v2.0.0.post3

## What's Changed
* fix(mcp): migrate ${VAR} headers to env credential refs during driver migration by @xiaoming-qxm in https://github.com/agentscope-ai/QwenPaw/pull/6091
* refactor(ci): harden desktop workflows and drop legacy verify dead code by @yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/6110
* fix(memory): restrict automatic memory to external user queries by @jinliyl in https://github.com/agentscope-ai/QwenPaw/pull/6120
* feat(plugin/cloudpaw): migrate to QwenPaw 2.0 and bump version to 0.0.4 by @Saint-Yin in https://github.com/agentscope-ai/QwenPaw/pull/6099
* fix(governance): clear stale OFF-mode sandbox state by @niceIrene in https://github.com/agentscope-ai/QwenPaw/pull/6122
* fix(runtime): honor per-request model override by @RerankerGuo in https://github.com/agentscope-ai/QwenPaw/pull/5731
* fix: allow auto_memory_interval to be set to 0 to disable auto memory by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/6135
* fix(mcp): make legacy MCP migration one-shot via schema watermark (#6130) by @xiaoming-qxm in https://github.com/agentscope-ai/QwenPaw/pull/6133
* fix(console): require auto_memory_interval as int >= 0, disallow empty by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/6142
* ci: pass Supabase config to website build by @Osier-Yi in https://github.com/agentscope-ai/QwenPaw/pull/6143
* fix(utils): add errors='replace' to _run_command for GBK compatibility by @liu6yi1 in https://github.com/agentscope-ai/QwenPaw/pull/6140
* feat(website): add blog view/like counts and switch GA to QwenPaw property by @yuluo1007 in https://github.com/agentscope-ai/QwenPaw/pull/6147
* feat(memory): enhance ReMe configuration and indexing safeguards by @jinliyl in https://github.com/agentscope-ai/QwenPaw/pull/6153
* fix(agents): surface malformed tool-call input to model by @wananing in https://github.com/agentscope-ai/QwenPaw/pull/5761
* fix(desktop): keep Tauri updates on OSS only by @jinglinpeng in https://github.com/agentscope-ai/QwenPaw/pull/6071
* fix(desktop): prevent WKWebView from pinning stale console frontend by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/6107
* fix(chat): preserve whitespace in streaming thinking/text deltas by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/6166
* fix: images stripped for multimodal models when model info lookup fails or builtin annotation is wrong by @qbc2016 in https://github.com/agentscope-ai/QwenPaw/pull/6154
* feat(website): add Community Benefits nav and improve blog tags/meta cards by @yuluo1007 in https://github.com/agentscope-ai/QwenPaw/pull/6164
* fix(website): update architecture overview by @cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/6172
* feat(crons): add silent agent delivery by @AaronZ345 in https://github.com/agentscope-ai/QwenPaw/pull/6080
* fix(scroll): harden context limits and recoverable tool-result compaction by @niceIrene in https://github.com/agentscope-ai/QwenPaw/pull/6123
* chore(deps): bumping version of agentscope to 2.0.4.post1 by @qbc2016 in https://github.com/agentscope-ai/QwenPaw/pull/6179
* fix(loop): fine-tune doom loop thresholds, fix frontend after calc & align tests with #5761 by @rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/6184
* fix(mcp): unblock workspace startup after connection timeout by @jinglinpeng in https://github.com/agentscope-ai/QwenPaw/pull/6174
* fix(chat): refresh updated_at on user messages and invalidate stale m… by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/6180
* fix(channels): bound unbounded state and track fire-and-forget tasks to prevent memory leaks by @hongxicheng in https://github.com/agentscope-ai/QwenPaw/pull/6168
* fix(memory): add dream schedule toggle by @ployts in https://github.com/agentscope-ai/QwenPaw/pull/6171
* test(ci): run console vitest with coverage in nightly full sweep by @yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/6194
* test(e2e): adapt selectors for v2.0.0 UI redesigns by @yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/6185
* fix(model_factory): resolve file:// URIs in DataBlock to local paths before formatting by @qbc2016 in https://github.com/agentscope-ai/QwenPaw/pull/6191
* fix(skill): skill-hub related memory leakage by @Leirunlin in https://github.com/agentscope-ai/QwenPaw/pull/6208
* fix(utils): drop redundant nvidia-smi probe in get_vram_size_gb by @Yigtwxx in https://github.com/agentscope-ai/QwenPaw/pull/6204
* fix: sanitize fallback namespace in MCP tool name to comply with OpenAI constraints by @qbc2016 in https://github.com/agentscope-ai/QwenPaw/pull/6209
* fix(cli): conditionally elevate UAC on Windows so VBS headless launchers stay windowless by @wangfei010313 in https://github.com/agentscope-ai/QwenPaw/pull/6127
* ci: add CodeQL 2-shard security scan (dry-run) + Dependabot by @hanson-hex in https://github.com/agentscope-ai/QwenPaw/pull/6027
* fix(memory): bound summary task history by @jinliyl in https://github.com/agentscope-ai/QwenPaw/pull/6206
* chore: bump the version to 2.0.0post3 by @cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/6211
* feat(console): add history_retention_days config to context compact p… by @zhaozhuang521 in https://github.com/agentscope-ai/QwenPaw/pull/6214
* fix(website): switch GA tag ID and add Jul 17 developer day session by @yuluo1007 in https://github.com/agentscope-ai/QwenPaw/pull/6212
* test(integration): Sprint 4.2 — access-control / fork / coding-mode / agent-status by @yutai78786 in https://github.com/agentscope-ai/QwenPaw/pull/6213
* feat(governance): add rules by @cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/6215
* fix: expand regex shorthands in tool schema patterns for GBNF compatibility by @qbc2016 in https://github.com/agentscope-ai/QwenPaw/pull/6216
* fix(browser): add MAX_WAITTIME for browser use by @x1n95c in https://github.com/agentscope-ai/QwenPaw/pull/6170
* fix: treat unprobed multimodal as fail-open to prevent image stripping by @qbc2016 in https://github.com/agentscope-ai/QwenPaw/pull/6217
* fix(runtime): pass model_slot_override from HTTP request to model factory by @cuiyuebing in https://github.com/agentscope-ai/QwenPaw/pull/6218
* fix(token_usage): don't persist an unseeded cache on shutdown by @Yigtwxx in https://github.com/agentscope-ai/QwenPaw/pull/6220
* Refactor channel base by @yuanxs21 in https://github.com/agentscope-ai/QwenPaw/pull/6159
* feat: bound multi-agent startup and improve readiness UX by @rayrayraykk in https://github.com/agentscope-ai/QwenPaw/pull/6198

## New Contributors
* @liu6yi1 made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/6140
* @AaronZ345 made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/6080
* @Yigtwxx made their first contribution in https://github.com/agentscope-ai/QwenPaw/pull/6204

**Full Changelog**: https://github.com/agentscope-ai/QwenPaw/compare/v2.0.0.post2...v2.0.0.post3