Qwen Code v0.20.0

<!-- qwen-release-notes:v1 --> ## Highlights _See the complete change list below._ ## Breaking Changes No known breaking changes. ## Complete Change List ### Features - feat(cli): Add bounded daemon log rotation ([#6969](https://github.com/QwenLM/qwen-code/pull/6969)) by @doudouOUC - feat(review): bake the round label into a findings role's identity line and key ([#7171](https://github.com/QwenLM/qwen-code/pull/7171)) by @wenshao - feat(webshell): replay ChatRecord history in readonly WebShell ([#6999](https://github.com/QwenLM/qwen-code/pull/6999)) by @cxruan - feat(ui): let the user read the full plan from the exit_plan_mode confirmation ([#7060](https://github.com/QwenLM/qwen-code/pull/7060)) by @zjunothing - feat(providers): add qwen3.8-max-preview to Token Plan model list ([#7199](https://github.com/QwenLM/qwen-code/pull/7199)) by @qwen-code-dev-bot ### Bug Fixes - fix(sdk-java): preserve exception cause in AcpClient init failures ([#7189](https://github.com/QwenLM/qwen-code/pull/7189)) by @chinesepowered - fix(web-shell): proxy /goals route in Vite dev server ([#7187](https://github.com/QwenLM/qwen-code/pull/7187)) by @wenshao - fix(sdk-java): correct TIMEOUT_30_MINUTES to actually be 30 minutes ([#7188](https://github.com/QwenLM/qwen-code/pull/7188)) by @chinesepowered - fix(cli): emit deferred stream-json startup warnings ([#7174](https://github.com/QwenLM/qwen-code/pull/7174)) by @barry166 - fix(review): judge a CI check by its name's latest run, not by any leftover ([#7183](https://github.com/QwenLM/qwen-code/pull/7183)) by @wenshao - fix(review): count Step 6's inline findings from the drafted comments, never from typed numbers ([#7173](https://github.com/QwenLM/qwen-code/pull/7173)) by @wenshao - fix(web-shell): dedupe restored images and harden the sidebar shortcut handler ([#7169](https://github.com/QwenLM/qwen-code/pull/7169)) by @zjunothing - fix(mcp): normalize tool names for strict providers ([#6976](https://github.com/QwenLM/qwen-code/pull/6976)) by @ran411285752 - fix(core): apply native tool calling schema for gemma 4 ([#7177](https://github.com/QwenLM/qwen-code/pull/7177)) by @ghisguth - fix(cli): share one process.stdout resize listener in useTerminalSize ([#7186](https://github.com/QwenLM/qwen-code/pull/7186)) by @mvanhorn - fix: surface underlying .cause of OpenAI-compatible connection errors in debug log and API error message ([#7010](https://github.com/QwenLM/qwen-code/pull/7010)) by @mvanhorn - fix(web-shell): prevent toolbar label clipping ([#7196](https://github.com/QwenLM/qwen-code/pull/7196)) by @carffuca - fix(review): one disclosure per subject — dedupe Not-reviewed, collapse an all-built-none-launched roster ([#7190](https://github.com/QwenLM/qwen-code/pull/7190)) by @wenshao - fix(review): an unverified Critical must not become a public blocker — soften the Request changes it rides ([#7191](https://github.com/QwenLM/qwen-code/pull/7191)) by @wenshao ### Performance - perf(channels): cache channel memory recall ([#7175](https://github.com/QwenLM/qwen-code/pull/7175)) by @qwen-code-dev-bot - perf(cli): Defer TUI runtime from ACP startup ([#7182](https://github.com/QwenLM/qwen-code/pull/7182)) by @doudouOUC ### Internal Changes - chore(vscode-ide-companion): sync third-party notices and guard against future drift ([#7161](https://github.com/QwenLM/qwen-code/pull/7161)) by @wenshao - ci(autofix): harden the address path against stale targets and untrusted route events ([#7163](https://github.com/QwenLM/qwen-code/pull/7163)) by @wenshao ## New Contributors - @ghisguth made their first contribution in [#7177](https://github.com/QwenLM/qwen-code/pull/7177) **Full Changelog**: https://github.com/QwenLM/qwen-code/compare/v0.19.12...v0.20.0