roast-ai 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: d4f229785a3a00ff70e98323c5edc14f0722c113993de498136054eb7716b7aa
+  data.tar.gz: 5ec6dbc6d4d44d7cda7d451d0226b7eb7730942193d452fdd41c67c222d0c952
+SHA512:
+  metadata.gz: cd9c770a184b0a93b16ddccec14100eb922d0432c15513497c0dccab9223b473054198c2af5b169d251b9fcb72aad3665c0339799ad72aa7054eeb03a3a1acec
+  data.tar.gz: 3414b3447e3636b80f224d5560b90981acfc018ab702ad0c4a152bfe203db79d070263d4a34ecca787a21a651f0ecc6715ed4ac3eef961f2fb825b56ebb3ae70

data/.claude/settings.json

@@ -0,0 +1,12 @@
+{
+    "permissions": {
+      "allow": [
+        "Bash(bundle:*)",
+        "FileRead(*)",
+        "LS",
+        "Grep",
+        "Glob",
+        "Agent"
+      ]
+    }
+  }

data/.github/workflows/ci.yaml

@@ -0,0 +1,29 @@
+name: ci
+
+on:
+  pull_request:
+    branches:
+      - main
+  push:
+    branches:
+      - main
+  schedule:
+    - cron:  '45 4 * * *'
+
+jobs:
+  rubies:
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu]
+        ruby: ['3.4', 'ruby-head']
+    runs-on: ${{ matrix.os }}-latest
+    continue-on-error: ${{ matrix.ruby == 'ruby-head' }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ruby/setup-ruby@v1
+        with:
+          ruby-version: ${{ matrix.ruby }}
+          bundler-cache: true
+      - run: bundle exec rake
+

data/.github/workflows/cla.yml

@@ -0,0 +1,22 @@
+name: Contributor License Agreement (CLA)
+
+on:
+  pull_request_target:
+    types: [opened, synchronize]
+  issue_comment:
+    types: [created]
+
+jobs:
+  cla:
+    runs-on: ubuntu-latest
+    if: |
+      (github.event.issue.pull_request
+        && !github.event.issue.pull_request.merged_at
+        && contains(github.event.comment.body, 'signed')
+      )
+|| (github.event.pull_request && !github.event.pull_request.merged)
+    steps:
+      - uses: Shopify/shopify-cla-action@v1
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          cla-token: ${{ secrets.CLA_TOKEN }}

data/.gitignore

@@ -0,0 +1,13 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+.CLAUDE.local.md
+.rspec_status
+**/.claude/settings.local.json
+
+**/CLAUDE.local.md

data/.rspec

@@ -0,0 +1 @@
+--require spec_helper

data/.rubocop.yml

@@ -0,0 +1,12 @@
+inherit_gem:
+  rubocop-shopify: rubocop.yml
+
+AllCops:
+  CacheRootDirectory: tmp
+  Exclude:
+    - 'bin/*'
+    - 'spec/fixtures/**/*'
+    - 'test/fixtures/**/*'
+  SuggestExtensions: false
+  TargetRubyVersion: 3.4
+  UseCache: true

data/.ruby-version

@@ -0,0 +1 @@
+3.4.2

data/CLAUDE.md

@@ -0,0 +1,31 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## About the codebase
+- This is a Ruby gem called Roast. Its purpose is to run AI workflows defined in a YAML file.
+
+## Commands
+
+- Build: `bundle exec rake build`
+- Test all: `bundle exec rspec`
+- Run single test: `bundle exec rspec spec/path/to/test_file.rb`
+- Lint: `bundle exec rubocop -A`
+- Default (tests + lint): `bundle exec rake`
+
+## Tech stack
+- `cli-kit` and `cli-ui` for the CLI tool
+- Testing: Use Rspec, VCR for HTTP mocking, test files named with `_spec.rb` suffix
+
+## Code Style Guidelines
+
+- Naming: snake_case for variables/methods, CamelCase for classes/modules, ALL_CAPS for constants
+- Module structure: Use nested modules under the `Roast` namespace
+- Command pattern: Commands implement a `call` method and class-level `help` method
+- Error handling: Use custom exception classes and structured error handling
+- Errors that should stop the program execution should `raise(CLI::Kit::Abort, "Error message")`
+- Documentation: Include method/class documentation with examples when appropriate
+- Dependencies: Prefer existing gems in the Gemfile before adding new ones
+- Define class methods inside `class << self; end` declarations.
+- Add runtime dependencies to `roast.gemspec`.
+- Add development dependencies to `Gemfile`.

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,133 @@
+
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual
+identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the overall
+  community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or advances of
+  any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email address,
+  without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official email address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+opensource@shopify.com.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of
+actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or permanent
+ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior, harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the
+community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.1, available at
+[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
+
+Community Impact Guidelines were inspired by
+[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
+
+For answers to common questions about this code of conduct, see the FAQ at
+[https://www.contributor-covenant.org/faq][FAQ]. Translations are available at
+[https://www.contributor-covenant.org/translations][translations].
+
+[homepage]: https://www.contributor-covenant.org
+[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
+[Mozilla CoC]: https://github.com/mozilla/diversity
+[FAQ]: https://www.contributor-covenant.org/faq
+[translations]: https://www.contributor-covenant.org/translations

data/CONTRIBUTING.md

@@ -0,0 +1,35 @@
+# How to contribute
+
+## Things we will merge
+
+* Bugfixes
+* Performance improvements
+* Features that are likely to be useful to the majority of Roast users
+* Documentation updates that are concise and likely to be useful to the majority of Roast users
+
+## Things we won't merge
+
+* Code that introduces considerable performance degrations
+* Code that touches performance-critical parts of Roast and comes without benchmarks
+* Features that are not important for most people (we want to keep the core Roast code small and tidy)
+* Features that can easily be implemented on top of Roast
+* Code that does not include tests
+* Code that breaks existing tests
+* Documentation changes that are verbose, incorrect or not important to most people (we want to keep it simple and easy to understand)
+
+## Workflow
+
+* [Sign the CLA](https://cla.shopify.com/) if you haven't already
+* Fork the Roast repository
+* Create a new branch in your fork
+  * For updating [Roast documentation](https://shopify.github.io/roast/), create it from `gh-pages` branch. (You can skip tests.)
+* If it makes sense, add tests for your code and/or run a performance benchmark
+* Make sure all tests pass (`bundle exec rake`)
+* Create a pull request
+
+## Releasing
+
+* Bump the version in `lib/roast/version.rb`
+* Update the `CHANGELOG.md` file
+* Open a PR like and merge it to `main`
+* Create a new release using the [GitHub UI](https://github.com/Shopify/roast/releases/new)

data/Gemfile

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in roast.gemspec
+gemspec
+
+gem "dotenv"
+gem "guard-rspec"
+gem "guard"
+gem "mocha"
+gem "pry"
+gem "rake", require: false
+gem "rspec", require: false
+gem "rubocop-shopify", require: false
+gem "vcr", require: false
+gem "webmock", require: false

data/Gemfile.lock

@@ -0,0 +1,194 @@
+PATH
+  remote: .
+  specs:
+    roast-ai (0.1.0)
+      activesupport (~> 8.0)
+      faraday-retry
+      json-schema
+      raix (= 0.8.3)
+      thor (~> 1.3)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    activesupport (8.0.2)
+      base64
+      benchmark (>= 0.3)
+      bigdecimal
+      concurrent-ruby (~> 1.0, >= 1.3.1)
+      connection_pool (>= 2.2.5)
+      drb
+      i18n (>= 1.6, < 2)
+      logger (>= 1.4.2)
+      minitest (>= 5.1)
+      securerandom (>= 0.3)
+      tzinfo (~> 2.0, >= 2.0.5)
+      uri (>= 0.13.1)
+    addressable (2.8.7)
+      public_suffix (>= 2.0.2, < 7.0)
+    ast (2.4.3)
+    base64 (0.2.0)
+    benchmark (0.4.0)
+    bigdecimal (3.1.9)
+    coderay (1.1.3)
+    concurrent-ruby (1.3.5)
+    connection_pool (2.5.1)
+    crack (1.0.0)
+      bigdecimal
+      rexml
+    diff-lcs (1.6.1)
+    dotenv (3.1.8)
+    drb (2.2.1)
+    event_stream_parser (1.0.0)
+    faraday (2.13.0)
+      faraday-net_http (>= 2.0, < 3.5)
+      json
+      logger
+    faraday-multipart (1.1.0)
+      multipart-post (~> 2.0)
+    faraday-net_http (3.4.0)
+      net-http (>= 0.5.0)
+    faraday-retry (2.3.1)
+      faraday (~> 2.0)
+    ffi (1.17.2)
+    ffi (1.17.2-arm64-darwin)
+    formatador (1.1.0)
+    guard (2.19.1)
+      formatador (>= 0.2.4)
+      listen (>= 2.7, < 4.0)
+      logger (~> 1.6)
+      lumberjack (>= 1.0.12, < 2.0)
+      nenv (~> 0.1)
+      notiffany (~> 0.0)
+      ostruct (~> 0.6)
+      pry (>= 0.13.0)
+      shellany (~> 0.0)
+      thor (>= 0.18.1)
+    guard-compat (1.2.1)
+    guard-rspec (4.7.3)
+      guard (~> 2.1)
+      guard-compat (~> 1.1)
+      rspec (>= 2.99.0, < 4.0)
+    hashdiff (1.1.2)
+    i18n (1.14.7)
+      concurrent-ruby (~> 1.0)
+    json (2.10.2)
+    json-schema (5.1.1)
+      addressable (~> 2.8)
+      bigdecimal (~> 3.1)
+    language_server-protocol (3.17.0.4)
+    lint_roller (1.1.0)
+    listen (3.9.0)
+      rb-fsevent (~> 0.10, >= 0.10.3)
+      rb-inotify (~> 0.9, >= 0.9.10)
+    logger (1.7.0)
+    lumberjack (1.2.10)
+    method_source (1.1.0)
+    minitest (5.25.5)
+    mocha (2.7.1)
+      ruby2_keywords (>= 0.0.5)
+    multipart-post (2.4.1)
+    nenv (0.3.0)
+    net-http (0.6.0)
+      uri
+    notiffany (0.1.3)
+      nenv (~> 0.1)
+      shellany (~> 0.0)
+    open_router (0.3.3)
+      activesupport (>= 6.0)
+      dotenv (>= 2)
+      faraday (>= 1)
+      faraday-multipart (>= 1)
+    ostruct (0.6.1)
+    parallel (1.27.0)
+    parser (3.3.8.0)
+      ast (~> 2.4.1)
+      racc
+    prism (1.4.0)
+    pry (0.15.2)
+      coderay (~> 1.1)
+      method_source (~> 1.0)
+    public_suffix (6.0.1)
+    racc (1.8.1)
+    rainbow (3.1.1)
+    raix (0.8.3)
+      activesupport (>= 6.0)
+      faraday-retry (~> 2.0)
+      open_router (~> 0.2)
+      ruby-openai (~> 7)
+    rake (13.2.1)
+    rb-fsevent (0.11.2)
+    rb-inotify (0.11.1)
+      ffi (~> 1.0)
+    regexp_parser (2.10.0)
+    rexml (3.4.1)
+    rspec (3.13.0)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.3)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.3)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.2)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.2)
+    rubocop (1.75.3)
+      json (~> 2.3)
+      language_server-protocol (~> 3.17.0.2)
+      lint_roller (~> 1.1.0)
+      parallel (~> 1.10)
+      parser (>= 3.3.0.2)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 2.9.3, < 3.0)
+      rubocop-ast (>= 1.44.0, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 2.4.0, < 4.0)
+    rubocop-ast (1.44.1)
+      parser (>= 3.3.7.2)
+      prism (~> 1.4)
+    rubocop-shopify (2.17.0)
+      rubocop (~> 1.62)
+    ruby-openai (7.4.0)
+      event_stream_parser (>= 0.3.0, < 2.0.0)
+      faraday (>= 1)
+      faraday-multipart (>= 1)
+    ruby-progressbar (1.13.0)
+    ruby2_keywords (0.0.5)
+    securerandom (0.4.1)
+    shellany (0.0.1)
+    thor (1.3.2)
+    tzinfo (2.0.6)
+      concurrent-ruby (~> 1.0)
+    unicode-display_width (3.1.4)
+      unicode-emoji (~> 4.0, >= 4.0.4)
+    unicode-emoji (4.0.4)
+    uri (1.0.3)
+    vcr (6.3.1)
+      base64
+    webmock (3.25.1)
+      addressable (>= 2.8.0)
+      crack (>= 0.3.2)
+      hashdiff (>= 0.4.0, < 2.0.0)
+
+PLATFORMS
+  arm64-darwin-23
+  ruby
+
+DEPENDENCIES
+  dotenv
+  guard
+  guard-rspec
+  mocha
+  pry
+  rake
+  roast-ai!
+  rspec
+  rubocop-shopify
+  vcr
+  webmock
+
+BUNDLED WITH
+   2.6.8

data/LICENSE.md

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025-present Shopify Inc.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

data/README.md

@@ -0,0 +1,27 @@
+![image](https://github.com/user-attachments/assets/39589441-d15a-452b-b51c-3bf28f470308)
+
+# Roast
+
+A convention-oriented framework for creating structured AI workflows, maintained by the Augmented Engineering team at Shopify.
+
+## Why you should use Roast
+TBD
+
+## What does it look like?
+TBD
+
+## How to use Roast
+TBD
+
+## Installation
+```
+$ gem install roast
+```
+
+## Development
+
+After checking out the repo, run `bundle install` to install dependencies. Then, run `bundle exec rake` to run the tests and linter. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

data/Rakefile

@@ -0,0 +1,24 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+require "rubocop/rake_task"
+require "rake/testtask"
+
+RSpec::Core::RakeTask.new(:spec) do |t|
+  t.pattern = "spec/**/*_spec.rb"
+end
+
+Rake::TestTask.new(:minitest) do |t|
+  t.libs << "test"
+  t.libs << "lib"
+  t.test_files = FileList["test/**/*_test.rb"]
+end
+
+task test: [:spec, :minitest]
+
+RuboCop::RakeTask.new do |task|
+  task.options = ["--autocorrect"]
+end
+
+task default: [:test, :rubocop]

data/bin/console

@@ -0,0 +1,11 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+
+# Add the lib directory to the load path
+$LOAD_PATH.unshift(File.expand_path("../lib", __dir__))
+
+require "roast"
+
+require "irb"
+IRB.start(__FILE__)

data/examples/grading/analyze_coverage/prompt.md

@@ -0,0 +1,52 @@
+<coverage_results>
+<%= workflow.output["run_coverage"] %>
+</coverage_results>
+
+Analyze the results and score them on a scale of 1-10 using the following rubrics:
+
+<line_coverage>
+0-1: Critical failure (0-20% coverage) - Core functionality remains completely untested
+2-3: Poor coverage (21-40%) - Major gaps; many key functions lack any testing
+4-5: Inadequate coverage (41-60%) - Several important code paths are not executed
+6-7: Moderate coverage (61-80%) - Notable gaps remain; some important functionality lacks coverage
+8-9: Good coverage (81-95%) - Only minor or edge case code paths remain untested
+10: Excellent coverage (96-100%)
+</line_coverage>
+
+<branch_coverage>
+0-1: Critical failure (0-20% branch coverage) - Almost no conditional branches are tested
+2-3: Poor coverage (21-40%) - Most conditional logic remains untested
+4-5: Inadequate coverage (41-60%) - Many conditions are only tested for one outcome
+6-7: Moderate coverage (61-80%) - Some conditions lack testing for all outcomes
+8-9: Good coverage (81-95%) - Most conditions are tested for most outcomes
+10: Excellent coverage (96-100%)
+</branch_coverage>
+
+<method_coverage>
+0-1: Critical failure (0-20% method coverage) - Most or core functionality methods are untested
+2-3: Poor coverage (21-40%) - Several public API methods remain untested
+4-5: Inadequate coverage (41-60%) - Some important public methods lack tests
+6-7: Moderate coverage (61-80%) - Notable gaps remain; some public methods may lack comprehensive testing
+8-9: Good coverage (81-95%) - Nearly all public methods are tested; private methods are mostly covered via public method tests
+10: Excellent coverage (96-100%)
+</method_coverage>
+
+RESPONSE FORMAT
+You must respond in JSON format within <json> XML tags. Example:
+
+<json>
+{
+  "method_coverage": {
+    "score": "10",
+    "justification": "The source file has 100% method coverage, indicating all methods are being tested."
+  },
+  "line_coverage": {
+    "score": 10,
+    "justification": "The source file has 100% line coverage, indicating all executable lines are tested."
+  },
+  "branch_coverage": {
+    "score": 8,
+    "justification": "The source file has 80% branch coverage, indicating some branches need testing."
+  }
+}
+</json>