[CI] n8n-automation-gpt-oss / lemonade-chat-gpt-oss-120b-windows failed on halo (windows)

[github-actions]

This issue was opened automatically by the Test Playbooks workflow after the test lemonade-chat-gpt-oss-120b-windows failed on the main branch.

Failure scope

• Playbook: n8n-automation-gpt-oss
• Test id: lemonade-chat-gpt-oss-120b-windows
• Device: halo
• Operating system: windows
• Runner labels: self-hosted, Windows, halo
• Runner name: xsj-aimlab-halo-0
• Commit: 5a22a31a3eb737edd92dfc76328b87983433199f
• Workflow run: https://github.com/amd/playbooks/actions/runs/25470865068

Hardware / OS to use to reproduce

Run the failing test on a machine that matches the runner labels above (OS = windows, device = halo). The repo's self-hosted runners already advertise these labels; if you reproduce locally, use the same OS family and the same AMD device class.

How to dispatch the same test from CI

Re-run only the failing playbook on the same matrix entry by triggering the workflow with the playbook id:

gh workflow run test-playbooks.yml --repo amd/playbooks -f playbook_id=n8n-automation-gpt-oss

The workflow's matrix narrows down to this (device, platform) combination automatically based on the playbook's tested_platforms.

How to run just this test locally

python .github/scripts/run_playbook_tests.py --playbook n8n-automation-gpt-oss --platform windows --device halo

The runner extracts test blocks from playbooks/*/n8n-automation-gpt-oss/README.md (the failing block starts around line 257).

Failing test (verbatim from the README)

• Timeout: 1200s

$ErrorActionPreference = "Stop"

# Wait for server to come up
$modelsJson = $null
for ($i=0; $i -lt 120; $i++) {
  $modelsJson = curl.exe -s --max-time 2 http://127.0.0.1:13305/api/v1/models
  if ($modelsJson) { break }
  Start-Sleep -Seconds 1
}
if (-not $modelsJson) { throw "Lemonade server not ready on http://127.0.0.1:13305" }
Write-Host "OK: Lemonade server is responding"

# Now that the server is responding, check if model is downloaded in Lemonade (robust JSON parse)
$parsed = $modelsJson | ConvertFrom-Json
$entry  = $parsed.data | Where-Object { $_.id -eq "gpt-oss-120b-mxfp-GGUF" } | Select-Object -First 1
if (-not $entry) { throw "Model gpt-oss-120b-mxfp-GGUF is not present in Lemonade /api/v1/models." }
if (-not $entry.downloaded) { throw "Model gpt-oss-120b-mxfp-GGUF is present but not downloaded in Lemonade. Please download it." }
Write-Host "OK: gpt-oss-120b-mxfp-GGUF model is downloaded in Lemonade"

# Model chat test
$body = @{
  model = "gpt-oss-120b-mxfp-GGUF"
  messages = @(@{ role = "user"; content = "Reply with exactly: OK" })
  temperature = 0
  max_tokens = 32
} | ConvertTo-Json -Depth 5

$tmpBody = Join-Path $env:TEMP "lemonade-chat-body.json"
[System.IO.File]::WriteAllText($tmpBody, $body, [System.Text.UTF8Encoding]::new($false))

try {
  $out = curl.exe -sS --fail-with-body --max-time 300 http://127.0.0.1:13305/api/v1/chat/completions `
  -H "Content-Type: application/json" `
  --data-binary "@$tmpBody"
  if (-not $out) { throw "Empty response from Lemonade chat/completions" }
}
finally {
  Remove-Item  $tmpBody -Force -ErrorAction SilentlyContinue
}

Result

• Exit code: 1

stderr (last lines)

Lemonade server not ready on http://127.0.0.1:13305
At line:10 char:25
+ ... delsJson) { throw "Lemonade server not ready on http://127.0.0.1:1330 ...
+                 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    + CategoryInfo          : OperationStopped: (Lemonade server...127.0.0.1:13305:String) [], RuntimeException
    + FullyQualifiedErrorId : Lemonade server not ready on http://127.0.0.1:13305
 

---

This issue is opened and deduplicated by .github/scripts/create_failure_issues.py. Close it once the failure is fixed; subsequent failures with the same scope will reopen a fresh issue.

[github-actions]

Test failed again on a subsequent CI run.

• Workflow run: https://github.com/amd/playbooks/actions/runs/25470865068
• Commit: 5a22a31a3eb737edd92dfc76328b87983433199f
• Runner: xsj-aimlab-halo-0 (self-hosted, Windows, halo)

[github-actions]

Test failed again on a subsequent CI run.

• Workflow run: https://github.com/amd/playbooks/actions/runs/25531561294
• Commit: bba38dfe1f3535aed4bdc16add29c15340751e20
• Runner: xsj-aimlab-halo-0 (self-hosted, Windows, halo)

[github-actions]

Test failed again on a subsequent CI run.

• Workflow run: https://github.com/amd/playbooks/actions/runs/25587850188
• Commit: bba38dfe1f3535aed4bdc16add29c15340751e20
• Runner: xsj-aimlab-halo-0 (self-hosted, Windows, halo)

[github-actions]

Test failed again on a subsequent CI run.

• Workflow run: https://github.com/amd/playbooks/actions/runs/25707714875
• Commit: bba38dfe1f3535aed4bdc16add29c15340751e20
• Runner: xsj-aimlab-halo-0 (self-hosted, Windows, halo)

[sreeram-11]

The Lemonade server was not running on the Windows Halo runner xsj-aimlab-halo-0. The issue was resolved after manually logging into the runner and starting the Lemonade server.