What's Changed
- feat(skills): add bundled /review skill for out-of-the-box code review by @wenshao in #2348
- fix(insight): handle individual LLM failures in qualitative insights (#2341) by @netbrah in #2361
- fix(core): add deepseek-r1 to output token limit patterns by @netbrah in #2362
- chore(release): bump version to 0.12.4 by @qwen-code-ci-bot in #2393
- fix(i18n): localize slash command descriptions by @chen893 in #2333
- fix(core): guard against empty choices in convertOpenAIResponseToGemini by @netbrah in #2364
- feat(skills): add docs audit and update helpers by @DragonnZhang in #2397
- Docs/subagent system prompt limits by @hs-ye in #2001
- fix(extension): disable symlinks on Windows during git clone to fix install failure by @LaZzyMan in #2286
- fix(core): reject PDF files to prevent session corruption (fixes #2020) by @drewd789 in #2024
- Keep rejected plan content visible in plan mode by @DragonnZhang in #2157
- fix(cli): allow /dev/ptmx and /dev/ttys* in macOS permissive sandbox by @kkhomej33-netizen in #2391
- fix: correct hooks JSON schema type definition by @xuewenjie123 in #2280
- fix(core): strip orphaned user entries before retry to prevent API errors by @tanzhenxin in #2367
- fix(core): correctly capture rapid pty outputs in interactive shell mode by @tanzhenxin in #2389
- fix(vscode): prevent race conditions in prompt cancellation and streaming by @tanzhenxin in #2374
- fix(core): improve shell tool truncation, simplify tool output handling, and remove summarization by @tanzhenxin in #2388
- fix:remove redundant plan files by @LaZzyMan in #2407
- chore(CODEOWNERS): remove required reviewers for vscode-ide-companion and webui packages by @yiliang114 in #2408
- fix(core): normalize Windows PATH-like env keys for shell execution by @Sakuranda in #1904
- docs: explain Docker sandbox runtime and Java usage by @kiri-chenchen in #1642
- docs(integration): add ACP Registry for Zed and JetBrains integration docs by @ShihaoShenDev in #2372
- Increase DEFAULT_OUTPUT_TOKEN_LIMIT from 8K to 16K by @Mingholy in #2411
- fix: auto-detect max_tokens from model when not set by provider by @netbrah in #2356
New Contributors
- @netbrah made their first contribution in #2361
- @chen893 made their first contribution in #2333
- @hs-ye made their first contribution in #2001
- @drewd789 made their first contribution in #2024
- @Sakuranda made their first contribution in #1904
- @kiri-chenchen made their first contribution in #1642
- @ShihaoShenDev made their first contribution in #2372
Full Changelog: v0.12.3...v0.12.4