chore(changesets): simplify pending CLI changelog entries (#2823)

This commit is contained in:
liruifengv 2026-08-11 21:37:00 +08:00 committed by GitHub
parent ad12ad8a14
commit 911d41b0f6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 5 additions and 5 deletions

View file

@ -3,4 +3,4 @@
"@moonshot-ai/kimi-code-sdk": patch
---
Detect MCP servers that require OAuth by reusing the existing connection-time authorization check.
Detect MCP servers that require OAuth without needing `auth: "oauth"` in the config.

View file

@ -2,4 +2,4 @@
"@moonshot-ai/kimi-code": patch
---
Fix the token counts reported after compaction reading far below the real context size: the before/after stats and the context gauge now include the system prompt and tool definitions, matching the numbers shown while the session runs.
Fix the token counts reported after compaction reading far below the real context size; they now match the numbers shown while the session runs.

View file

@ -2,4 +2,4 @@
"@moonshot-ai/kimi-code": patch
---
Fix multi-second typing and rendering freezes at startup or while idle when a large search index loads, replays, or rebuilds.
Fix multi-second freezes at startup or while idle when a large search index loads, replays, or rebuilds.

View file

@ -2,4 +2,4 @@
"@moonshot-ai/kimi-code": patch
---
Prevent one session's subagent tool projection from changing builtin profiles in later sessions.
Fix subagent tool changes in one session leaking into builtin profiles in later sessions.

View file

@ -2,4 +2,4 @@
"@moonshot-ai/kimi-code": patch
---
Fix a Windows binary-planting risk: child processes spawned by bare command name before the workspace trust prompt (stty, fd detection, package-manager update installs) could resolve to a malicious executable placed in the current directory. These commands are now skipped on Windows, deferred until after the trust prompt, or resolved to an absolute PATH location with hits inside the current directory refused.
Fix a Windows security risk where commands launched before the workspace trust prompt could run a malicious executable placed in the current folder.