xuwenhao/Kimi Code Action

GitHub automation driven by the kimi-code CLI: PR reviews with inline comments, @kimi mentions, and custom workflows.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
trigger_phraseThe trigger phrase to look for in comments or issue bodyno@kimi
assignee_triggerThe assignee username that triggers the action (e.g. @kimi)no
label_triggerThe label that triggers the action (e.g. kimi)nokimi
base_branchThe branch to use as the base/source when creating new branches (defaults to repository default branch)no
branch_prefixThe prefix to use for kimi branches (defaults to 'kimi/', use 'kimi-' for dash format)nokimi/
branch_name_templateTemplate for branch naming. Available variables: {{prefix}}, {{entityType}}, {{entityNumber}}, {{timestamp}}, {{sha}}, {{label}}, {{description}}. {{label}} will be first label from the issue/PR, or {{entityType}} as a fallback. {{description}} will be the first 5 words of the issue/PR title in kebab-case. Default: '{{prefix}}{{entityType}}-{{entityNumber}}-{{timestamp}}'no""
allowed_botsComma-separated list of allowed bot usernames, or '*' to allow all bots. Empty string (default) allows no bots. WARNING: On public repos with '*', external Apps may be able to invoke this action with prompts they control. See docs/security.md.no""
include_comments_by_actorComma-separated list of actor usernames to INCLUDE in comments. Supports wildcards: '*[bot]' matches all bots, 'dependabot[bot]' matches specific bot. Empty (default) includes all actors.no""
exclude_comments_by_actorComma-separated list of actor usernames to EXCLUDE from comments. Supports wildcards: '*[bot]' matches all bots, 'renovate[bot]' matches specific bot. Empty (default) excludes none. If actor is in both lists, exclusion takes priority.no""
promptInstructions for the agent. Can be a direct prompt or custom template.no""
settingskimi config.toml fragment as a string, or path to a .toml file (appended to the generated config.toml)no""
kimi_api_keyKimi API keyno
kimi_modelModel name used to synthesize the kimi provider (KIMI_MODEL_NAME)nok3
kimi_platformWhich Kimi platform your API key belongs to: 'code' = Kimi Code Console subscription (api.kimi.com/coding, default), 'open-cn' = Open Platform CN (platform.moonshot.cn), 'open-intl' = Open Platform international (platform.kimi.com / moonshot.ai). Sets the provider base URL preset; open-* presets also require an Open Platform model id in kimi_model.nocode
kimi_base_urlBase URL for the kimi provider (KIMI_MODEL_BASE_URL). Empty (default) follows the kimi_platform preset; an explicit value overrides the preset.no""
kimi_versionkimi-code CLI version to install (npm dist-tag or version). Empty installs latest.no""
github_tokenGitHub token with repo and pull request permissionsno
kimi_argsAdditional arguments to pass directly to the kimi CLIno""
use_sticky_commentUse just one comment to deliver issue/PR commentsnofalse
classify_inline_commentsBuffer inline comments without confirmed=true and classify them (real review vs test/probe) before posting after the session ends. Set to 'false' to post all inline comments immediately (pre-buffering behavior).notrue
use_commit_signingEnable commit signing using GitHub's commit signature verification. When false, the agent uses standard git commandsnofalse
ssh_signing_keySSH private key for signing commits. When provided, git will be configured to use SSH signing. Takes precedence over use_commit_signing.no""
bot_idGitHub user ID to use for git operations (defaults to github-actions[bot]'s user ID)no41898282
bot_nameGitHub username to use for git operations (defaults to github-actions[bot])nogithub-actions[bot]
track_progressForce tag mode with tracking comments for pull_request and issue events. Only applicable to pull_request (opened, synchronize, ready_for_review, reopened) and issue (opened, edited, labeled, assigned) events.nofalse
path_to_kimi_executableOptional path to a custom kimi executable. If provided, skips automatic installation and uses this executable instead. WARNING: Using an older version may cause problems if the action begins taking advantage of new kimi features. This input is typically not needed unless you're debugging something specific or have unique needs in your environment.no""
path_to_bun_executableOptional path to a custom Bun executable. If provided, skips automatic Bun installation and uses this executable instead. WARNING: Using an incompatible version may cause problems if the action requires specific Bun features. This input is typically not needed unless you're debugging something specific or have unique needs in your environment.no""
display_reportWhether to display the Kimi Code Report in GitHub Step Summary. Set to 'false' to disable when using custom formatting solutions. WARNING: This outputs agent-authored content in the GitHub Step Summary. This should only be used in cases where the action is used solely with trusted input.nofalse
show_full_outputShow full JSON output from the agent run. WARNING: This outputs ALL messages including tool execution results which may contain secrets, API keys, or other sensitive information. These logs are publicly visible in GitHub Actions. Only enable for debugging in non-sensitive environments.nofalse
namedescription
execution_filePath to the agent execution output file
branch_nameThe branch created by the agent for this execution
github_tokenThe GitHub token used by the action
session_idThe kimi session ID that can be used with `kimi -r` to continue this conversation