Print a few lines from the test harness and log the rest to a file

Test output for an agent stays short, puts each error on one searchable line, and includes precomputed summaries.

Prompt

Evaluate and apply this CI technique to my repository: Print a few lines from the test harness and log the rest to a file.

Test output for an agent stays short, puts each error on one searchable line, and includes precomputed summaries.

Read the technique and its source-backed company examples: https://starsling.dev/ci-playbooks/techniques/agent-readable-test-output.md

Inspect this repository’s CI workflows, build and test commands, dependencies, and recent run timings. Identify where this technique applies and explain the expected benefit using this repository’s evidence.
Measure a baseline from recent comparable runs: elapsed time, queue time, runner minutes and failures where available. If data is unavailable, say what cannot be measured.
Compare relevant company approaches, checking prerequisites, platform differences and tradeoffs. Rank applicable options by evidence, fit and measurable opportunity; do not present company results as predictions for this repo.
Recommend the smallest safe change, show what checks and fallback paths remain, and ASK ME WHICH CHANGE TO APPROVE BEFORE EDITING ANY FILES.
Only after approval, work on a new feature branch, make one reversible change, and open a reviewable pull request. Never merge or push to a default or protected branch.
Keep required checks, test coverage, deployment and release behavior intact. Validate the change and compare equivalent runs where possible; report limitations and what should be monitored after merge.

View all playbooks

How Anthropic used this technique

Read what Anthropic changed and follow the original sources.

Print a few lines from the test harness and log the rest to a file

In Anthropic's C compiler project, the test harness prints at most a few lines and logs important information to a file, so the agent's context window holds no thousands of useless bytes. Log files put ERROR and the reason on the same line, so grep finds them, and aggregate summary statistics are precomputed. The harness prints incremental progress infrequently and has a default --fast option that runs a 1% or 10% random sample, deterministic per agent and random across machines.

Use it when: An agent reads CI logs or test output to decide what to fix, and that output is long or free-form.
Before applying it: The full detail stays in a log file the agent opens on demand, uploaded as an artifact so people read the same file.

How Anthropic used this technique

Print a few lines from the test harness and log the rest to a file

Company Playbooks