ai-agent-plugin

# AI Agent

[![CI](https://github.com/jenkinsci/ai-agent-plugin/actions/workflows/ci.yml/badge.svg)](https://github.com/jenkinsci/ai-agent-plugin/actions/workflows/ci.yml)
[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
[![Jenkins Plugin](https://img.shields.io/badge/Jenkins-2.528.3+-blue.svg)](https://www.jenkins.io/)

A Jenkins plugin that adds a reusable **Run AI Agent** build step for running autonomous coding
agents (Claude Code, Codex CLI, Cursor Agent, OpenCode, Cursor CLI) in Jenkins jobs and pipelines.

Plugin ID (artifactId): `ai-agent`

## Features

- **Reusable build step** — add `Run AI Agent` to Freestyle jobs or Pipeline via `aiAgent(...)`.
- **Multiple agent support** — Claude Code, Codex CLI, Cursor Agent, OpenCode, and Cursor CLI.
- **Inline conversation view** — live-streaming conversation on the build page with structured display of assistant messages, tool calls with inputs/outputs, and thinking blocks. Multiple invocations in the same build are shown as separate cards (latest expanded, older collapsible).
- **Markdown rendering** — assistant and result messages are rendered as formatted HTML.
- **Approval gates** — optionally pause builds for human review before tool execution.
- **Usage statistics** — token counts, cost, and duration extracted from agent logs and displayed per build.
- **Codex per-job config** — optionally provide a job-scoped `~/.codex/config.toml` to override settings/MCP for Codex runs.
- **Standard Jenkins integrations** — SCM checkout, build triggers, credentials injection, post-build shell steps, and publishers.

## Supported Agents

| Agent | Output Format | Cost Tracking |
|-------|--------------|---------------|
| [Claude Code](https://docs.anthropic.com/en/docs/claude-code) | stream-json | Full (tokens + cost) |
| [Codex CLI](https://github.com/openai/codex) | JSON | Tokens only |
| [Cursor Agent](https://www.cursor.com/) | stream-json | Tokens only |
| [OpenC