chore(deps): run upgrade automation with Kimi K3 - #2723
Conversation
Bugbot couldn't run - usage limit reachedBugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit. A user or team admin can review and increase usage limits in the Cursor dashboard. (requestId: serverGenReqId_34cb8d1a-fdae-4877-8c23-273fc01a5139) |
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
🚀 Deploying Preview to Cloudflare 🚀Preview URL: https://chore-upgrade-deps-kimi-k3-viteplus-dev.voidzero-docs.workers.dev (commit 6cf6491)This URL reflects your latest Preview deploymentPreview Deployments by commit
|
Bugbot couldn't run - usage limit reachedBugbot is counted against Cursor usage for this user or team, and this run hit a usage or spend limit. A user or team admin can review and increase usage limits in the Cursor dashboard. (requestId: serverGenReqId_ad27ba90-2e18-481e-91c8-dedf819c1b17) |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 4a6fcc95df
ℹ️ About Codex in GitHub
Your team has set up Codex to 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 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
|
K3 works #2725 |
2 participants
Summary
api.kimi.comk3[1m]for the primary, Opus, Fable, and sub-agent tierskimi-for-codingValidation
GET /coding/v1/modelsreturned all four Kimi Code model IDsk3,k3-256k,kimi-for-coding, andkimi-for-coding-highspeedactionlint .github/workflows/upgrade-deps.ymlgit diff --checkNote
Medium Risk
Changes only CI automation, but it alters how daily dependency-upgrade fixups and PR text are generated and depends on a new external API secret and model behavior.
Overview
The daily upgrade-deps workflow now runs its two Claude Code Action steps (dependency fixup and PR description enhancement) against Kimi’s Anthropic-compatible API instead of Anthropic directly.
Both steps bump claude-code-action from v1.0.221 to v1.0.226, switch auth from
claude_code_oauth_token/ANTHROPIC_API_KEYtoanthropic_api_key/MOONSHOT_API_KEY, and setANTHROPIC_BASE_URLtohttps://api.kimi.com/coding/. NewsettingsJSON maps default models tok3[1m]andkimi-for-coding, raises context limits to 1M tokens, and setsCLAUDE_CODE_EFFORT_LEVELto max.claude_argsnow pass--model "k3[1m]"instead ofopus.Setup: add a
MOONSHOT_API_KEYrepository secret before the workflow can run.Reviewed by Cursor Bugbot for commit 4a6fcc9. Bugbot is set up for automated code reviews on this repo. Configure here.