From 1e9ee1c93dfbcb48033a32b688397d27ba4aaec0 Mon Sep 17 00:00:00 2001
From: Anirudh Kamath <github@kamath.io>
Date: Sat, 21 Dec 2024 23:08:41 -0800
Subject: [PATCH] package json and changeset

---
 .changeset/dirty-apples-pay.md |  4 +-
 .github/workflows/ci.yml       | 94 +++++++++++++++++-----------------
 package.json                   |  3 +-
 3 files changed, 51 insertions(+), 50 deletions(-)

diff --git a/.changeset/dirty-apples-pay.md b/.changeset/dirty-apples-pay.md
index 93aa10d4..38be23d6 100644
--- a/.changeset/dirty-apples-pay.md
+++ b/.changeset/dirty-apples-pay.md
@@ -1,5 +1,5 @@
 ---
-"@browserbasehq/stagehand": major
+"@browserbasehq/stagehand": patch
 ---
 
-Move stagehand.act() -> stagehand.page.act()
+Move stagehand.act() -> stagehand.page.act() and deprecate stagehand.act()
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 99a46700..93377ddf 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -85,6 +85,53 @@ jobs:
       - name: Run E2E Tests
         run: npm run e2e
 
+run-act-evals:
+    runs-on: ubuntu-latest
+    timeout-minutes: 25
+    needs: [run-text-extract-evals]
+    env:
+      OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+      BRAINTRUST_API_KEY: ${{ secrets.BRAINTRUST_API_KEY }}
+      BROWSERBASE_API_KEY: ${{ secrets.BROWSERBASE_API_KEY }}
+      BROWSERBASE_PROJECT_ID: ${{ secrets.BROWSERBASE_PROJECT_ID }}
+      HEADLESS: true
+      EVAL_ENV: browserbase
+
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v4
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: "20"
+
+      - name: Install dependencies
+        run: npm install --no-frozen-lockfile
+
+      - name: Install Playwright browsers
+        run: npm exec playwright install --with-deps
+
+      - name: Run Act Evals
+        run: npm run evals category act
+
+      - name: Log Act Evals Performance
+        run: |
+          experimentName=$(jq -r '.experimentName' eval-summary.json)
+          echo "View results at https://www.braintrust.dev/app/Browserbase/p/stagehand/experiments/${experimentName}"
+          if [ -f eval-summary.json ]; then
+            act_score=$(jq '.categories.act' eval-summary.json)
+            echo "Act category score: $act_score%"
+            if (( $(echo "$act_score < 80" | bc -l) )); then
+              echo "Act category score is below 80%. Failing CI."
+              exit 1
+            fi
+          else
+            echo "Eval summary not found for act category. Failing CI."
+            exit 1
+          fi
+
   run-extract-evals:
     needs: [run-lint, run-build, run-e2e-tests]
     runs-on: ubuntu-latest
@@ -201,52 +248,7 @@ jobs:
             exit 1
           fi
 
-  run-act-evals:
-    runs-on: ubuntu-latest
-    timeout-minutes: 25
-    needs: [run-text-extract-evals]
-    env:
-      OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-      ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-      BRAINTRUST_API_KEY: ${{ secrets.BRAINTRUST_API_KEY }}
-      BROWSERBASE_API_KEY: ${{ secrets.BROWSERBASE_API_KEY }}
-      BROWSERBASE_PROJECT_ID: ${{ secrets.BROWSERBASE_PROJECT_ID }}
-      HEADLESS: true
-      EVAL_ENV: browserbase
-
-    steps:
-      - name: Check out repository code
-        uses: actions/checkout@v4
-
-      - name: Set up Node.js
-        uses: actions/setup-node@v4
-        with:
-          node-version: "20"
-
-      - name: Install dependencies
-        run: npm install --no-frozen-lockfile
-
-      - name: Install Playwright browsers
-        run: npm exec playwright install --with-deps
-
-      - name: Run Act Evals
-        run: npm run evals category act
-
-      - name: Log Act Evals Performance
-        run: |
-          experimentName=$(jq -r '.experimentName' eval-summary.json)
-          echo "View results at https://www.braintrust.dev/app/Browserbase/p/stagehand/experiments/${experimentName}"
-          if [ -f eval-summary.json ]; then
-            act_score=$(jq '.categories.act' eval-summary.json)
-            echo "Act category score: $act_score%"
-            if (( $(echo "$act_score < 80" | bc -l) )); then
-              echo "Act category score is below 80%. Failing CI."
-              exit 1
-            fi
-          else
-            echo "Eval summary not found for act category. Failing CI."
-            exit 1
-          fi
+  
 
   run-observe-evals:
     runs-on: ubuntu-latest
diff --git a/package.json b/package.json
index 9941326a..e0eeaee7 100644
--- a/package.json
+++ b/package.json
@@ -81,6 +81,5 @@
   "bugs": {
     "url": "https://github.com/browserbase/stagehand/issues"
   },
-  "homepage": "https://github.com/browserbase/stagehand#readme",
-  "packageManager": "pnpm@9.15.0+sha512.76e2379760a4328ec4415815bcd6628dee727af3779aaa4c914e3944156c4299921a89f976381ee107d41f12cfa4b66681ca9c718f0668fa0831ed4c6d8ba56c"
+  "homepage": "https://github.com/browserbase/stagehand#readme"
 }