Analysis and re-analysis

ReviewArc analyzes the pull request’s complete current diff against its base revision. Re-analysis is intentionally end to end: it evaluates the current pull request again rather than analyzing only commits added since the previous run.

That choice keeps chapters, risks, test relationships, and cross-file behavior coherent after a revision changes. It also means re-analysis cost and time generally scale with the full pull request, not only its newest commit.

Read-only execution

ReviewArc invokes Codex with structured JSON or JSONL output against an isolated snapshot. The analysis process is read-only. ReviewArc does not run arbitrary project commands, package scripts, tests, hooks, or generated instructions from the repository.

Progress is streamed into the app while the structured review model is built.

Evidence validation

AI output is treated as a proposal, not ground truth. Before displaying evidence, ReviewArc validates that each referenced file belongs to the reviewed revision and that each line range exists in that file or diff.

Claims without valid supporting evidence remain explicitly unverified. ReviewArc preserves the distinction between:

• Facts supported directly by the reviewed source or diff.
• Inferences reasoned from available evidence.
• Unknowns that cannot be resolved from the pull request alone.

Stale analysis

ReviewArc records the head revision used by an analysis. When GitHub reports a different pull request head, the existing analysis is marked stale. Your previous analysis and notes remain available, but the app makes the revision mismatch visible and offers re-analysis against the new head.