JohnXu22786/ci-runner0

dsh-ci-runner

Trigger GitHub Actions workflow runs and local test pipelines, stream their logs back, and on failure hand the tail of the log to DeepSeek for a Markdown root-cause diagnosis.

AI 分析

核心用途是让 Agent 能够触发 CI 流程、监控状态,并在失败时自动提取日志交由 DeepSeek 进行根因分析。适合需要自动化运维、持续集成的开发场景。

パッケージ
dsh-ci-runner
バージョン
0.1.0
ライセンス
MIT
最終更新
2026/08/23

インストール

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:JohnXu22786/ci-runner

ドキュメント

README 全文を読む ↗

Configuration

FieldDefaultMeaning
github.tokenEnvGITHUB_TOKENEnv var holding the GitHub token (read at call time, never logged)
github.defaultRepo''Default owner/repo for GitHub calls
github.defaultBranchmainRef used when a trigger doesn't specify one
github.apiBasehttps://api.github.comREST base (GitHub Enterprise override)
github.pollIntervalMs5000Poll interval for status tracking
github.pollTimeoutMs600000Hard cap for waiting on a run
github.dispatchWindowMs20000How long a dispatch may take to surface a run id
github.requestTimeoutMs30000Per-request HTTP timeout
github.readLogChars30000Default tail cap for ci_logs
local.cwd.Working directory for command runs
local.timeoutMs120000Hard timeout per command
local.maxOutputChars40000Per-stream output cap
local.templates[{name: 'npm test', command: 'npm test'}, {name: 'pytest', command: 'pytest'}]Named command templates
diagnosis.llmnullOpenAI-compatible endpoint override {baseUrl, apiKey, model}
diagnosis.provider''ctx.llm provider route ('' = auto)
diagnosis.model''ctx.llm model ('' = auto)
diagnosis.maxTailChars12000Chars of the log tail sent to the model
diagnosis.timeoutMs120000Hard budget for the analysis call
diagnosis.temperature0.2Sampling temperature
diagnosis.providerLabelOpenAI-compatibleLabel recorded in reports when the endpoint override is used

Templates let the model and the CLI reference pipelines by name (ci_trigger {source: local, command: 'npm test'}). Any value that doesn't match a template name is treated as a raw shell command line.