Update msbench script and pipeline

.gitignore

@@ -1,4 +1,6 @@
 
+venv/
+.venv/
 __integration_*__/
 __pycache__/
 __test_fixtures__/

pipelines/azure-benchmarks.yml

@@ -1,8 +1,13 @@
-trigger: none
+trigger:
+  branches:
+    include:
+    - main
+
 pr: none
 
 stages:
 - stage: RunBenchmark
+  displayName: 'Run Benchmarks'
   pool:
     name: $(LINUXPOOL)
     image: $(LINUXVMIMAGE)
@@ -14,6 +19,11 @@ stages:
   - job: RunBenchmark
     displayName: 'Run Copilot Benchmarks'
     steps:
+    - task: UsePythonVersion@0
+      displayName: 'Use Python 3.14'
+      inputs:
+        versionSpec: '3.14'
+
     - task: AzureCLI@2
       displayName: 'Run Copilot Benchmarks script'
       inputs:
@@ -22,5 +32,3 @@ stages:
         scriptType: 'pscore'
         scriptLocation: 'scriptPath'
         scriptPath: $(Build.SourcesDirectory)/pipelines/scripts/Invoke-CopilotBenchmarks.ps1
-        arguments: >
-          -BuildId $(OfficialBuildId)

pipelines/scripts/Invoke-CopilotBenchmarks.ps1

@@ -1,12 +1,111 @@
+<#
+.SYNOPSIS
+    Installs MSBench CLI in a local virtual environment and runs a Copilot Azure benchmark.
+
+.DESCRIPTION
+    This script is executed by the Azure DevOps benchmark pipeline to run Azure benchmarks using the
+    github-copilot-cli agent.
+
+    The script installs MSBench CLI from the MicrosoftSweBench Azure Artifacts feed and invokes:
+    msbench-cli run --agent github-copilot-cli --benchmark <benchmark> --model <model>
+
+    MSBench CLI reference:
+    - https://github.com/devdiv-microsoft/MicrosoftSweBench/wiki
+
+.PARAMETER Benchmark
+    Benchmark identifier
+
+.PARAMETER NoWait
+    Whether to add --no-wait to the run command.
+    Default: false
+
+.EXAMPLE
+    PS> ./Invoke-CopilotBenchmarks.ps1
+
+    Runs benchmark azure with default model.
+
+.EXAMPLE
+    PS> ./Invoke-CopilotBenchmarks.ps1 -BenchmarkInstanceId azure.120 -Model "claude-sonnet-4.5-autodev-test" -NoWait
+
+    Runs benchmark azure.120 with explicit model and does not wait for completion.
+
+.LINK
+    https://github.com/devdiv-microsoft/MicrosoftSweBench/wiki
+#>
+
 param(
-    [string]$BuildId
+    [string]$Benchmark = "azure",
+    [string]$Model = "claude-sonnet-4.5-autodev-test",
+    [switch]$NoWait
 )
 
+Set-StrictMode -Version Latest
+$ErrorActionPreference = "Stop"
+
+
+if (!$Benchmark) {
+    throw "Benchmark parameter is required."
+}
+
+if (!$Model) {
+    throw "Model parameter is required."
+}
+
+$indexUrl = "https://pkgs.dev.azure.com/devdiv/_packaging/MicrosoftSweBench/pypi/simple/"
+$vaultName = "kv-msbench-eval-azuremcp"
+$secretName = "azure-eval-gh-pat"
+
+# pull the azure-eval-gh-pat secret from KeyVault using Azure CLI
+try {
+    Write-Host "Retrieving GitHub PAT from KeyVault $vaultName secret $secretName"
+    $pat = az keyvault secret show --vault-name $vaultName --name $secretName --query value -o tsv
+    if (!$pat) {
+        throw "Secret $secretName not found in KeyVault $vaultName."
+    }
+
+    $env:GITHUB_MCP_SERVER_TOKEN = $pat
+}
+catch {
+    throw "Failed to retrieve GitHub PAT from KeyVault: $_"
+}
+
+Write-Host "Benchmark: $Benchmark"
+Write-Host "Model: $Model"
+Write-Host "NoWait: $NoWait"
+
+$pythonCommand = Get-Command python
+Write-Host "Using python from: $($pythonCommand.Path). Version: $(python --version)"
+
+Write-Host "Install/upgrade pip"
+python -m pip install --upgrade pip
+
+Write-Host "Installing artifact authentication dependencies"
+python -m pip install keyring artifacts-keyring
+
+Write-Host "Checking MSBench CLI versions from feed"
+python -m pip index versions msbench-cli --index-url $indexUrl
+
+Write-Host "Installing/upgrading MSBench CLI"
+python -m pip install msbench-cli --index-url $indexUrl
+
+Write-Host "MSBench CLI version"
+& 'msbench-cli' version
+
+$runArgs = @(
+    "run",
+    "--agent", "github-copilot-cli",
+    "--benchmark", $Benchmark,
+    "--model", $Model,
+    "--env", "GITHUB_MCP_SERVER_TOKEN"
+)
 
+if ($NoWait) {
+    $runArgs += "--no-wait"
+}
 
-# Install MSBench CLI
-Write-Host "Installing keyring"
-pip install keyring artifacts-keyring
+Write-Host "Running: msbench-cli $($runArgs -join ' ')"
+& 'msbench-cli' @runArgs
 
-Write-Host "Listing key vaults in the resource group"
-az keyvault list --resource-group rg-msbench-eval-kv-azure-mcp --query "[].name" -o tsv
+if ($LASTEXITCODE -ne 0) {
+    throw "msbench-cli run failed with exit code $LASTEXITCODE"
+}