Semantic Function Clustering¶

Analyze code for semantic function clustering and refactoring opportunities.

How it works¶

Scans source files (by language or custom glob) to find semantically related functions that live in different files, duplicate implementations of the same logic, and functions that belong in a different module. Files a report with specific refactoring recommendations.

Quick Install¶

mkdir -p .github/workflows && curl -sL \
  https://raw.githubusercontent.com/elastic/ai-github-actions/v0/gh-agent-workflows/semantic-function-clustering/example.yml \
  -o .github/workflows/semantic-function-clustering.yml

Trigger¶

Event	Schedule
`schedule`	Weekdays
`workflow_dispatch`	Manual

Inputs¶

Input	Description	Required	Default
`languages`	Comma-separated languages to analyze (ignored if `file-globs` is set)	No	`"go"`
`file-globs`	Comma-separated file globs to analyze (overrides `languages`)	No	`""`
`additional-instructions`	Repo-specific instructions appended to the agent prompt	No	`""`
`setup-commands`	Shell commands run before the agent starts	No	`""`
`allowed-bot-users`	Allowlisted bot actor usernames (comma-separated)	No	`github-actions[bot]`

Safe Outputs¶

create-issue — file a refactoring report (max 1, auto-closes older reports)

Example Workflow¶

name: Semantic Function Clustering
on:
  schedule:
    - cron: "0 12 * * 1-5"
  workflow_dispatch:

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

jobs:
  run:
    uses: elastic/ai-github-actions/.github/workflows/gh-aw-semantic-function-clustering.lock.yml@v0
    with:
      languages: "go,python,typescript"
    secrets:
      COPILOT_GITHUB_TOKEN: ${{ secrets.COPILOT_GITHUB_TOKEN }}