Merge remote-tracking branch 'origin/main' into docker-blackwell-build

Three conflicts, all where main rewrote code this branch had also touched:

- .github/workflows/studio-backend-ci.yml path filter: kept both sides,
  so docker/** still triggers Backend CI and main's install.sh,
  install.ps1 and scripts/** triggers come along too.
- The same workflow's shell-test step and tests/run_all.sh: took main's
  directory discovery over this branch's hand-written file lists, which
  had drifted. tests/studio/test_ci_shell_suite_coverage.py passes.
- studio/install_llama_prebuilt.py: took main's delegation of
  _os_error_messages and is_busy_lock_error to prebuilt_core and kept
  this branch's is_cross_device_error, which the EXDEV copy-and-remove
  fallback still calls. BusyInstallConflict is already the prebuilt_core
  class here, so the delegated isinstance check is unchanged.

.github/workflows/cross-platform-parity-ci.yml

@@ -1,18 +1,16 @@
 # SPDX-License-Identifier: AGPL-3.0-only
 # Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
 
-# Runs installer parity and autostart opt-out tests on Windows and macOS.
+# Runs installer parity and autostart opt-out tests across all three platforms.
 #
-# Why: that test is the guard that install.sh and install.ps1 stay in
-# sync, but today it only runs on ubuntu-latest (auto-discovered by
-# studio-backend-ci.yml's "Repo tests (CPU)" job). The test reads both
-# installer scripts, and on Windows Path.read_text() defaults to the
-# cp1252 locale encoding, so a non-cp1252 byte in install.sh (it already
-# contains a U+274C) raises UnicodeDecodeError there even though Linux and
-# macOS default to UTF-8. The reads were pinned to encoding="utf-8" in
-# #6166; this job keeps that from silently regressing by exercising the
-# test on the platforms it claims parity for. Pure pytest, no GPU,
-# sub-second, so the matrix is cheap.
+# Why: the parity test guards that install.sh and install.ps1 stay in sync.
+# It originally ran only on ubuntu-latest through studio-backend-ci.yml.
+# On Windows, Path.read_text() defaults to the cp1252 locale encoding, so a
+# non-cp1252 byte in install.sh raises UnicodeDecodeError even though Linux
+# and macOS default to UTF-8. The reads were pinned to encoding="utf-8" in
+# #6166; this matrix keeps that from silently regressing. Pure pytest, no GPU,
+# sub-second, so the matrix is cheap. Linux also runs the POSIX rollback test
+# under dash, matching the supported curl-to-sh installer path.
 
 name: Cross-platform parity
 
@@ -23,6 +21,8 @@ on:
       - 'install.ps1'
       - 'tests/test_installer_skip_autostart.py'
       - 'tests/python/test_cross_platform_parity.py'
+      - 'tests/sh/test_install_rollback_lifecycle.sh'
+      - 'tests/studio/test_install_rollback_lifecycle.ps1'
       - '.github/workflows/cross-platform-parity-ci.yml'
   push:
     branches: [main]
@@ -31,6 +31,8 @@ on:
       - 'install.ps1'
       - 'tests/test_installer_skip_autostart.py'
       - 'tests/python/test_cross_platform_parity.py'
+      - 'tests/sh/test_install_rollback_lifecycle.sh'
+      - 'tests/studio/test_install_rollback_lifecycle.ps1'
       - '.github/workflows/cross-platform-parity-ci.yml'
   workflow_dispatch:
 
@@ -47,7 +49,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [windows-latest, macos-latest]
+        os: [ubuntu-latest, windows-latest, macos-latest]
     runs-on: ${{ matrix.os }}
     timeout-minutes: 10
     steps:
@@ -67,3 +69,10 @@ jobs:
           tests/python/test_cross_platform_parity.py
           tests/test_installer_skip_autostart.py
           -q
+      - name: PowerShell rollback lifecycle tests
+        if: runner.os == 'Windows'
+        shell: pwsh
+        run: pwsh -NoProfile -File tests/studio/test_install_rollback_lifecycle.ps1
+      - name: POSIX rollback lifecycle tests
+        if: runner.os == 'Linux'
+        run: sh tests/sh/test_install_rollback_lifecycle.sh

.github/workflows/studio-backend-ci.yml

@@ -33,6 +33,13 @@ on:
       # The validate_studio_features.py step below guards docker/jupyter and the
       # docker notebook helpers, so a docker-only change must trigger this CI.
       - 'docker/**'
+      # The root installers: tests/sh/*.sh and tests/studio/install/* assert
+      # against these two files, so a change here must run the suite that
+      # covers it. Without them an install-only edit (the shape most AMD/ROCm
+      # routing fixes take) skipped Backend CI entirely.
+      - 'install.sh'
+      - 'install.ps1'
+      - 'scripts/**'
       - 'pyproject.toml'
       - '.github/workflows/studio-backend-ci.yml'
   push:
@@ -196,6 +203,7 @@ jobs:
             --ignore=tests/sh \
             --ignore=tests/studio/test_hardware_dispatch_matrix.py \
             --ignore=tests/studio/test_is_mlx_dispatch_gate.py \
+            --ignore=tests/studio/test_xpu_spoof_pipeline.py \
             --ignore=tests/vllm_compat \
             --ignore=tests/version_compat \
             -m 'not server and not e2e' \
@@ -208,39 +216,45 @@ jobs:
         env:
           PYTHONPATH: ${{ github.workspace }}/studio
           UNSLOTH_COMPILE_DISABLE: '1'
-        # These two files mutate hardware.py module globals at runtime
-        # via the spoof fixtures, which leaks state into any other test
-        # that imports hardware. Run them in their own pytest invocation
-        # so the leak does not cross file boundaries.
+        # These files mutate hardware.py module globals at runtime via the
+        # spoof fixtures (CUDA/ROCm/XPU/MLX/CPU), which leaks state into any
+        # other test that imports hardware. Run them in their own pytest
+        # invocation so the leak does not cross file boundaries.
         run: |
           python -m pytest -q --tb=short \
             tests/studio/test_hardware_dispatch_matrix.py \
-            tests/studio/test_is_mlx_dispatch_gate.py
+            tests/studio/test_is_mlx_dispatch_gate.py \
+            tests/studio/test_xpu_spoof_pipeline.py
 
       - name: Shell installer tests
-        # Subset that does not depend on a writable / pristine install.sh
-        # tree; test_install_host_defaults.sh checks install.ps1 layout
-        # which has drifted (separate followup).
+        # Auto-discovered rather than allowlisted. The old hardcoded list had
+        # silently fallen seven files behind tests/run_all.sh, including
+        # test_strixhalo_wsl_reroute.sh -- the only shell coverage of the ROCm
+        # WSL reroute -- so that suite never ran on a PR. Skips are explicit,
+        # each with a reason, and tests/studio/test_ci_shell_suite_coverage.py
+        # fails if this step stops discovering the directory or the skip list
+        # grows without one.
+        #
+        # Skipped:
+        #   test_install_host_defaults.sh: asserts an install.ps1 layout that
+        #     has drifted (separate followup).
+        #   test_install_rollback_lifecycle.sh: already runs on both platforms
+        #     in cross-platform-parity-ci.yml.
         run: |
           set -e
-          for s in \
-              tests/sh/test_get_torch_index_url.sh \
-              tests/sh/test_mac_intel_compat.sh \
-              tests/sh/test_node_decision.sh \
-              tests/sh/test_studio_home_node_dir.sh \
-              tests/sh/test_system_node_readonly.sh \
-              tests/sh/test_nvcc_meets_llama_minimum.sh \
-              tests/sh/test_resolve_cuda_archs.sh \
-              tests/sh/test_select_cuda_jit_tools.sh \
-              tests/sh/test_tauri_install_exit_order.sh \
-              tests/sh/test_torch_constraint.sh \
-              tests/sh/test_torch_flavor.sh \
-              tests/sh/test_with_llama_cpp_dir_flag.sh \
-              tests/sh/test_with_llama_cpp_dir_link_behavior.sh; do
+          skip="test_install_host_defaults.sh test_install_rollback_lifecycle.sh"
+          found=0
+          for s in tests/sh/test_*.sh; do
+              case " $skip " in
+                  *" $(basename "$s") "*) echo "skipping $s (see workflow comment)"; continue ;;
+              esac
+              found=$((found + 1))
               echo "::group::$s"
               bash "$s"
               echo "::endgroup::"
           done
+          [ "$found" -gt 0 ] || { echo "::error::no shell tests discovered under tests/sh"; exit 1; }
+          echo "ran $found shell installer test files"
 
       - name: Docker JupyterLab/notebook feature validation
         # Named validate_studio_features.py (not test_*.py) so pytest skips it;

.github/workflows/studio-ui-smoke.yml

@@ -231,12 +231,69 @@ jobs:
           mkdir -p logs/playwright_extra
           python tests/studio/playwright_extra_ui.py
 
+      - name: UI font size scaling regression (Playwright)
+        env:
+          BASE_URL: http://127.0.0.1:18894
+          STUDIO_PW: ${{ env.STUDIO_EXTRA_NEW_PW }}
+          PW_ART_DIR: logs/playwright_fontscale
+        run: |
+          mkdir -p logs/playwright_fontscale
+          python tests/studio/playwright_ui_font_scale.py
+
       - name: Stop second Unsloth
         if: always()
         run: |
           kill "${STUDIO_EXTRA_PID}" 2>/dev/null || true
           sleep 2
 
+      # Model-picker per-model-config regression (PR #7207 re-land of #6647).
+      # Fourth Unsloth on its own port; loads the tiny GGUF and drives the
+      # picker's run-settings surface: Context Length persists across a reload,
+      # Reset clears the stored override (never pins it), and the infra models
+      # (RAG embedder + llama.cpp probe) stay hidden from the picker.
+      - name: Reset auth + boot Unsloth for model-config tests (port 18898)
+        run: |
+          unsloth studio reset-password
+          mkdir -p logs
+          UNSLOTH_API_ONLY=1 unsloth studio -H 127.0.0.1 -p 18898 \
+            > logs/studio_modelcfg.log 2>&1 &
+          echo "STUDIO_MODELCFG_PID=$!" >> "$GITHUB_ENV"
+
+      - name: Wait for /api/health on 18898
+        run: |
+          for i in $(seq 1 180); do
+            if curl -fs "http://127.0.0.1:18898/api/health" > /tmp/health4.json; then
+              jq -e '.status == "healthy"' /tmp/health4.json && break
+            fi
+            sleep 1
+          done
+          jq -e '.status == "healthy"' /tmp/health4.json
+
+      - name: Pass bootstrap pw for model-config test
+        run: |
+          NEW="CIModelCfg-$(python -c 'import secrets; print(secrets.token_urlsafe(16))')"
+          echo "::add-mask::$NEW"
+          echo "STUDIO_MODELCFG_NEW_PW=$NEW" >> "$GITHUB_ENV"
+
+      - name: Drive model-picker per-model-config with Playwright
+        env:
+          BASE_URL: http://127.0.0.1:18898
+          STUDIO_NEW_PW: ${{ env.STUDIO_MODELCFG_NEW_PW }}
+          PW_ART_DIR: logs/playwright_modelcfg
+          STUDIO_UI_STRICT: '1'
+          GGUF_REPO: ${{ env.GGUF_REPO }}
+          GGUF_VARIANT: ${{ env.GGUF_VARIANT }}
+          STUDIO_MODEL_HINT: gemma-3-270m
+        run: |
+          mkdir -p logs/playwright_modelcfg
+          python tests/studio/playwright_model_config.py
+
+      - name: Stop fourth Unsloth
+        if: always()
+        run: |
+          kill "${STUDIO_MODELCFG_PID}" 2>/dev/null || true
+          sleep 2
+
       # IME + multilingual paste regression (issue #5318 / PR #5327).
       # Third Unsloth on its own port so a hang here cannot poison the
       # earlier UI tests. No GGUF -- the bug surface is the composer.
@@ -297,12 +354,15 @@ jobs:
           path: |
             logs/studio.log
             logs/studio_extra.log
+            logs/studio_modelcfg.log
             logs/studio_ime.log
             logs/install.log
             logs/server-logs/
             logs/playwright
             logs/playwright-permissions-*
             logs/playwright_extra
+            logs/playwright_fontscale
+            logs/playwright_modelcfg
             logs/playwright_ime
             logs/studio-permissions-*.log
           retention-days: 7