0.71.0

mailcow/mailcow-dockerized0.71.0Feb 17, 2026by takahirom

AI Summary

The update introduces a new command-line feature allowing users to run specific tasks for benchmarking purposes. It also enhances configuration management by adding tags to the result file to support integration with other tools.

Key Highlights

Added 'arbigent run task' command for single-goal execution and performance benchmarking
Added tags to result.yml for scenario management with external tools
Added AndroidWorld benchmark CI workflow

New Features

Added 'run task' subcommand for single-goal execution
Added tags to ArbigentScenarioResult in result.yml
Added AndroidWorld benchmark CI workflow
Prevented Legal information scenario from opening Third-party licenses

Full Release Notes

* We've added the `arbigent run task "goal"` command so you can easily try an Arbigent task. This lets us measure Arbigent’s performance with benchmarks.
* We've added tags to result.yml so you can manage scenarios with other tools.

## What's Changed
* Add 'run task' subcommand for single-goal execution by @takahirom in https://github.com/takahirom/arbigent/pull/366
* Add AndroidWorld benchmark CI workflow by @takahirom in https://github.com/takahirom/arbigent/pull/367
* Prevent Legal information scenario from opening Third-party licenses by @takahirom in https://github.com/takahirom/arbigent/pull/370
* Add tags to ArbigentScenarioResult in result.yml by @takahirom in https://github.com/takahirom/arbigent/pull/371


**Full Changelog**: https://github.com/takahirom/arbigent/compare/0.70.0...0.71.0