Guides

Filtering events

Compose declarative event filters from small builders over named junk categories.

Scoring sentiment

Wrap an inference model in a composable ScoreSpec whose deterministic stages short-circuit or post-process its score.

The Rust engine

Why cc-transcript executes on a single compiled engine, and how hand-owned literals and golden fixtures pin its correctness without a second implementation.

Compose your own policy

Declare a project’s filtering and scoring policy as data — one FilterSpec and one ScoreSpec, built from primitives, in a single module.

Mining feedback

Detect user corrections — tool denials, plan rejections, interrupts, review comments — as confidence-calibrated signals you can filter, persist, and judge.

The transcript CLI

Investigate Claude Code transcripts from the shell — list, stats, grep, and show form a funnel that keeps token spend proportional to what you read.

Codex rollouts

Parse OpenAI Codex CLI sessions with the same API — provider-transparent parsing, rollout discovery, subagent joins, gate specs over apply_patch, rollout attachments, per-rollout session info, and the activity probe.

The deep view

Query across every subagent and attached transcript — walk the sidechain tree lazily, union tool calls with Session.deep, and fold external rollouts in at depth 1.