Open Code Review (OCR) — Session & manifest
The audit trail: what was reviewed, what was skipped, why, and what a --resume run can safely reuse. Package: internal/session/.
What flows through it
Technical details
Package: internal/session/
Depends on: llm
Depended on by: CLI, LLM loop (Runner), Review agent, Scan agent, Session viewer
What actually happens here
history.go opens one JSONL file per run and appends TaskRecords (prompt, response, tool results) as the review progresses. manifest.go's ManifestBuilder is a strict state machine — RegisterSelected/SealSelected freezes the coverage denominator before any dispatch, then every item must transition through exactly one of MarkCompleted/MarkReused/MarkFailed before Finalize, or Finalize's validation catches the gap. resume.go matches a prior run's completed items to the current run by a content fingerprint (mode + paths + diff text, SHA-256), never by file path alone.
How the LLM / model version is chosen
No model calls — this package only records what other packages' model calls produced.
Deterministic (non-LLM) work in this module
All of it — this is the deterministic bookkeeping layer the architecture explicitly separates from the AI-driven review packages above it.
Part of the module docs index. Full interactive version, with every module
side by side: architecture.html §7. Cross-cutting mechanisms
this module participates in (retry, compression, manifest, resume, hashing): LLD.