v2.2.0

Feature

v2.2.0

Feature

Flaky case detection

Cases that flip between pass and fail on the same input are marked flaky and kept out of the merge gate.

+

flaky: true marker in results

~

Threshold math ignores flaky cases

+

flaky: true marker in results

~

Threshold math ignores flaky cases

A case is flaky when it gives different verdicts on the same input in three of its last ten runs. Flaky cases still show in the report.

Upgrade

Run npm i @tessel/sdk@2.2.0 or pip install -U tessel. No config changes needed.

A case is flaky when it gives different verdicts on the same input in three of its last ten runs. Flaky cases still show in the report.

Upgrade

Run npm i @tessel/sdk@2.2.0 or pip install -U tessel. No config changes needed.

tessel

Evals for LLM apps, on every commit.

Release notes, once a month

All systems normal · © 2026 Tessel Labs

tessel

tessel

Evals for LLM apps, on every commit.

Release notes, once a month

All systems normal · © 2026 Tessel Labs

tessel

Create a free website with Framer, the website builder loved by startups, designers and agencies.