diff --git a/.github/workflows/studio-mac-ui-smoke.yml b/.github/workflows/studio-mac-ui-smoke.yml index 512af54d53..20ca247b9f 100644 --- a/.github/workflows/studio-mac-ui-smoke.yml +++ b/.github/workflows/studio-mac-ui-smoke.yml @@ -185,13 +185,14 @@ jobs: # Retry up to 3 times to absorb known macos-14 free-runner # flakes: (1) Playwright Node 24 pipeTransport.js 'Unexpected # end of JSON input' crash when the Chromium browser process - # dies mid-test, and (2) Chromium net::ERR_NO_BUFFER_SPACE - # when the runner's kernel briefly runs out of socket buffers. - # The retry FULLY resets Studio (kill, reset-password, reboot, - # wait /api/health, re-export bootstrap pw) before re-running - # the script. A real test failure (assertion / timeout) does - # NOT match either pattern so it bypasses retry and surfaces - # immediately. + # dies mid-test, (2) Chromium net::ERR_NO_BUFFER_SPACE when the + # runner's kernel briefly runs out of socket buffers, and (3) a + # goto 'interrupted by another navigation' when the SPA auth + # guard redirects mid-navigation. The retry FULLY resets Studio + # (kill, reset-password, reboot, wait /api/health, re-export + # bootstrap pw) before re-running the script. A real test failure + # (assertion / timeout) does NOT match any pattern so it bypasses + # retry and surfaces immediately. run: | mkdir -p logs/playwright attempt=1 @@ -204,8 +205,9 @@ jobs: if [ "$rc" -eq 0 ]; then break fi - if { grep -q "Unexpected end of JSON input" logs/playwright_attempt_${attempt}.log \ - || grep -q "ERR_NO_BUFFER_SPACE" logs/playwright_attempt_${attempt}.log; } \ + if { grep -q "Unexpected end of JSON input" logs/playwright_attempt_${attempt}.log \ + || grep -q "ERR_NO_BUFFER_SPACE" logs/playwright_attempt_${attempt}.log \ + || grep -q "interrupted by another navigation" logs/playwright_attempt_${attempt}.log; } \ && [ "$attempt" -lt "$max_attempts" ]; then echo "::warning::Playwright flake on attempt ${attempt}; resetting Studio and retrying..." kill "${STUDIO_PID}" 2>/dev/null || true @@ -280,8 +282,8 @@ jobs: STUDIO_UI_TURN_TIMEOUT_MS: '540000' GGUF_REPO: ${{ env.GGUF_REPO }} GGUF_VARIANT: ${{ env.GGUF_VARIANT }} - # Same flake-retry shape as "Drive the chat UI with Playwright" - # -- catches pipeTransport JSON crash and ERR_NO_BUFFER_SPACE. + # Same flake-retry shape as "Drive the chat UI with Playwright" -- catches + # pipeTransport JSON crash, ERR_NO_BUFFER_SPACE, and nav interrupts. run: | mkdir -p logs/playwright_extra attempt=1 @@ -294,8 +296,9 @@ jobs: if [ "$rc" -eq 0 ]; then break fi - if { grep -q "Unexpected end of JSON input" logs/playwright_extra_attempt_${attempt}.log \ - || grep -q "ERR_NO_BUFFER_SPACE" logs/playwright_extra_attempt_${attempt}.log; } \ + if { grep -q "Unexpected end of JSON input" logs/playwright_extra_attempt_${attempt}.log \ + || grep -q "ERR_NO_BUFFER_SPACE" logs/playwright_extra_attempt_${attempt}.log \ + || grep -q "interrupted by another navigation" logs/playwright_extra_attempt_${attempt}.log; } \ && [ "$attempt" -lt "$max_attempts" ]; then echo "::warning::Playwright flake on attempt ${attempt}; resetting Studio and retrying..." kill "${STUDIO_EXTRA_PID}" 2>/dev/null || true diff --git a/.github/workflows/studio-windows-inference-smoke.yml b/.github/workflows/studio-windows-inference-smoke.yml index c44c68278d..08a0ee782d 100644 --- a/.github/workflows/studio-windows-inference-smoke.yml +++ b/.github/workflows/studio-windows-inference-smoke.yml @@ -1338,11 +1338,19 @@ jobs: shell: pwsh run: | $ErrorActionPreference = 'Stop' + # A Program Files dir can hold a transient handle (Defender / MSBuild node) + # so Rename-Item intermittently fails with "Access is denied"; retry to ride it out. + function Rename-WithRetry($Path, $NewName) { + for ($i = 1; $i -le 6; $i++) { + try { Rename-Item -LiteralPath $Path -NewName $NewName -ErrorAction Stop; return } + catch { if ($i -eq 6) { throw }; Start-Sleep -Seconds 3 } + } + } # Rename the Visual Studio install roots (incl. the Installer that holds # vswhere.exe) so Find-VsBuildTools' vswhere + filesystem scan both miss. foreach ($d in @("$env:ProgramFiles\Microsoft Visual Studio", "${env:ProgramFiles(x86)}\Microsoft Visual Studio")) { if (Test-Path -LiteralPath $d) { - Rename-Item -LiteralPath $d -NewName ((Split-Path $d -Leaf) + '.vsoff') + Rename-WithRetry $d ((Split-Path $d -Leaf) + '.vsoff') Write-Host "Hid VS: $d" } } @@ -1351,7 +1359,7 @@ jobs: $hidden = @() foreach ($c in (Get-Command cmake -All -ErrorAction SilentlyContinue)) { if ($c.Source -and (Test-Path -LiteralPath $c.Source)) { - Rename-Item -LiteralPath $c.Source -NewName ((Split-Path $c.Source -Leaf) + '.off') + Rename-WithRetry $c.Source ((Split-Path $c.Source -Leaf) + '.off') $hidden += $c.Source Write-Host "Hid cmake: $($c.Source)" } @@ -1536,8 +1544,16 @@ jobs: shell: pwsh run: | $ErrorActionPreference = 'Stop' + # Retry the rename: a Program Files dir can hold a transient handle that + # makes Rename-Item intermittently fail with "Access is denied". + function Rename-WithRetry($Path, $NewName) { + for ($i = 1; $i -le 6; $i++) { + try { Rename-Item -LiteralPath $Path -NewName $NewName -ErrorAction Stop; return } + catch { if ($i -eq 6) { throw }; Start-Sleep -Seconds 3 } + } + } foreach ($d in @("$env:ProgramFiles\Microsoft Visual Studio", "${env:ProgramFiles(x86)}\Microsoft Visual Studio")) { - if (Test-Path -LiteralPath $d) { Rename-Item -LiteralPath $d -NewName ((Split-Path $d -Leaf) + '.vsoff'); Write-Host "Hid VS: $d" } + if (Test-Path -LiteralPath $d) { Rename-WithRetry $d ((Split-Path $d -Leaf) + '.vsoff'); Write-Host "Hid VS: $d" } } - name: Windows CUDA and ROCm prebuilts exist in unslothai/llama.cpp (what GPU users download, no VS) diff --git a/tests/studio/playwright_chat_ui.py b/tests/studio/playwright_chat_ui.py index a892d3414d..a53534acc0 100644 --- a/tests/studio/playwright_chat_ui.py +++ b/tests/studio/playwright_chat_ui.py @@ -1225,15 +1225,17 @@ with sync_playwright() as p: # ───────────────────────────────────────────────────── step("Shutdown via account menu") # Re-login with NEW2 for a valid /api/shutdown token (CLI rotation - # invalidated the old one). The stale token can make the SPA auth - # guard abort this goto with ERR_ABORTED; resolve on - # domcontentloaded and tolerate it -- the pw-field wait confirms /login. + # invalidated the old one). The stale token can make the SPA auth guard + # abort this goto with ERR_ABORTED, or redirect to the same /login URL + # ("interrupted by another navigation"); resolve on domcontentloaded and + # tolerate either -- the pw-field wait below confirms we are on /login. + _tolerated_nav = ("ERR_ABORTED", "interrupted by another navigation") try: page.goto(f"{BASE}/login", wait_until = "domcontentloaded", timeout = 60_000) except Exception as exc: - if "ERR_ABORTED" not in str(exc): + if not any(t in str(exc) for t in _tolerated_nav): raise - info(f"goto /login aborted ({exc!r}); password-field wait will confirm /login") + info(f"goto /login interrupted ({exc!r}); password-field wait will confirm /login") pw_field = page.locator("#password") pw_field.wait_for(state = "visible", timeout = 60_000) pw_field.fill(NEW2)