toolshrink

Cut large agent tool output by what it means, not by where it was cut.

I use Claude Code every day, and I always wanted to intervene in how it manages context. In the early days you could edit the session JSONL directly. Then that door closed.

When DeepSeek open-sourced Harness, where everything is a plugin, I looked inside. Tool output there is cut by size: keep the head, keep the tail, drop the middle. I read Codex and pi, and they do the same. None of them look at what the text contains.

That fails in a predictable way. Your test suite prints 5,000 passing lines and 3 failures in the middle. A size cut keeps the passes and throws away the failures. The model reads it, believes the run, and answers wrong.

So I built the shrinker I always wished Claude Code had. It reads the output first, recognizes its shape, and keeps the part that carries the information:

input: a vitest run, 31,958 chars, 805 lines, budget 2,000 chars

head+tail cut:   1,904 chars   the model learns: the summary
toolshrink:        255 chars   the model learns: which test failed,
                               why, at which line, and the summary

Everything removed is counted in a marker the model can read, and the complete original is saved to disk with a locator. Nothing is lost silently.

The cuts

Each cut recognizes one shape of text. The first one that recognizes the input runs. When none does, the size fallback runs, so the result always fits the budget.

Cut	Recognizes	Keeps	Drops
diff	git diff, patches	changed lines, file and hunk headers, 1 context line each side	unchanged context
json	one JSON value	the structure, 3 samples per long array, 5 keys per wide object, counts	repeated records
tests	vitest, jest, pytest, cargo test, go test	failures with their explanation, the summary	passing tests
build	tsc, cargo, gcc, webpack, esbuild	errors and warnings with their code frame, the summary	build progress
stacktrace	node, Python, Java, Ruby traces	the message and frames in YOUR code	dependency frames, counted
log	timestamped logs	errors and warnings with the lines before them, the ending	routine lines
tree	find, ls -R, file listings	the structure, 8 entries per directory, counts	crowded directories
repeat	retry storms, progress spam	2 samples per run plus "2,998 similar lines omitted"	consecutive near-identical lines
lint	eslint, ruff, clippy	each rule with its count and example locations, worst files	repeated occurrences of the same rule
install	npm, pip, pnpm, cargo	the summary, versions, deprecations, vulnerabilities, errors	fetch and download progress
csv	CSV, TSV, pipe tables	header, 5 rows from the start, 2 from the end, row and column counts	the rows between
gitlog	git log, both formats	the 15 newest commits, the total, the authors with counts	older commits
size	everything (fallback)	bash: the end · grep/read: the start · unknown: both ends	the rest, counted

Thirteen cuts ship today. Each one is a plain file with a shared interface, so adding your own is one file, not a fork.

Every cut follows four rules, taken from the three agents I read:

…