Using Pi with GitHub Agentic Workflows

Pi is a provider-agnostic coding agent for repository analysis and code changes. GitHub Agentic Workflows runs Pi through GitHub Actions from a Markdown workflow and adds GitHub triggers, sandbox controls, and safe outputs for event-driven, reviewable automation.

Pi requires tools.github.mode: gh-proxy and tools.cli-proxy: true. The compiler rejects Pi workflows that omit either requirement.

Selecting Pi + GitHub as the AI engine

To select Pi as the AI engine, with inference hosted and billed through a GitHub Copilot subscription, use a copilot/ model. A model without a provider prefix also uses the Copilot backend.

engine:
  id: pi
  model: copilot/gpt-5.4

To authenticate:

For organization-billed usage, grant copilot-requests: write.
Otherwise, provide a COPILOT_GITHUB_TOKEN secret containing a fine-grained PAT with Copilot Requests access.

Selecting Pi + Anthropic as the AI engine

To run Pi with inference hosted and billed through Anthropic, use an anthropic/ model:

engine:
  id: pi
  model: anthropic/claude-sonnet-4.6

To authenticate, provide ANTHROPIC_API_KEY as a GitHub Actions repository secret.

Selecting Pi + OpenAI as the AI engine

To run Pi with inference hosted and billed through OpenAI, use an openai/ or codex/ model:

engine:
  id: pi
  model: openai/gpt-5.4

To authenticate, provide a CODEX_API_KEY or OPENAI_API_KEY as a GitHub Actions repository secret.

For any provider, recompile the workflow with gh aw compile and commit the changes to the repository.

Example: scheduled repository report

---
on:
  schedule: daily

permissions:
  contents: read
  issues: read
  pull-requests: read
  copilot-requests: write

engine:
  id: pi
  model: copilot/gpt-5.4

tools:
  cli-proxy: true
  github:
    mode: gh-proxy
    toolsets: [default]

safe-outputs:
  create-issue:
    title-prefix: "[status] "
    labels: [report]
    close-older-issues: true
---

# Daily Repository Status

Analyze the repository and create a concise daily status report covering:
- Open issues and their priority
- Recent PR activity
- Upcoming work items

Capabilities and limitations

Pi supports top-level max-turns, provider-prefixed models, and engine.extensions. Pi already runs in bare mode, so engine.bare: true is accepted but has no effect. Pi does not provide native MCP server integration, native tools.web-search, per-command bash allowlisting, max-continuations, native engine.agent selection, or custom engine.harness scripts. MCP-backed tools must be exposed through the required CLI proxy.

See the AI engine feature comparison and Pi extensions reference.

GitHub Agentic Workflows vs. running Pi directly in Actions

Running coding agent CLIs such as Pi directly in GitHub Actions without an adequate security architecture is not recommended. GitHub Agentic Workflows provides sandboxing, credential isolation, scoped permissions, safe outputs, and workflow portability across AI engines.