by @hanson-hex in https://github.com/agentscope-ai/QwenPaw/pull/5844
* fix(console): improve dark mode text contrast for loop templates and chat history by @Marlin-Phone in https://github.com/agentscope-ai/QwenPaw/pull/5975
* fix(console): promote formatCompact unit on rounding rollover by @Osamaali313 in https://github.com/agentscope-ai/QwenPaw/pull/5791
* Feat/strict mode disable always allow by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/6019
* refactor(governance): auto-sync DEFAULT_USER_RULES without manual whitelist by @rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/6025
* feat(memory): add Windows-safe session ID encoding for ReMe file storage by @jinliyl in https://github.com/agentscope-ai/QwenPaw/pull/6022
* fix(chat): prioritize built-in slash commands by @RerankerGuo in https://github.com/agentscope-ai/QwenPaw/pull/5751
* feat(app): add /api/healthz readiness probe endpoint by @rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/6028
* feat(auth): implement trusted proxy verification and enhance client IP resolution by @zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/6030
* docs(quickstart): add AgentScope Platform deployment option by @Osier-Yi in https://github.com/agentscope-ai/QwenPaw/pull/6033
* feat(website): add AgentScope Platform entry in nav and hero CTA by @yuluo1007 in https://github.com/agentscope-ai/QwenPaw/pull/6035
* fix: filter tool results with same id by @qbc2016 in https://github.com/agentscope-ai/QwenPaw/pull/6032
* fix(console): allow enqueue on new chat and migrate temp session queue by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/6040
* fix(Telegram): harden Telegram polling against 409 conflict loop by @hongxicheng in https://github.com/agentscope-ai/QwenPaw/pull/6005
* feat(governance): allow gh CLI commands by @cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/6031
* fix(mcp): apply access policy updates immediately by @wananing in https://github.com/agentscope-ai/QwenPaw/pull/5949
* fix: skills page scroll loading stops after first batch by @feng183043996 in https://github.com/agentscope-ai/QwenPaw/pull/5968
* fix(packaging): bundle AgentScope resource files by @jinglinpeng in https://github.com/agentscope-ai/QwenPaw/pull/6026
* fix(providers): use max_completion_tokens for reasoning models by @RerankerGuo in https://github.com/agentscope-ai/QwenPaw/pull/6015
* fix: multi-layer orphan tool_result message defense by @tadebao in https://github.com/agentscope-ai/QwenPaw/pull/5989
* fix(plugins): bridge register_tool to runtime ToolRegistry pipeline by @zhijianma in https://github.com/agentscope-ai/QwenPaw/pull/6044
* fix(console): clear message queue when a session is deleted by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/6045
* refactor(tool_calls): unify result pruning with block-scoped metadata by @jinliyl in https://github.com/agentscope-ai/QwenPaw/pull/5935
* feat(governance): relax no-finding fallback and add global sandbox sw… by @vanwaals in https://github.com/agentscope-ai/QwenPaw/pull/6054
* fix(tool_calls): flatten offload hint + temporarily disable broken offload mechanism by @rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/6058

## New Contributors
* @Marlin-Phone made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/5975
* @feng183043996 made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/5968
* @tadebao made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/5989

**Full Changelog**: https://github.com/agentscope-ai/QwenPaw/compare/v2.0.0...v2.0.0.post1