thebrain-digest

A digest of the brain

The modification log is unreadable on its own: a hundred lines of "note changed". The job is to turn it into an account of what the person was doing.

How to gather it

brain_recent_changes { since: "2026-08-04T00:00:00Z", limit: 200, identifiers: true }

Without since it takes a week. The tool already decodes the numeric codes into readable phrasings and names the thoughts. identifiers: true adds a Thoughts section: every thought the rows name that is still there, once, as name — identifier. Leave it out if you will not open any thought: it makes the result about a third longer.

A thought created, renamed or deleted in the period is named from the log itself, and a deleted one reads name (deleted).

Limit: the tool reads at most sixty thoughts a call. Over a long period a thought past that has the name the log kept, or reads (name not read) when it was only edited or linked in the period, and Totals says how many were not read — that is not lost data, it is saved requests. If you need a full breakdown, take a shorter period.

How to narrate it

Do not retell the log line by line. Group by theme and say what was going on.

Bad:

11 August 13:24 created — API layer
11 August 13:24 note created
11 August 13:24 created — Semantic layer
11 August 13:24 note created

Good:

The week was mostly the "Implementation" branch: four layers appeared
(API, semantics, operations, server), each with a note carrying measurements.

Separately, the tools area was extended: entries about brain_ingest and the
race condition found in it.

Old entries were revised: "Search indexing takes up to 15 seconds" was renamed
to "Writes are not immediately visible" — the earlier phrasing turned out to be
wrong.

To narrate like that, look at which thoughts changed:

brain_get_thought { thoughtId: "<identifier from the Thoughts section>" }

A few key ones are enough, not every single one.

What to pay attention to