Logbook

logbook

[ci] [npm]

Git history is large. When coding agents do not inspect it, they can re-propose approaches a repository already rejected.

Logbook turns a repository's Git history into memory an agent can use: a deterministic recall layer (hotspots, reverted approaches, suppressions, assertion weakening, and bounded history queries) plus durable notes an agent writes down after it investigates why a change happened.

Everything runs locally. The CLI has zero npm dependencies, reads raw Git objects for evidence checks, and never sends repository data anywhere. Node.js 18 or newer is required.

npx -y @promptwheel/logbook@latest init

init analyzes the repo, writes the history artifacts, and installs a compact workflow in AGENTS.md, CLAUDE.md, or .cursorrules so the agent reads history before it plans: read LOGBOOK.md, page each task path with context --file, verify leads with git show, refresh, audit, and annotate what it verified. The same workflow ships as an agent skill in plugin/skills/logbook/SKILL.md.

Its output, shortened:

  1,326 commits · 322 files · 7.3 years · 354 authors
  ✓ wrote LOGBOOK.md     hotspots · do-not-retry · suppression ledger  ✓ wrote events.jsonl   1,326 structured events

The examples below use logbook as the binary name. Run them through the exact package above, or install @promptwheel/logbook@latest locally or globally.

Quick start

logbook                                      # refresh the history artifactslogbook context --file src/cache.ts --revert # bounded history for a pathlogbook audit                                # what is still suppressed, and since whenlogbook query --json --file src/cache.ts     # the same events as JSONLlogbook doctor                               # read-only artifact and wiring health

context returns history in pages of at most 20 events and 8 KiB; repeat the identical filters with each NEXT cursor until END complete.

When an agent investigates why a prior change happened during real work, it can preserve the result immediately, with no prompt or human gate:

logbook annotate <commit> "why this approach was rejected" --by codex

The note is durably appended to annotations.jsonl and appears in LOGBOOK.md before the command exits. It is always labeled machine-authored and unreviewed and is bounded in the startup digest. An optional exact quote can be attached with --span, --side, and (for diff evidence) --evidence-file; a quote that does not ground in raw Git objects is rejected rather than guessed.

What it stores

Commit annotations.jsonl to share the notes with the team, or add it to .gitignore to keep them local to one checkout.

History queries and context economics

context preserves filtered query order but emits pages of at most 20 events and 8 KiB. A cursor is bound to the repository HEAD, filters, analysis window, and ordered event set, so a stale or edited cursor is rejected instead of silently drifting.

The history scan is cached in bounded windows. On a history of tens of thousands of commits a cold run takes tens of seconds, a warm run that reuses the ledger on disk is well under a second, and a repeat call with an unchanged HEAD in an MCP session is milliseconds. LOGBOOK_NO_CACHE=1 forces a rebuild; LOGBOOK_WINDOW=N tunes the window.

In a random 400-repo sample of the top 2,500 GitHub repositories, the median LOGBOOK.md was about 1,000 estimated tokens while the median full git log was 82× larger. See context economics and the bounded context format.

Integrate: CLI, MCP, or import

Three surfaces over the same deterministic history layer:

• CLI + JSON. logbook query --json (filtered, 200 rows unless you pass --limit) and logbook --json (the full ledger) emit JSONL you can shell from any language. logbook audit --json returns the live suppressions as one array. The JSON is cache-invariant (byte-identical with and without LOGBOOK_NO_CACHE=1), so it is safe to parse in CI.
• MCP. @promptwheel/logbook-mcp (bin logbook-mcp) serves the history to an agent over the Model Context Protocol: a Claude Code or other MCP client reads hotspots, do-not-retry reverts, and suppression signals without shelling anything.
• Import. The package is importable and importing it never runs the CLI. queryEvents, analyze, auditHead, and hotspots are exported for advanced in-process use; the scan and cache entry points take explicit options, so the CLI and MCP are the first-class surfaces for most integrations.

The paired check engine, promptwheel, has the matching surface. Both are described in its INTEGRATE.md.

Evidence status

An internal six-task planning experiment on history-dense repos found that agents without history re-proposed already-tried or already-finished work in 4 of 6 repos and 0 of 6 with LOGBOOK.md in context, at about 4.7k extra plan tokens. A later sealed held-out screen on ten new tasks found no advantage over a strong raw-Git instruction, and traced the gap to retrieval rather than the index. The calibrated claim is: valuable on sufficiently difficult, history-dense tasks; not universally better. Details and limits are in wrong-work-benchmark.md and does-it-change-agent-behavior.md.

Honest scope

• Findings are leads, not verdicts. A suppression means "look here," not misconduct.
• Detection is deterministic regex over commit subjects and diffs. It misses history erased by squash/rebase and anything never committed.
• Shallow clones starve historical analysis; fetch the missing history before treating absence as evidence.
• Code maps explain where code is. Logbook focuses on what happened over time.

Command reference

logbook init [path]logbook [path] [--json]logbook audit [path] [--json [--file P ...] [--ref REF]]logbook doctor [path]logbook query [path] [filters] [--json]logbook context [path] [filters] [--cursor TOKEN]logbook annotate SHA "WHY" [optional evidence] [--by WHO]

logbook --help lists every filter and option.

Upgrading

0.11.0 removes logbook refine, logbook journey, and --out. Both commands now fail with not a git repository, and --out is an unknown option. Artifacts always go to the repository root. The analyze result no longer carries first, last, threshold, mentor, abyss, winter, or trials, and renderJourneyAnsi, journeyBeats, almanacStats, GATE_PAT, and MENTOR_PAT are no longer exported. The event and --json shapes, the five MCP tools, and doctor did not change. MCP server 0.8.0 requires this core.

0.10.0 removed the experimental reviewed-decision layer and the OKF export: annotate-draft, pending, accept/accept-draft, accept-lead, reject-lead, check, publish, outcomes, and export. Files that layer left behind (.logbook/, decision-cards.jsonl, annotation-reviews.jsonl) are ignored and can be deleted by hand.

From any release, a normal refresh rewrites a ## Repo memory block that an earlier release generated, so doctor passes after an upgrade. User-edited blocks are never touched. Existing annotations.jsonl rows stay unreviewed digest notes. A JOURNEY.md left by a release before 0.9.7 is ignored and can be deleted. If 0.8 wrote annotations to a custom directory, move that annotations.jsonl to the repository root. Earlier notes are in the git history of this file.

The logbook records what happened; the check verifies what holds

Logbook tells you what history says. promptwheel is the check that verifies whether today's claimed improvement came from the code rather than moving the goalposts.

Apache 2.0.