diff --git a/benchmarks/osworld/README.md b/benchmarks/osworld/README.md index 32785afc..327ad59c 100644 --- a/benchmarks/osworld/README.md +++ b/benchmarks/osworld/README.md @@ -26,4 +26,5 @@ Custom `/tests/test.sh` defined inline in the Dockerfile. Reward is hard-coded t - `Dockerfile` — builds the benchmark image - `compose.yaml` — compose file for `eval-containers run osworld` +- `benchmarks/_chart/presets/osworld.yaml` — this benchmark's bespoke k8s topology (sidecars/Deployments/Services), overlaid on the shared chart when rendered with `--set benchmark=osworld` - `README.md` — this file diff --git a/benchmarks/tau-bench/README.md b/benchmarks/tau-bench/README.md index d2eaecbc..2ad646a4 100644 --- a/benchmarks/tau-bench/README.md +++ b/benchmarks/tau-bench/README.md @@ -26,4 +26,5 @@ Custom `/tests/test.sh` defined inline in the Dockerfile. Reward is hard-coded t - `Dockerfile` — builds the benchmark image - `compose.yaml` — compose file for `eval-containers run tau-bench` +- `benchmarks/_chart/presets/tau-bench.yaml` — this benchmark's bespoke k8s topology (sidecars/Deployments/Services), overlaid on the shared chart when rendered with `--set benchmark=tau-bench` - `README.md` — this file diff --git a/benchmarks/visualwebarena/README.md b/benchmarks/visualwebarena/README.md index ef291613..7ff6bbec 100644 --- a/benchmarks/visualwebarena/README.md +++ b/benchmarks/visualwebarena/README.md @@ -26,4 +26,5 @@ Custom `/tests/test.sh` defined inline in the Dockerfile. Reward is hard-coded t - `Dockerfile` — builds the benchmark image - `compose.yaml` — compose file for `eval-containers run visualwebarena` +- `benchmarks/_chart/presets/visualwebarena.yaml` — this benchmark's bespoke k8s topology (sidecars/Deployments/Services), overlaid on the shared chart when rendered with `--set benchmark=visualwebarena` - `README.md` — this file diff --git a/benchmarks/webarena/README.md b/benchmarks/webarena/README.md index a55fac29..c8773df3 100644 --- a/benchmarks/webarena/README.md +++ b/benchmarks/webarena/README.md @@ -26,4 +26,5 @@ Custom `/tests/test.sh` defined inline in the Dockerfile. - `Dockerfile` — builds the benchmark image - `compose.yaml` — compose file for `eval-containers run webarena` +- `benchmarks/_chart/presets/webarena.yaml` — this benchmark's bespoke k8s topology (sidecars/Deployments/Services), overlaid on the shared chart when rendered with `--set benchmark=webarena` - `README.md` — this file