github QwenLM/qwen-code v0.27.2-preview.0
Release v0.27.2-preview.0

latest release: v0.27.2
pre-release59 minutes ago

What's Changed

  • fix(ci): read prettier's whole ignore set at the base tip by @wenshao in #16729
  • fix(cli,core): let an Agent Host retry an enrollment whose answer was lost by @wenshao in #16722
  • fix(channels): shape-check authorExclude on the inbound task record by @wenshao in #16740
  • feat(managed-agent): import Skills from the original Runtime by @doudouOUC in #16638
  • docs: clarify tool bridge requirements when migrating from tools.core by @521Peter in #16750
  • fix(ci): annotate a truncated tree and pin the encoded tree ref by @wenshao in #16747
  • refactor(managed-agent): give JDBC stores names distinct from their interfaces by @doudouOUC in #16759
  • fix(ci): stop the Ctrl+C and Java heap failures that block fork PRs by @TianYuan1024 in #16150
  • fix(core): decode ANSI-C words and the -c option terminator with bash's rules by @yiliang114 in #16540
  • feat(cli): thread /btw session history and decouple its request lifecycle by @sorrycc in #16408
  • refactor(managed-agent): share Hosted Harness feature tokens between connectors by @doudouOUC in #16763
  • fix(ci): stop stale-base updates from restarting timed-out PR reviews by @wenshao in #16749
  • fix(web-shell): bump @datafe-open/markdown-chart to 0.4.1 by @zhangxy-zju in #16021
  • ci: reduce all sharded CI lanes to two shards by @wenshao in #16764
  • feat(managed-agent): add Tool v4 execution measurements by @doudouOUC in #16498
  • test(core): keep the background renewal out of the byte-offset title case by @wenshao in #16756
  • perf(memory): drop the bundled auto-memory reference and keep the resident policy by @qqqys in #16739
  • perf(github): poll with conditional requests so unchanged data costs no quota by @wenshao in #16741
  • feat(serve): add PR-watch host discovery and ordered shutdown by @wenshao in #16732
  • fix(web-templates): lift the export renderer budget to the merged size by @yiliang114 in #16774
  • feat(cli): send OpenTUI's model rounds through the shared agent loop by @qqqys in #16743
  • feat(mods): run model completions from Mods by @qqqys in #16737
  • feat(managed-agent): add private BTW and session recap by @doudouOUC in #16758
  • fix(cli): let idle-only slash commands run from an idle session by @qqqys in #16731
  • feat(core): Goal verifier verdict inherits the session output language by @4ekuct25 in #15806
  • fix(web-shell): prioritize slash menu names by @callmeYe in #16790
  • refactor(cli): single-source the Managed Runtime worker route surface by @doudouOUC in #16788
  • docs(managed-agent): design Managed /loop support (schedules and wakeups) by @wenshao in #16792
  • fix(cli): notify when a background agent or workflow parks an approval by @qqqys in #16800
  • feat(mods): let Mods rewrite reply rows in the Ink terminal by @qqqys in #16794
  • feat(ci): raise the self-hosted autofix agent budget to 240 minutes by @wenshao in #16777
  • fix(cli): defer unlisted subscription model errors to send by @liuxuely0626 in #16798
  • feat(web-shell): configure the Email channel from the channel manager by @wenshao in #16746
  • feat(cli): run OpenTUI's tool batches on the shared agent loop by @qqqys in #16789
  • fix(core): write auto session titles in the conversation's language by @qqqys in #16806
  • feat(mods): keep each plugin's values between sessions with $.store by @qqqys in #16791
  • fix(cli): show a foreground agent's pending approval in the live panel by @qqqys in #16809
  • fix(cli): only enable sandbox debugging for explicit DEBUG values by @yiliang114 in #16805
  • fix(deps)!: upgrade dependencies shipped by SDK and Web Shell by @yiliang114 in #16452
  • docs(managed-agent): Managed scheduling designs — loop review fixes and external schedulers by @wenshao in #16796
  • fix(core): attribute gh pr create in the directory the command runs in by @wenshao in #16725
  • chore(managed-agent): remove unused constructors and helpers by @doudouOUC in #16822
  • fix(core): keep reacquireWriter from acquiring behind a seal by @wenshao in #16726
  • perf(managed-agent): cheapen proof copies, CSI lookup and startup polling by @doudouOUC in #16828
  • refactor(serve): extract the session restore core for in-process callers by @wenshao in #16810
  • feat(web-shell): let managed sessions reuse the host shell by @yiliang114 in #16324
  • feat(managed-agent): keep the channel delivery ledger segment-faithful by @wenshao in #16797
  • feat(channels): gate review/verify bound delivery on active watches by @wenshao in #16772
  • feat(web-shell): configure the WeChat channel with in-browser QR login by @wenshao in #16736
  • fix(core): reject recycled PIDs in runtime session status by @yiliang114 in #16128
  • docs(design): correct the wakeDormant delivery claim to a latency gap by @wenshao in #16834
  • perf(managed-agent): remove redundant read-path queries by @doudouOUC in #16827
  • feat(channels): add a QR-login management contract and the QQ config surface by @wenshao in #16724
  • feat(managed-agent): expose channel delivery segments in the public read model by @wenshao in #16807
  • feat(web-shell): show session speed and cache hit under the composer by @qqqys in #16815
  • fix(channels): let a config field declare an inclusive lower bound by @wenshao in #16783

New Contributors

Full Changelog: v0.27.1...v0.27.2-preview.0

Don't miss a new qwen-code release

NewReleases is sending notifications on new releases.