From d6f374082da49b3dc916907b374e5134e4ee9990 Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Wed, 29 Jul 2026 08:43:07 +0000
Subject: [PATCH] Make the Intel auto-route guard test able to fail and stop
 the ps1 harness doubling --force-cpu

test_non_vulkan_backend_suppresses_intel_auto_route ran on Linux x86_64, where
dropping the explicit_backend guard changes only a log line, so the test passed
either way. Move it to Linux ARM64 + Intel GPU, the host where the guard decides
the routed repo, and assert that value.

_run_ps1 composed the --force-cpu snippet twice: it is already inside the
normalized block the helper extracts. The substring assertion hid the duplicate.
Compose it once and compare the whole argv. setup.ps1 appends the flag once and
is unchanged.
---
 .../tests/test_install_resolve_prebuilt.py     | 13 +++++++++----
 .../tests/test_setup_llama_cpp_backend.py      | 18 ++++++++++--------
 2 files changed, 19 insertions(+), 12 deletions(-)

diff --git a/studio/backend/tests/test_install_resolve_prebuilt.py b/studio/backend/tests/test_install_resolve_prebuilt.py
index b29df53a0a..cb1ce8b63b 100644
--- a/studio/backend/tests/test_install_resolve_prebuilt.py
+++ b/studio/backend/tests/test_install_resolve_prebuilt.py
@@ -759,21 +759,26 @@ def test_route_to_vulkan_prebuilt_cpu_fallback_wins():
 @pytest.mark.parametrize("backend", ["hip", "rocm", "cpu"])
 def test_non_vulkan_backend_suppresses_intel_auto_route(monkeypatch, backend, via):
     # The selector suppresses the Intel auto-route the same way whether it arrives
-    # from the environment or from --llama-backend.
+    # from the environment or from --llama-backend. Pinned to Linux ARM64, the one
+    # host where the suppression shows up in a returned VALUE: without it the Intel
+    # auto-route fires, falls through to the ARM64 fork -> upstream reroute and
+    # hands back UPSTREAM with the fork pin dropped. On x86_64 the auto-route
+    # rewrites neither host nor repo, so only a log line differs and the same case
+    # there cannot fail.
     kwargs = {}
     if via == "env":
         monkeypatch.setenv("UNSLOTH_LLAMA_CPP_BACKEND", backend)
     else:
         kwargs["llama_backend"] = backend
-    host = _host(is_linux = True, is_x86_64 = True, has_intel_gpu = True)
+    host = _linux_arm64_vulkan_host()
 
     routed, repo, tag, persist = ilp._route_to_vulkan_prebuilt(
         host, FORK, "b9596-mix-abc", force_cpu = False, **kwargs
     )
 
     assert routed is host
-    assert repo == FORK
-    assert tag == "b9596-mix-abc"
+    assert repo == FORK, repo
+    assert tag == "b9596-mix-abc", tag
     assert persist is None
 
 
diff --git a/studio/backend/tests/test_setup_llama_cpp_backend.py b/studio/backend/tests/test_setup_llama_cpp_backend.py
index 118ec0a5ce..d9f78a684b 100644
--- a/studio/backend/tests/test_setup_llama_cpp_backend.py
+++ b/studio/backend/tests/test_setup_llama_cpp_backend.py
@@ -300,15 +300,15 @@ def test_llama_backend_source_choice_in_setup_ps1(backend, force_vulkan, expecte
 
 
 def _run_ps1(value: str | None) -> str:
-    # The override is normalized (assign + warn) at the top of the prebuilt block and
-    # applied to $prebuiltArgs lower down; compose both real snippets.
+    # One snippet, not two: NORMALIZE already spans the whole if/elseif chain up to
+    # and including the "Ignoring UNSLOTH_LLAMA_CPP_BACKEND" warn, so the --force-cpu
+    # append is inside it. Composing the apply snippet on top of it made the harness
+    # emit the flag twice while setup.ps1 appends it once.
     normalize = _ps1_search(
         r"\$llamaBackend = \$sourceLlamaBackend.*?Ignoring UNSLOTH_LLAMA_CPP_BACKEND.*?\n\s*\}",
         re.DOTALL,
     )
-    apply_flag = _ps1_search(
-        r'if \(\$llamaBackend -eq "cpu"\) \{\s*\$prebuiltArgs \+= "--force-cpu"\s*\}'
-    )
+    assert normalize.count('$prebuiltArgs += "--force-cpu"') == 1, normalize
     env = {
         k: v
         for k, v in os.environ.items()
@@ -320,7 +320,7 @@ def _run_ps1(value: str | None) -> str:
         "$prebuiltArgs = @()\n"
         '$sourceLlamaBackend = "$($env:UNSLOTH_LLAMA_CPP_BACKEND)".Trim().ToLowerInvariant()\n'
         '$sourceLegacyForceVulkan = "$($env:UNSLOTH_FORCE_VULKAN)".Trim().ToLowerInvariant()\n'
-        f'{normalize}\n{apply_flag}\n"ARGS:" + ($prebuiltArgs -join ",")'
+        f'{normalize}\n"ARGS:" + ($prebuiltArgs -join ",")'
     )
     out = subprocess.run(
         ["pwsh", "-NoProfile", "-Command", harness],
@@ -336,8 +336,10 @@ def _run_ps1(value: str | None) -> str:
 @pytest.mark.parametrize("value", ["cpu", "CPU", "Cpu", " cpu ", "CPU\t"])
 def test_ps1_backend_cpu_appends_flag(value):
     out = _run_ps1(value)
-    assert "--force-cpu" in out
-    assert "Ignoring" not in out
+    # The whole argv, not a substring: an `in` check passed while the harness was
+    # emitting --force-cpu twice. setup.ps1 appends it exactly once, and nothing
+    # else, for a cpu override.
+    assert out.strip() == "ARGS:--force-cpu"
 
 
 @_SKIP_NO_PWSH