Merge branch 'main' into contrib/132

Author: miguelg719

.changeset/dog-of-interesting-energy.md

@@ -0,0 +1,5 @@
+---
+"stagehand": patch
+---
+
+Fix stagehand.metrics on env:BROWSERBASE

.changeset/dragon-of-fabulous-persistence.md

@@ -0,0 +1,5 @@
+---
+"stagehand": patch
+---
+
+Fix max_steps parsing for agent execute options

.changeset/feathered-singing-duck.md

@@ -0,0 +1,5 @@
+---
+"stagehand": patch
+---
+
+Fix openai-litellm dependency bug

.changeset/gorilla-of-strongest-novelty.md

@@ -0,0 +1,5 @@
+---
+"stagehand": patch
+---
+
+Multi-tab support

.changeset/silkworm-of-regular-downpour.md

@@ -0,0 +1,5 @@
+---
+"stagehand": patch
+---
+
+added regression tests

.changeset/towering-organic-grouse.md

@@ -0,0 +1,5 @@
+---
+"stagehand": patch
+---
+
+Fix temperature setting for GPT-5 family of models

.changeset/vegan-intrepid-mustang.md

@@ -0,0 +1,5 @@
+---
+"stagehand": patch
+---
+
+Added frame_id_map to support multi-tab handling on API

.github/workflows/changesets.yml

@@ -69,6 +69,8 @@ jobs:
           cat pr-description.md >> $GITHUB_ENV
           echo "EOF" >> $GITHUB_ENV
           rm pr-description.md
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Bump versions
         if: steps.check_changesets.outputs.has_changesets == 'true'

.github/workflows/feature-parity.yml

@@ -47,7 +47,7 @@ jobs:
                 owner: context.repo.owner,
                 repo: context.repo.repo,
                 issue_number: context.issue.number,
-                body: `❌ **Parity Label Removed**\n\n@${context.actor}, you do not have sufficient permissions to add the 'parity' label. Only users with write access can trigger feature parity issues.\n\nIf you believe this feature should be implemented in the Python SDK, please ask a maintainer to add the label.`
+                body: `❌ **Parity Label Removed**\n\n@${context.actor}, you do not have sufficient permissions to add the 'parity' label. Only users with write access can trigger feature parity issues.\n\nIf you believe this feature should be implemented in the Typescript SDK, please ask a maintainer to add the label.`
               });
               
               throw new Error(`User ${context.actor} does not have write access to add parity label`);
@@ -62,7 +62,7 @@ jobs:
           app-id: ${{ secrets.PARITY_APP_ID }}
           private-key: ${{ secrets.PARITY_APP_PRIVATE_KEY }}
           owner: browserbase
-          repositories: stagehand
+          repositories: stagehand-python
 
       - name: Create issue in Python SDK repository
         uses: actions/github-script@v7
@@ -104,7 +104,7 @@ jobs:
             const issueTitle = `[Feature Parity] ${pullRequest.title}`;
             const issueBody = `## Feature Parity Request
 
-            This issue was automatically created from a pull request in the TypeScript Stagehand repository that was labeled with 'parity'.
+            This issue was automatically created from a pull request in the Python Stagehand repository that was labeled with 'parity'.
 
             ### Original PR Details
             - **PR**: #${context.issue.number} - ${pullRequest.title}
@@ -120,12 +120,12 @@ jobs:
             ${commentsSection}
 
             ### Action Required
-            Please review the changes in the original PR and implement equivalent functionality in the Python SDK if applicable.
+            Please review the changes in the original PR and implement equivalent functionality in the Typescript SDK if applicable.
 
             ---
             *This issue was automatically generated by the Feature Parity workflow.*`;
 
-            // Create the issue in the Python repository
+            // Create the issue in the Typescript repository
             const { data: issue } = await github.rest.issues.create({
               owner: 'browserbase',
               repo: 'stagehand',
@@ -141,5 +141,5 @@ jobs:
               owner: context.repo.owner,
               repo: context.repo.repo,
               issue_number: context.issue.number,
-              body: `🔄 **Feature Parity Issue Created**\n\nAn issue has been automatically created in the Python SDK repository to track parity implementation:\n${issue.html_url}`
+              body: `🔄 **Feature Parity Issue Created**\n\nAn issue has been automatically created in the Typescript SDK repository to track parity implementation:\n${issue.html_url}`
             });

.github/workflows/test.yml

@@ -180,6 +180,66 @@ jobs:
         name: smoke-test-results
         path: junit-smoke.xml
 
+  test-regression:
+    name: Regression Tests
+    runs-on: ubuntu-latest
+    needs: test-unit
+    if: |
+      contains(github.event.pull_request.labels.*.name, 'test-regression') ||
+      contains(github.event.pull_request.labels.*.name, 'regression')
+    
+    steps:
+    - uses: actions/checkout@v4
+    
+    - name: Set up Python 3.11
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.11"
+    
+    - name: Install system dependencies
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y xvfb
+    
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -e ".[dev]"
+        pip install jsonschema
+        playwright install chromium
+        playwright install-deps chromium
+    
+    - name: Run regression tests
+      run: |
+        xvfb-run -a pytest tests/ -v \
+          --cov=stagehand \
+          --cov-report=xml \
+          --junit-xml=junit-regression.xml \
+          -m "regression" \
+          --tb=short \
+          --maxfail=10
+      env:
+        BROWSERBASE_API_KEY: ${{ secrets.BROWSERBASE_API_KEY || 'mock-api-key' }}
+        BROWSERBASE_PROJECT_ID: ${{ secrets.BROWSERBASE_PROJECT_ID || 'mock-project-id' }}
+        MODEL_API_KEY: ${{ secrets.MODEL_API_KEY || 'mock-model-key' }}
+        STAGEHAND_API_URL: ${{ secrets.STAGEHAND_API_URL || 'http://localhost:3000' }}
+    
+    - name: Upload regression test results
+      uses: actions/upload-artifact@v4
+      if: always()
+      with:
+        name: regression-test-results
+        path: junit-regression.xml
+    
+    - name: Upload coverage data
+      uses: actions/upload-artifact@v4
+      if: always()
+      with:
+        name: coverage-data-regression
+        path: |
+          .coverage
+          coverage.xml
+
   test-e2e:
     name: End-to-End Tests
     runs-on: ubuntu-latest