{"id":41603726,"url":"https://github.com/dielduarte/janusdoc-evals","last_synced_at":"2026-01-24T10:53:37.424Z","repository":{"id":330910951,"uuid":"1124398264","full_name":"dielduarte/janusdoc-evals","owner":"dielduarte","description":null,"archived":false,"fork":false,"pushed_at":"2025-12-29T02:41:24.000Z","size":194,"stargazers_count":0,"open_issues_count":8,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-12-31T19:12:57.762Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dielduarte.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/contributing.md","funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-12-29T00:31:55.000Z","updated_at":"2025-12-29T02:41:28.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/dielduarte/janusdoc-evals","commit_stats":null,"previous_names":["dielduarte/janusdoc-evals"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/dielduarte/janusdoc-evals","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dielduarte%2Fjanusdoc-evals","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dielduarte%2Fjanusdoc-evals/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dielduarte%2Fjanusdoc-evals/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dielduarte%2Fjanusdoc-evals/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dielduarte","download_url":"https://codeload.github.com/dielduarte/janusdoc-evals/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dielduarte%2Fjanusdoc-evals/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28725378,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-24T10:24:43.181Z","status":"ssl_error","status_checked_at":"2026-01-24T10:24:36.112Z","response_time":89,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-01-24T10:53:37.373Z","updated_at":"2026-01-24T10:53:37.418Z","avatar_url":"https://github.com/dielduarte.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# JanusDoc Evaluation Suite\n\nAutomated evaluation system for [JanusDoc](https://github.com/dielduarte/janusdoc) using [Evalite](https://www.evalite.dev/).\n\n## Overview\n\nThis repository contains 8 realistic test scenarios to measure JanusDoc's ability to suggest documentation updates based on code changes. Each scenario is a separate PR with specific code changes that should (or should not) trigger documentation suggestions.\n\n**Test Project:** TaskFlow - A simple TypeScript/Express task management API with 14 documentation files.\n\n## Running Evaluations\n\n```bash\n# Install dependencies\nnpm install\n\n# Run all evaluations\nnpm run eval\n\n# Run in watch mode\nnpm run eval:watch\n```\n\n## Test Scenarios\n\n| # | Scenario | Change Type | Expected Files | Difficulty |\n|---|----------|-------------|----------------|------------|\n| 1 | New Endpoint | Add POST endpoint | 3 files | Easy |\n| 2 | Rename Parameter | Parameter rename | 2 files | Medium |\n| 3 | Breaking Change | Schema change | 4 files | Easy |\n| 4 | New Feature | Major feature | 4+ files | Hard |\n| 5 | Deprecation | Deprecate endpoint | 4 files | Medium |\n| 6 | Internal Refactor | No API changes | 0 files (negative) | Hard |\n| 7 | Config Change | New env vars | 2 files | Easy |\n| 8 | Behavior Change | Sorting behavior | 4 files | Hard |\n\nSee [EXPECTED_RESULTS.md](./EXPECTED_RESULTS.md) for detailed expected suggestions per scenario.\n\n## Evaluation Metrics\n\n- **Precision:** Correct suggestions / Total suggestions (avoids false positives)\n- **Recall:** Correct suggestions / Expected suggestions (catches all needed updates)\n- **F1 Score:** Harmonic mean of Precision and Recall\n\n## Repository Structure\n\n```\njanusdoc-evals/\n├── src/                    # TaskFlow API source code\n├── docs/                   # TaskFlow documentation (test fixtures)\n├── evals/                  # Evalite test configuration\n│   ├── janusdoc.eval.ts   # Main eval file\n│   ├── test-scenarios.ts  # Scenario definitions\n│   ├── scorers.ts         # Precision/Recall/F1 scorers\n│   └── utils.ts           # Helper functions\n├── EXPECTED_RESULTS.md    # Expected suggestions per scenario\n└── README.md              # This file\n```\n\n## Environment Setup\n\nCreate a `.envrc` file (or export manually):\n\n```bash\nexport GITHUB_TOKEN=\"your_github_token\"\nexport OPENAI_API_KEY=\"your_openai_key\"\n```\n\n## Results\n\nCurrent JanusDoc performance:\n- **5/8 scenarios** completing successfully\n- **Precision:** 100% (no false positives)\n- **Recall:** 25-50% (room for improvement)\n- **Best F1 Score:** 66.7% on behavior changes\n\nSee evaluation output for detailed per-scenario results.\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdielduarte%2Fjanusdoc-evals","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdielduarte%2Fjanusdoc-evals","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdielduarte%2Fjanusdoc-evals/lists"}