pr-review-core 0.2.0

Core engine for a self-hosted advisory AI PR reviewer: fetches a pull request diff, reviews it with a Claude model via OpenRouter, and posts line-anchored inline comments plus a summary. Works with GitHub and Bitbucket.
Documentation

pr-review-core

Core engine behind self-hosted, advisory AI pull-request reviewers.

pr-review-core fetches a pull request's unified diff, reviews it with a Claude model via OpenRouter, and posts line-anchored inline comments plus a summary comment. It works with both GitHub and Bitbucket, and optionally runs an agentic pass that clones the repo and lets the model investigate cross-file context (grep / read_file / list_dir) before writing its findings.

This crate is a library — it carries no bot identity of its own. Consumers (the actual bot binaries) depend on it and inject their branding and any extra prompt through Config.

What's in the box

  • Provider-agnostic review flow (review::run_review) across GitHub + Bitbucket.
  • Structured JSON review from the model, anchored to diff lines that the provider will accept (out-of-diff findings fold into the summary).
  • Optional agentic reviewer with a two-tier model split (cheap explore model + stronger synthesis model).
  • Noise control: an optional self-critique pass drops false positives / nits, a per-finding confidence score drives ranking, and a per-PR cap keeps reviews focused.
  • File globs: lockfiles, generated, vendored, and minified files are excluded from the diff before the model ever sees them (saves tokens and noise).
  • Any OpenAI-compatible endpoint: point it at OpenRouter, or Ollama / vLLM / Together / Groq / a local server via LLM_BASE_URL + LLM_API_KEY.
  • Webhook signature verification and payload parsing helpers.
  • Dedupe: the bot updates its own prior comments on re-review instead of stacking.

Injecting identity and prompt

Nothing about the bot's identity is hardcoded. Config::from_env() reads:

Field Env var Default
comment_marker COMMENT_MARKER 🤖 ai-pr-review
user_agent USER_AGENT pr-review-core
http_referer OPENROUTER_HTTP_REFERER https://github.com/nhatvu148/pr-review-core
x_title OPENROUTER_X_TITLE pr-review
extra_system_prompt EXTRA_SYSTEM_PROMPT / EXTRA_SYSTEM_PROMPT_FILE (empty)
  • comment_marker is the signature appended to every comment and the dedupe key used to find/update the bot's own comments.
  • extra_system_prompt is appended to the built-in system prompts. Set it inline via EXTRA_SYSTEM_PROMPT, or point EXTRA_SYSTEM_PROMPT_FILE at a file baked into your Docker image to inject a large conventions block without touching the library.

Other operational settings (OpenRouter key/models, provider tokens, agentic mode, size caps) are also read from the environment — see src/config.rs.

Review quality & cost controls

Env var Default Effect
SELF_CRITIQUE true Second skeptical pass that removes false positives / low-value nits.
MIN_CONFIDENCE 0 Drop findings below this confidence (0–100).
MAX_FINDINGS 20 Cap findings per PR (ranked by severity then confidence).
EXCLUDE_GLOBS lockfiles, generated, vendored, minified Comma-separated globs skipped before the LLM call.
INCLUDE_GLOBS (empty = all) If set, only files matching these globs are reviewed.
LLM_BASE_URL OPENROUTER_BASE_URL → openrouter OpenAI-compatible endpoint (e.g. http://localhost:11434/v1 for Ollama).
LLM_API_KEY OPENROUTER_API_KEY API key for the endpoint above.

License

Licensed under either of

at your option.

Contribution

Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in the work by you, as defined in the Apache-2.0 license, shall be dual licensed as above, without any additional terms or conditions.