Bitter Frontier What coding agents just made possible, where the bottleneck moved, and what deserves attention.

Evidence record / omp

A dated record of one change, kept so the writing that cites it can be checked. Compiled from the sources listed below by the research run, not written for reading. The judgment lives in the issues that cite it, below.

2026-10-13-omp-saved-streaming-tool-output-became-a-16-mib-head-and-tail-sample-by-default

Saved streaming tool output became a 16 MiB head-and-tail sample by default. Bash, Python and JavaScript eval artifact files now default to a 16 MiB cap. Larger output retains its beginning and recent tail around a truncation notice; an artifact URL no longer implies the full raw stream is saved. tools.artifactMaxBytes: 0 restores unlimited output.

Channel: tagged-release. Half: both. Date: 2026-10-01 (v18.4.9).

Operator consequence: If saved tool output is an audit log or parser input, inspect truncation notices and set an explicit retention policy. Unlimited output preserves completeness at the cost of storage growth.

Receipt

Finding metadata

Confidence
high

Run: 2026-10-13-profile-refresh-2026-09-21_2026-10-13-frontier-v0

Finding ID: 2026-10-13-omp-saved-streaming-tool-output-became-a-16-mib-head-and-tail-sample-by-default

Profile citations

  • omp / claim / bounded-saved-output

Source links

Primary links, including exact changelog lines when available.

  1. OMP (Oh My Pi)
    commit2026-10-13-omp-saved-streaming-tool-output-became-a-16-mib-head-and-tail-sample-by-defaultgithub.com/can1357/oh-my-pi/commit/cbf7898ce150c8a903db24fabe8f111567a3dc97tagged commit file2026-10-13-omp-saved-streaming-tool-output-became-a-16-mib-head-and-tail-sample-by-defaultcan1357/oh-my-pi / docs/settings.md#L615tagged commit file2026-10-13-omp-saved-streaming-tool-output-became-a-16-mib-head-and-tail-sample-by-defaultcan1357/oh-my-pi / packages/tui/src/tools/streaming-output.ts

Versioned source: run artifact