chore: Cherry-picked changes from upstream

.github/workflows/ci.yml

@@ -13,7 +13,7 @@ permissions:
 
 jobs:
   test-typescript:
-    name: TypeScript Tests
+    name: TypeScript Checks
     runs-on: ubuntu-latest
 
     steps:
@@ -39,12 +39,12 @@ jobs:
         run: npm ci
         working-directory: eval
 
-      - name: Check Format
-        id: npm-format-check
-        run: npm run format:check
+      - name: Check
+        id: check
+        run: npm run check
         working-directory: eval
 
-      - name: Lint
-        id: npm-lint
-        run: npm run lint
+      - name: Test
+        id: test
+        run: npm run test
         working-directory: eval

.github/workflows/linter.yml

@@ -10,12 +10,10 @@ on:
 
 permissions:
   contents: read
-  packages: read
-  statuses: write
 
 jobs:
   lint:
-    name: Lint Codebase
+    name: Vite+ Check
     runs-on: ubuntu-latest
 
     steps:
@@ -27,8 +25,6 @@ jobs:
       - name: Checkout
         id: checkout
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
-        with:
-          fetch-depth: 0
 
       - name: Setup Node.js
         id: setup-node
@@ -43,15 +39,7 @@ jobs:
         run: npm ci
         working-directory: eval
 
-      - name: Lint Codebase
-        id: super-linter
-        uses: super-linter/super-linter/slim@9e863354e3ff62e0727d37183162c4a88873df41 # v8.6.0
+      - name: Check
+        id: check
+        run: npm run check
         working-directory: eval
-        env:
-          DEFAULT_BRANCH: main
-          FILTER_REGEX_EXCLUDE: dist/**/*
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          TYPESCRIPT_DEFAULT_STYLE: prettier
-          VALIDATE_ALL_CODEBASE: true
-          VALIDATE_JAVASCRIPT_STANDARD: false
-          VALIDATE_JSCPD: false

.tool-versions

@@ -1 +1,2 @@
 nodejs 24.15.0
+pnpm 10.33.0

README.md

@@ -9,7 +9,7 @@ simply include the following step in an action file:
 
 ```yaml
 - name: Run Evals
-  uses: step-security/eval-action@v1
+  uses: step-security/eval-action@v2
   with:
     api_key: ${{ secrets.BRAINTRUST_API_KEY }}
     runtime: node
@@ -20,12 +20,12 @@ You can configure the following variables:
 - `api_key`: Your
   [Braintrust API key](https://www.braintrust.dev/docs/api-reference/index#api-reference).
 - `root`: The root directory containing your evals (defaults to `'.'`). The root
-  directory must either have `node` or `python` configured.
+  directory must have `node`, `python`, or `go` configured.
 - `paths`: Specific paths, relative to the root, containing evals you'd like to
   run.
-- `runtime`: Either `node` or `python`
-- `package_manager`: Either `npm`, `pnpm`, or `yarn` for a `node` runtime, or
-  `pip` or `uv` for a `python` runtime.
+- `runtime`: Either `node`, `python`, or `go`
+- `package_manager`: Either `npm` or `pnpm` for a `node` runtime, `pip` or `uv`
+  for a `python` runtime, or `go` for a `go` runtime. You can omit this for Go.
 - `use_proxy`: Either `true` or `false`. If set, `OPENAI_BASE_URL` will be set
   to `https://braintrustproxy.com/v1`, which will automatically cache repetitive
   LLM calls and run your evals faster. Defaults to `true`.
@@ -61,7 +61,7 @@ jobs:
 
       - name: Setup Node.js
         id: setup-node
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v7
         with:
           node-version: 20
 
@@ -74,7 +74,7 @@ jobs:
         run: pnpm install
 
       - name: Run Evals
-        uses: step-security/eval-action@v1
+        uses: step-security/eval-action@v2
         with:
           api_key: ${{ secrets.BRAINTRUST_API_KEY }}
           runtime: node
@@ -90,11 +90,32 @@ To see examples of fully configured templates, see the `examples` directory:
 - [`node with pnpm`](examples/node/pnpm.yml)
 - [`python with pip`](examples/python/pip.yml)
 - [`python with uv`](examples/python/uv.yml)
+- [`go`](examples/go/go.yml)
+
+## Go evals
+
+The Go runtime executes `go run ${paths}`. To include Go eval results in the PR
+comment, print each `ExperimentSummary` as one JSON line after calling
+`result.Summarize(ctx)`:
+
+```go
+summary, err := result.Summarize(ctx)
+if err != nil {
+    log.Fatal(err)
+}
+b, err := json.Marshal(summary)
+if err != nil {
+    log.Fatal(err)
+}
+fmt.Println(string(b))
+```
 
 ## How it works
 
-The action runs `braintrust eval` and collects experiment results, which are
-posted as a comment in the PR alongside a link to Braintrust. For example:
+For Node and Python, the action runs `braintrust eval`. For Go, the action runs
+`go run` on `paths` from `root`. It collects experiment results emitted as JSONL
+and posts them as a comment in the PR alongside a link to Braintrust. For
+example:
 
 ### Example braintrust eval report
 

action.yml

@@ -21,12 +21,12 @@ inputs:
     required: false
     default: "."
   runtime:
-    description: "The runtime to use for evals. Valid values: node, python."
+    description: "The runtime to use for evals. Valid values: node, python, go."
     required: true
   package_manager:
     description:
-      "The package manager to use for evals. Valid values: npm, pnpm, yarn, pip,
-      or uv depending on the runtime."
+      "The package manager to use for evals. Valid values: npm or pnpm for node,
+      pip or uv for python, or go for Go."
     required: false
     default: ""
   use_proxy: