wenshao d510a77a28 fix(review): promote most-violated rules to top of prompt ... Two rules repeatedly violated by LLMs despite being documented: 1. Language matching (Chinese output on English PRs) 2. Create Review API (falling back to individual gh api comments) Moved both to a "Critical rules" section at the very top of the prompt, before the design philosophy. Early placement = higher attention from the LLM. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>		2026-04-09 09:27:27 +08:00
..
channels	fix(release): run release:version 0.14.2 to sync all package versions (#3026)	2026-04-08 21:33:40 +08:00
cli	Merge remote-tracking branch 'origin/main' into feat/review-skill-improvements	2026-04-09 08:52:01 +08:00
core	fix(review): promote most-violated rules to top of prompt	2026-04-09 09:27:27 +08:00
sdk-java	feat: simplify subagent model configuration with model selector	2026-03-27 11:49:45 +08:00
sdk-typescript	Merge pull request #2698 from QwenLM/refactor/subagent-model-selection	2026-04-01 16:17:54 +08:00
test-utils	fix(release): run release:version 0.14.2 to sync all package versions (#3026)	2026-04-08 21:33:40 +08:00
vscode-ide-companion	Merge pull request #2954 from QwenLM/fix/disable-followup-suggestions-default	2026-04-08 18:02:00 +08:00
web-templates	fix(release): run release:version 0.14.2 to sync all package versions (#3026)	2026-04-08 21:33:40 +08:00
webui	fix(followup): prevent tool call UI leak and Enter accept buffer race (#2872)	2026-04-09 00:07:03 +08:00
zed-extension	chore(zed-extension): update package version to 0.10.0	2026-02-06 14:26:01 +08:00