ci: release packages

[github-actions]

This PR was opened by the Changesets release GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically. If you're not ready to do a release yet, that's fine, whenever you add more changesets to main, this PR will be updated.

Releases

@moonshot-ai/kimi-code@0.11.0

Minor Changes

• #468 df4f2d6 - Add experimental sub-skill discovery gated by the KIMI_CODE_EXPERIMENTAL_SUB_SKILL environment variable. Ships the sub-skill builtin bundle (sub-skill.review, sub-skill.consolidate) for inventorying and consolidating skills into hierarchical groups.

• #480 f555c89 - Show built-in skills as direct slash commands and group them ahead of external skill commands.

• #458 93eb70a - Migrate still-relevant environment variables from kimi-cli:

  • KIMI_MODEL_TEMPERATURE, KIMI_MODEL_TOP_P — sampling parameters applied globally to any kimi provider (not tied to KIMI_MODEL_NAME).
  • KIMI_MODEL_THINKING_KEEP — Moonshot preserved-thinking passthrough (thinking.keep), injected only while Thinking is on.
  • KIMI_CODE_NO_AUTO_UPDATE (legacy alias KIMI_CLI_NO_AUTO_UPDATE) — fully disables the update preflight (no check, background install, or prompt).

• #470 aa610e2 - Use a fixed 30-minute timeout for subagents and show concise resume instructions when they time out.

Patch Changes

• #474 658e465 - Show the upcoming-goal confirmation with the same accent treatment as goal lifecycle messages.

• #474 658e465 - Fix slash command autocomplete so goal text can be submitted when the cursor is before existing text.

• #474 658e465 - Fix queued goals so failed promotion attempts do not lose or duplicate queued work.

• #456 3a98713 - Show concise provider filtering errors when responses are blocked before visible output.

• #442 960a0e2 - Show "unknown command" instead of "too many arguments" when an invalid subcommand is entered.

• #474 658e465 - Fix upcoming-goal queue handling while editing or pasting queued goals.

• #457 1fe5d55 - Clamp OpenAI Chat Completions xhigh and max thinking effort to high unless the model supports xhigh on v1/chat/completions.

• #464 4f9977d - Preserve thinking effort when compacting long conversations.

• #474 658e465 - Ask before starting goals in YOLO mode so users can switch to Auto for unattended work.

• #461 2af19e2 - Refresh provider model metadata when capabilities change without model ID changes.

• #474 658e465 - Start upcoming goals immediately when there is no active goal to wait for.
  Support multiline edits when managing upcoming goals.

• #474 658e465 - Highlight goal queue subcommands while typing slash commands.

@moonshot-ai/agent-core@0.10.0

Minor Changes

• #468 df4f2d6 - Add experimental sub-skill discovery gated by the KIMI_CODE_EXPERIMENTAL_SUB_SKILL environment variable. Ships the sub-skill builtin bundle (sub-skill.review, sub-skill.consolidate) for inventorying and consolidating skills into hierarchical groups.

• #458 93eb70a - Migrate still-relevant environment variables from kimi-cli:

  • KIMI_MODEL_TEMPERATURE, KIMI_MODEL_TOP_P — sampling parameters applied globally to any kimi provider (not tied to KIMI_MODEL_NAME).
  • KIMI_MODEL_THINKING_KEEP — Moonshot preserved-thinking passthrough (thinking.keep), injected only while Thinking is on.
  • KIMI_CODE_NO_AUTO_UPDATE (legacy alias KIMI_CLI_NO_AUTO_UPDATE) — fully disables the update preflight (no check, background install, or prompt).

• #470 aa610e2 - Use a fixed 30-minute timeout for subagents and show concise resume instructions when they time out.

Patch Changes

• #456 3a98713 - Show concise provider filtering errors when responses are blocked before visible output.

• #464 4f9977d - Preserve thinking effort when compacting long conversations.

• Updated dependencies [3a98713, 93eb70a]:

  • @moonshot-ai/kosong@0.3.4

@moonshot-ai/acp-adapter@0.2.2

Patch Changes

• Updated dependencies [df4f2d6, 3a98713, 93eb70a, 4f9977d, aa610e2]:
  • @moonshot-ai/agent-core@0.10.0
  • @moonshot-ai/kimi-code-sdk@0.8.0

@moonshot-ai/kosong@0.3.4

Patch Changes

• #456 3a98713 - Show concise provider filtering errors when responses are blocked before visible output.

• #458 93eb70a - Migrate still-relevant environment variables from kimi-cli:

  • KIMI_MODEL_TEMPERATURE, KIMI_MODEL_TOP_P — sampling parameters applied globally to any kimi provider (not tied to KIMI_MODEL_NAME).
  • KIMI_MODEL_THINKING_KEEP — Moonshot preserved-thinking passthrough (thinking.keep), injected only while Thinking is on.
  • KIMI_CODE_NO_AUTO_UPDATE (legacy alias KIMI_CLI_NO_AUTO_UPDATE) — fully disables the update preflight (no check, background install, or prompt).

@moonshot-ai/migration-legacy@0.1.10

Patch Changes

• Updated dependencies [df4f2d6, 3a98713, 93eb70a, 4f9977d, aa610e2]:
  • @moonshot-ai/agent-core@0.10.0

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: e231ecf836

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[chatgpt-codex-connector]

Sync release notes before publishing 0.10.2

When this release PR is merged, the release workflow publishes the package and then immediately deploys docs (.github/workflows/release.yml lines 74-78), but this commit only updates the package changelog; docs/en/release-notes/changelog.md and docs/zh/release-notes/changelog.md still stop at 0.10.0. Because the CLI's update prompt links users to that docs changelog, the 0.10.2 release would ship with stale public release notes despite docs/AGENTS.md documenting that the docs changelog is synced from the CLI changelog after each release.

Useful? React with 👍 / 👎.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 3c19043ced

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[chatgpt-codex-connector]

Bump the SDK for bundled core changes

For releases that include this agent-core behavior, the SDK needs a version bump too: packages/node-sdk/tsdown.config.ts aliases and always-bundles @moonshot-ai/agent-core, and SDKRpcClient constructs KimiCore from that bundled core (packages/node-sdk/src/sdk-rpc-client.ts lines 62-72). Since this PR leaves packages/node-sdk/package.json and its changelog at 0.8.0, publishing this release will not produce a new SDK artifact, so SDK consumers keep the old bundled core and miss the env-param, filtered-error, and compaction fixes. Please add a SDK changeset/version bump for these SDK-visible core changes.

Useful? React with 👍 / 👎.