refactor(harness): remove legacy agent architecture

2026-07-22 18:02:01 +08:00
parent bc36248cd8
commit 8ee7cc0b70
148 changed files with 3091 additions and 13889 deletions
@@ -0,0 +1,168 @@
+param(
+    [string]$BaseUrl = "http://localhost:9900",
+    [string]$SessionId = "mvp-demo-interview-payment-timeout-001",
+    [string]$RequestFile = "$PSScriptRoot/../requests/payment-timeout-chat.json",
+    [string]$OutputDir = "$PSScriptRoot/../output"
+)
+
+$ErrorActionPreference = "Stop"
+
+function Test-ServiceReachable {
+    param([string]$Url)
+
+    try {
+        $request = [System.Net.WebRequest]::Create($Url)
+        $request.Method = "GET"
+        $request.Timeout = 5000
+        $response = $request.GetResponse()
+        $response.Close()
+        return $true
+    } catch [System.Net.WebException] {
+        if ($_.Exception.Response -ne $null) {
+            $_.Exception.Response.Close()
+            return $true
+        }
+        return $false
+    }
+}
+
+function Get-TraceData {
+    param($TraceResponse)
+
+    if ($TraceResponse.PSObject.Properties.Name -contains "data") {
+        return $TraceResponse.data
+    }
+    return $TraceResponse
+}
+
+function Get-SelfEvaluation {
+    param($TraceData)
+
+    if ($null -eq $TraceData -or $null -eq $TraceData.session) {
+        return $null
+    }
+    return $TraceData.session.selfEvaluation
+}
+
+function Get-ToolNames {
+    param($TraceData)
+
+    if ($null -eq $TraceData -or $null -eq $TraceData.toolInvocations) {
+        return @()
+    }
+    return @($TraceData.toolInvocations | ForEach-Object { $_.toolName } | Where-Object { $_ } | Sort-Object -Unique)
+}
+
+New-Item -ItemType Directory -Force -Path $OutputDir | Out-Null
+
+Write-Host "Running interview demo preflight..."
+Write-Host "BaseUrl: $BaseUrl"
+Write-Host "SessionId: $SessionId"
+
+if (-not (Test-ServiceReachable -Url $BaseUrl)) {
+    throw "Service is not reachable: $BaseUrl. Start the app with mvp-demo profile first: mvn spring-boot:run -Dspring-boot.run.profiles=mvp-demo"
+}
+
+$request = Get-Content -Raw -Encoding UTF8 -Path $RequestFile | ConvertFrom-Json
+$request.Id = $SessionId
+$body = $request | ConvertTo-Json -Depth 8
+
+$chatRequest = @{
+    Method = "Post"
+    Uri = "$BaseUrl/api/chat"
+    ContentType = "application/json; charset=utf-8"
+    Body = $body
+}
+$chat = Invoke-RestMethod @chatRequest
+
+$chatPath = Join-Path $OutputDir "chat-response.json"
+$chat | ConvertTo-Json -Depth 30 | Set-Content -Encoding UTF8 -Path $chatPath
+
+$runId = $chat.data.runId
+if (-not $runId) {
+    throw "Chat response did not include runId; exact trace verification cannot continue."
+}
+
+$traceRequest = @{
+    Method = "Get"
+    Uri = "$BaseUrl/api/diagnosis/$SessionId/trace?runId=$([System.Uri]::EscapeDataString($runId))"
+}
+$trace = Invoke-RestMethod @traceRequest
+
+$tracePath = Join-Path $OutputDir "trace-response.json"
+$trace | ConvertTo-Json -Depth 80 | Set-Content -Encoding UTF8 -Path $tracePath
+
+$feedbackBody = @{
+    sessionId = $SessionId
+    runId = $runId
+    feedback = "useful"
+} | ConvertTo-Json
+
+$feedbackRequest = @{
+    Method = "Post"
+    Uri = "$BaseUrl/api/feedback"
+    ContentType = "application/json; charset=utf-8"
+    Body = $feedbackBody
+}
+$feedback = Invoke-RestMethod @feedbackRequest
+
+$feedbackPath = Join-Path $OutputDir "feedback-response.json"
+$feedback | ConvertTo-Json -Depth 30 | Set-Content -Encoding UTF8 -Path $feedbackPath
+
+$traceData = Get-TraceData -TraceResponse $trace
+$selfEvaluation = Get-SelfEvaluation -TraceData $traceData
+$verifierEvaluation = $null
+if ($null -ne $selfEvaluation) {
+    $verifierEvaluation = $selfEvaluation.verifier_evaluation
+}
+
+$gatekeeperResult = $null
+$promptAudit = $null
+if ($null -ne $verifierEvaluation) {
+    $gatekeeperResult = $verifierEvaluation.gatekeeper_result
+    $promptAudit = $verifierEvaluation.prompt_audit
+}
+
+$verdict = $null
+$gatekeeperStatus = $null
+$gatekeeperRuleSetVersion = $null
+$promptAuditVersion = $null
+if ($null -ne $verifierEvaluation) {
+    $verdict = $verifierEvaluation.verdict
+}
+if ($null -ne $gatekeeperResult) {
+    $gatekeeperStatus = $gatekeeperResult.status
+    $gatekeeperRuleSetVersion = $gatekeeperResult.rule_set_version
+}
+if ($null -ne $promptAudit) {
+    $promptAuditVersion = $promptAudit.version
+}
+$toolNames = Get-ToolNames -TraceData $traceData
+$summaryPath = Join-Path $OutputDir "interview-demo-summary.json"
+
+$summary = [ordered]@{
+    sessionId = $SessionId
+    runId = $runId
+    baseUrl = $BaseUrl
+    chatSuccess = $chat.data.success
+    verdict = $verdict
+    gatekeeperStatus = $gatekeeperStatus
+    gatekeeperRuleSetVersion = $gatekeeperRuleSetVersion
+    promptAuditVersion = $promptAuditVersion
+    toolNames = $toolNames
+    paths = [ordered]@{
+        chat = $chatPath
+        trace = $tracePath
+        feedback = $feedbackPath
+        summary = $summaryPath
+    }
+}
+
+$summary | ConvertTo-Json -Depth 20 | Set-Content -Encoding UTF8 -Path $summaryPath
+
+Write-Host ""
+Write-Host "Interview demo preflight completed."
+Write-Host "Verdict: $($summary.verdict)"
+Write-Host "Gatekeeper rules: $($summary.gatekeeperRuleSetVersion)"
+Write-Host "Prompt audit: $($summary.promptAuditVersion)"
+Write-Host "Summary: $summaryPath"