From 004ada2c0e3a23d937650286255ad1f8f473549e Mon Sep 17 00:00:00 2001 From: cte Date: Fri, 6 Jun 2025 09:15:58 -0700 Subject: [PATCH 1/2] Run evals on port 8080 --- apps/web-evals/package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/apps/web-evals/package.json b/apps/web-evals/package.json index 99fa68829c..92c68cf410 100644 --- a/apps/web-evals/package.json +++ b/apps/web-evals/package.json @@ -5,7 +5,7 @@ "scripts": { "lint": "next lint", "check-types": "tsc -b", - "dev": "scripts/check-services.sh && next dev", + "dev": "scripts/check-services.sh && next dev --port 8080", "format": "prettier --write src", "build": "next build", "start": "next start" From 618af52b17102ee3140698347cc01d00154f03dd Mon Sep 17 00:00:00 2001 From: cte Date: Fri, 6 Jun 2025 09:17:03 -0700 Subject: [PATCH 2/2] Forgot these --- packages/evals/README.md | 5 ++--- packages/evals/docker-compose.yml | 2 +- packages/evals/scripts/setup.sh | 4 ++-- 3 files changed, 5 insertions(+), 6 deletions(-) diff --git a/packages/evals/README.md b/packages/evals/README.md index bb202a7094..4ac670b8c2 100644 --- a/packages/evals/README.md +++ b/packages/evals/README.md @@ -29,13 +29,13 @@ Start the evals service: docker compose -f packages/evals/docker-compose.yml --profile server --profile runner up --build --scale runner=0 ``` -The initial build process can take a minute or two. Upon success you should see ouput indicating that a web service is running on [localhost:3000](http://localhost:3000/): +The initial build process can take a minute or two. Upon success you should see ouput indicating that a web service is running on [localhost:8080](http://localhost:8080/): Screenshot 2025-06-05 at 12 05 38 PM Additionally, you'll find in Docker Desktop that database and redis services are running: Screenshot 2025-06-05 at 12 07 09 PM -Navigate to [localhost:3000](http://localhost:3000/) in your browser and click the 🚀 button. +Navigate to [localhost:8080](http://localhost:8080/) in your browser and click the 🚀 button. By default a evals run will run all programming exercises in [Roo Code Evals](https://github.com/RooCodeInc/Roo-Code-Evals) repository with the Claude Sonnet 4 model and default settings. For basic configuration you can specify the LLM to use and any subset of the exercises you'd like. For advanced configuration you can import a Roo Code settings file which will allow you to run the evals with Roo Code configured any way you'd like (this includes custom modes, a footgun prompt, etc). @@ -68,7 +68,6 @@ To stop an evals run early you can simply stop the "controller" container using Screenshot 2025-06-06 at 9 00 41 AM - ## Advanced Usage / Debugging The evals system runs VS Code headlessly in Docker containers for consistent, reproducible environments. While this design ensures reliability, it can make debugging more challenging. For debugging purposes, you can run the system locally on macOS, though this approach is less reliable due to hardware and environment variability. diff --git a/packages/evals/docker-compose.yml b/packages/evals/docker-compose.yml index 24b9626f74..69dab9bee2 100644 --- a/packages/evals/docker-compose.yml +++ b/packages/evals/docker-compose.yml @@ -52,7 +52,7 @@ services: context: ../../ dockerfile: packages/evals/Dockerfile.web ports: - - "3000:3000" + - "8080:3000" environment: - HOST_EXECUTION_METHOD=docker volumes: diff --git a/packages/evals/scripts/setup.sh b/packages/evals/scripts/setup.sh index d95b6e2514..8ef48ff7b5 100755 --- a/packages/evals/scripts/setup.sh +++ b/packages/evals/scripts/setup.sh @@ -377,7 +377,7 @@ fi echo -e "\n🚀 You're ready to rock and roll! \n" -if ! nc -z localhost 3000; then +if ! nc -z localhost 8080; then read -p "🌐 Would you like to start the evals web app? (Y/n): " start_evals if [[ "$start_evals" =~ ^[Yy]|^$ ]]; then @@ -386,5 +386,5 @@ if ! nc -z localhost 3000; then echo "💡 You can start it anytime with 'pnpm --filter @roo-code/web-evals dev'." fi else - echo "👟 The evals web app is running at http://localhost:3000" + echo "👟 The evals web app is running at http://localhost:8080" fi