Add agent evaluations and Gadget durability tests - #268

Closed

AshishKumar4 wants to merge 8 commits into

mainfrom

wip/agent-eval-harness

Commits on Aug 18, 2026

Add a reusable agent session driver to integration-tests
AshishKumar4
committed
7974ef1
Add outcome evals for the Workshop agent, and a local runner
AshishKumar4
committed
3b51dfb
Run Workshop evals nightly and on demand
AshishKumar4
committed
7a1baa9

Commits on Aug 19, 2026

Replace the eval tasks with real applications
AshishKumar4
committed
309021c
Test Gadget durability, and prove the concurrency check can fail
AshishKumar4
committed
94f3909
Document which test suite to add to, and why they differ
AshishKumar4
committed
5383705
Add a testing strategy document
AshishKumar4
committed
59c495e
Make the testing strategy document technical
AshishKumar4
committed
f027065