peterj/docpr sync
Analyzes merged PR code changes and automatically updates documentation, if needed.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| llm_provider | LLM provider to use: 'anthropic' or 'openai' | no | anthropic |
| anthropic_api_key | Anthropic API key (required when llm_provider is 'anthropic') | no | — |
| openai_api_key | OpenAI API key (required when llm_provider is 'openai') | no | — |
| docs_repo | Documentation repository in the format 'owner/repo' | yes | — |
| docs_repo_token | GitHub token with read/write access to the documentation repository. Needs 'contents: write' and 'pull-requests: write' permissions. | yes | — |
| docs_base_branch | Base branch in the docs repo to branch from and PR into | no | main |
| docs_path | Subdirectory within the docs repo to search for documentation (e.g. 'docs/' or 'content/') | no | "" |
| source_repo_token | GitHub token for reading the source (current) repository. Defaults to github.token. | no | ${{ github.token }} |
| model | LLM model to use. Defaults to 'claude-opus-4-5' for Anthropic and 'gpt-4o' for OpenAI. | no | "" |
| max_doc_files | Maximum number of doc files to fetch and analyze (to control token usage) | no | 20 |
| pr_label | Label to apply to the created documentation PR | no | docpr |
Outputs
no outputs