Skip to content

Release v0.19.0

Latest

Choose a tag to compare

@qwen-code-ci-bot qwen-code-ci-bot released this 23 Jun 03:27
· 1 commit to release/v0.19.0 since this release

What's Changed

  • chore(release): v0.18.5 by @qwen-code-ci-bot in #5558
  • ci(release): Auto-publish VSCode companion after stable releases by @yiliang114 in #5572
  • fix(cli): render full resume preview history by @cyphercodes in #5565
  • fix(cli): fill content area background on wrapped input lines by @lcheng321 in #5568
  • fix(cli): fail non-interactive runs on loop detection by @cyphercodes in #5564
  • fix(core): respect zero OpenAI log file limit by @russeell in #5569
  • fix(core): keep bare fast model on current auth by @yiliang114 in #5553
  • feat(lint): enforce kebab-case filenames with ESLint by @ZijianZhang989 in #4797
  • [codex] Fix legacy filename allowlist for kebab-case lint by @qqqys in #5578
  • refactor(cli): Rename serve files to kebab-case by @doudouOUC in #5592
  • feat(extensions): support archive install sources by @kkhomej33-netizen in #4909
  • fix(cli): prefer command name over alias in slash completion ranking by @Alex-ai-future in #5577
  • test(integration): add fake OpenAI server for no-AK daemon tests by @yiliang114 in #5560
  • refactor(core): replace OpenRouter/Requesty provider classes with customHeaders in preset by @pomelo-nwu in #5539
  • feat(voice): voice dictation with native capture, streaming, and biasing by @qqqys in #5502
  • feat: revivable background sub-agents and subagent transcript TTL by @qqqys in #5556
  • feat(core): add Artifact tool to publish interactive HTML pages by @qqqys in #5557
  • feat(cli): add optional [HH:MM:SS] timestamp before each assistant turn by @ZijianZhang989 in #5001
  • fix(core): require confirmation when user manually enters plan mode by @LaZzyMan in #5595
  • fix(core): always-on guard for consecutive identical tool calls (#5019) by @wenshao in #5573
  • fix(ci): harden tmux triage reporting by @yiliang114 in #5548
  • fix(voice): surface native recorder fallback so missing prebuilds aren't silent by @qqqys in #5605
  • fix(core): prevent GLM on DashScope from dropping web_fetch content by @tanzhenxin in #5599
  • Fix native voice recorder retry after stop errors by @qqqys in #5609
  • [codex] ci(triage): acknowledge slash triage requests by @yiliang114 in #5594
  • [codex] Support artifact auto-open setting by @qqqys in #5617
  • feat(tui): remove tool group borders and collapse completed tool results by @chiga0 in #5003
  • feat(workflows): finish Dynamic Workflows port — resume, saved workflows, keyword trigger, notifications (#4721) by @LaZzyMan in #5600
  • feat(web-shell): support daemon session branching by @ytahdn in #5613
  • fix(core): backend-aware artifact publish confirmation + cancel handling by @qqqys in #5615
  • test(integration): run no-AK smoke tests on PRs by @yiliang114 in #5607
  • fix(cli): Fail dangling replayed tool calls by @doudouOUC in #5624
  • fix(voice): bundle native audio addon into standalone archives by @qqqys in #5628
  • ci: route in-repo PRs' Linux test to self-hosted runner by @yiliang114 in #5620
  • ci(release): queue release failures for autofix by @yiliang114 in #5551
  • feat(cli): browse MCP server resources in the /mcp dialog by @wenshao in #5635
  • refactor(cli): Finish serve kebab-case filenames by @doudouOUC in #5604
  • feat(core): default-on preserve_thinking for DashScope provider by @tanzhenxin in #5637
  • ci(audio-capture): cross-compile darwin-x64 prebuild on arm64, drop macos-13 runner by @qqqys in #5643
  • ci: harden self-hosted runner routing (follow-up to #5620 review) by @yiliang114 in #5644
  • fix(cli): harden ACP session list pagination params by @tt-a1i in #5618
  • docs(mcp): correct mcp add scope default by @tt-a1i in #5593
  • feat(tui): add thinking block viewer with Alt+T expand/collapse by @chiga0 in #5627
  • fix(cli): parse serve rate limit env strictly by @tt-a1i in #5612
  • fix(core): parse API timeout env strictly by @tt-a1i in #5602
  • fix(serve): validate readText line limits by @tt-a1i in #5639
  • fix(core): escape backslashes and quotes in emacs ediff paths by @he-yufeng in #5630
  • fix(cli): detect USE_OPENAI auth when the model is set via QWEN_MODEL by @he-yufeng in #5647
  • test(integration): skip qwen serve streaming suite under container sandbox by @yiliang114 in #5655
  • refactor(core): extract Protocol enum and decouple model identity from auth type by @zzhenyao in #5089
  • fix(webui): stop auto-recreating session on user-initiated delete by @yuanyuanAli in #5633
  • fix(cli): keep settings v5 migration idempotent by @yiliang114 in #5676
  • fix(test): restore openai model selection in ACP set_config_option test by @wenshao in #5721
  • fix(test): isolate ACP integration agents via QWEN_HOME to end parallel-settings race by @wenshao in #5724
  • fix(test): make ACP set_config_option test use a deterministic openai provider model by @wenshao in #5728
  • fix(core): keep active runtime model in default getAllConfiguredModels listing by @wenshao in #5729
  • feat(desktop): show file preview in a resizable side panel instead of fullscreen by @DragonnZhang in #5730
  • fix(core): remove redundant reportSuggestionUsage causing double-counted stats by @huww98 in #5684
  • fix(core): validate ask_user_question answer indexes by @russeell in #5622
  • feat(core): respect configurable agent ignore files by @shenyankm in #4653
  • fix(daemon): Refresh workspace provider defaults by @doudouOUC in #5638
  • feat(core): add fastOnly/voiceOnly flags to hide models from main model list by @callmeYe in #5632

New Contributors

Full Changelog: v0.18.5...v0.19.0