Fix Windows Cookbook background tasks, exit statuses, and empty SSH logs wrapper (#1389)

This commit consolidates all Windows Cookbook background fixes into a single comprehensive commit based on the latest main branch.

Key fixes included:
1. React looksSuccessful Mismatch: Append 'DOWNLOAD_OK' for pip install commands in routes/cookbook_routes.py.
2. Local Windows SSH Wrapper & Log Directory Mismatch: Bypassed ssh wrappers and dynamically selected odysseus-tmux logs for local tasks in static/js/cookbookRunning.js.
3. WSL Bash Filtration: Filtered out the WSL bash stub at C:\Windows\System32\bash.exe in core/platform_compat.py.
4. Drive-Colon Path Normalization: Replaced .as_posix() with git_bash_path() in routes/shell_routes.py and src/bg_jobs.py.
5. GGUF-Only Hardware Fitting: Restructured local Windows recommendations to rank GGUF only in services/hwfit/fit.py.
6. Safe Win32 Process Liveness Probe: Replaced os.kill(pid, 0) with a safe Win32 API probe using GetExitCodeProcess in core/platform_compat.py.
7. Prebuilt llama-cpp-python Wheels: Supply the CPU extra index during compilation failure fallback.
8. Enforce UTF-8 log encoding: Set PYTHONIOENCODING=utf-8 on Windows bootstrap runners.
9. Fix Linux Llama.cpp Build script syntax error in routes/cookbook_helpers.py.
10. Page Reload Status Check: Run sys.executable instead of 'python3' to bypass Microsoft Store execution stubs on local Windows hosts.
11. Llama.cpp serve build bypass: Bypassed cmake compilation checks on local Windows and verified python bindings directly.
12. Serve Command Path Validation: Masked safe GGUF path printf subshells '' inside the serve command validator.
13. CPU Mismatch Diagnostics: Intercepted AVX2-lacking '0xc000001d' (Illegal Instruction) crashes in static/js/cookbook-diagnosis.js and guided users to Ollama.
14. Windows Pytest stability: Fixed stub import leakage in test files.

routes/cookbook_helpers.py

@@ -206,12 +206,16 @@ def _pip_install_fallback_chain(package: str, *, python_cmd: str = "python3 -m p
     exit code is preserved (no ``| tail`` masking) and the last 5 lines of
     pip output appear in the Cookbook log on failure.
     """
+    from core.platform_compat import IS_WINDOWS
     upgrade_flag = " -U" if upgrade else ""
     # Shell-quote the package spec: an extras spec like ``llama-cpp-python[server]``
     # contains brackets that bash would treat as a glob, so it must be quoted
     # before being embedded in the install command. Plain names (e.g.
     # ``huggingface_hub``) are returned unchanged by ``shlex.quote``.
     pkg = shlex.quote(package)
+    if IS_WINDOWS and "llama-cpp-python" in package:
+        pkg += " --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu"
+
     base = _pip_install_attempt(f"{python_cmd} install -q{upgrade_flag} {pkg}")
     user = _pip_install_attempt(f"{python_cmd} install --user --break-system-packages -q{upgrade_flag} {pkg}")
     # Derive the python executable for the venv detection check.
@@ -525,6 +529,7 @@ def _validate_serve_cmd(v: str | None) -> str | None:
     # Backticks and raw newlines are never legitimate here.
     if any(c in v for c in ("`", "\n", "\r")):
         raise HTTPException(400, "Invalid characters in cmd")
+
     # Known GGUF launcher prelude → validate the serve invocation(s) it guards.
     m = _GGUF_PRELUDE_RE.match(v)
     if m:
@@ -533,9 +538,19 @@ def _validate_serve_cmd(v: str | None) -> str | None:
         for part in rest.split("||"):
             _check_serve_binary(part.strip())
         return v
+
     # Otherwise: a single invocation — no shell metacharacters allowed.
+    # Temporarily replace safe $(printf %s ...) expressions with a placeholder
+    # to avoid triggering the metacharacter/command-injection checks.
+    cleaned_v = v
+    printf_matches = list(re.finditer(r"\$\(\s*printf\s+%s\s+([^\n()]*?)\)", v))
+    for match in printf_matches:
+        inner = match.group(1)
+        if not any(c in inner for c in (";", "&&", "||", "$(", "`")):
+            cleaned_v = cleaned_v.replace(match.group(0), "/placeholder/safe/path.gguf")
+
     # (`$(` was the original intent; bare `$` is fine for shell-safe paths.)
-    if any(c in v for c in (";", "&&", "||", "$(")):
+    if any(c in cleaned_v for c in (";", "&&", "||", "$(")):
         raise HTTPException(400, "Invalid characters in cmd")
     _check_serve_binary(v)
     return v

routes/cookbook_routes.py

@@ -22,6 +22,7 @@ from core.platform_compat import (
     IS_WINDOWS,
     detached_popen_kwargs,
     find_bash,
+    git_bash_path,
     kill_process_tree,
     pid_alive,
     safe_chmod,
@@ -175,6 +176,7 @@ def setup_cookbook_routes() -> APIRouter:
         safe_chmod(key_path.with_suffix(".pub"), 0o644)
         return {"ok": True, "public_key": _read_cookbook_public_key()}
 
+
     def _needs_binary(cmd: str, binary: str) -> bool:
         return bool(re.search(rf"(^|[\s;&|()]){re.escape(binary)}($|[\s;&|()])", cmd or ""))
 
@@ -235,8 +237,8 @@ def setup_cookbook_routes() -> APIRouter:
             # POSIX form + shell-quoting so drive paths / spaces survive.
             inner = TMUX_LOG_DIR / f"{session_id}_run.sh"
             inner.write_text("\n".join(bash_lines) + "\n", encoding="utf-8")
-            lp = shlex.quote(log_path.as_posix())
-            ip = shlex.quote(inner.as_posix())
+            lp = shlex.quote(git_bash_path(log_path))
+            ip = shlex.quote(git_bash_path(inner))
             script_path = TMUX_LOG_DIR / f"{session_id}.sh"
             script_path.write_text(
                 f"bash {ip} > {lp} 2>&1\n",
@@ -352,6 +354,8 @@ def setup_cookbook_routes() -> APIRouter:
             ps_lines = []
             ps_lines.append('$sessionDir = "$env:TEMP\\odysseus-sessions"')
             ps_lines.append('New-Item -ItemType Directory -Force -Path $sessionDir | Out-Null')
+            ps_lines.append('$env:PYTHONIOENCODING = "utf-8"')
+            ps_lines.append('$env:PYTHONUTF8 = "1"')
             if req.hf_token:
                 ps_lines.append(f"$env:HF_TOKEN = '{_ps_squote(req.hf_token)}'")
             if req.env_prefix:
@@ -851,6 +855,16 @@ def setup_cookbook_routes() -> APIRouter:
             in_venv=sys.prefix != sys.base_prefix,
         )
         is_pip_install = bool(req.cmd and "pip install" in req.cmd)
+        remote = req.remote_host
+        is_windows = req.platform == "windows"
+        local_windows = IS_WINDOWS and not remote
+        if is_windows or local_windows:
+            if req.cmd.startswith("python3 "):
+                req.cmd = "python " + req.cmd[len("python3 "):]
+        if is_pip_install and ("llama-cpp-python" in req.cmd or "llama_cpp" in req.cmd) and (is_windows or local_windows):
+            if "--extra-index-url" not in req.cmd:
+                req.cmd += " --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu"
+
         if is_pip_install:
             # Keep big dependency wheel builds (vLLM, …) off the home filesystem's
             # pip cache so they don't fail mid-build with "No space left" (#1219)
@@ -908,6 +922,8 @@ def setup_cookbook_routes() -> APIRouter:
             ps_lines = []
             ps_lines.append('$sessionDir = "$env:TEMP\\odysseus-sessions"')
             ps_lines.append('New-Item -ItemType Directory -Force -Path $sessionDir | Out-Null')
+            ps_lines.append('$env:PYTHONIOENCODING = "utf-8"')
+            ps_lines.append('$env:PYTHONUTF8 = "1"')
             if req.hf_token:
                 ps_lines.append(f"$env:HF_TOKEN = '{_ps_squote(req.hf_token)}'")
             if req.gpus:
@@ -926,7 +942,7 @@ def setup_cookbook_routes() -> APIRouter:
                 ps_lines.append('try { python -c "import llama_cpp" 2>$null } catch {}')
                 ps_lines.append('if ($LASTEXITCODE -ne 0) {')
                 ps_lines.append('  Write-Host "Installing llama-cpp-python..."')
-                ps_lines.append('  python -m pip install llama-cpp-python[server]')
+                ps_lines.append('  python -m pip install llama-cpp-python[server] --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu')
                 ps_lines.append('}')
             elif "vllm" in req.cmd:
                 ps_lines.append('Write-Host "ERROR: vLLM is not supported on Windows. Use Ollama or llama.cpp instead."')
@@ -1001,45 +1017,57 @@ def setup_cookbook_routes() -> APIRouter:
                 # ollama is found (otherwise macOS falls back to a slow source build).
                 # /opt/homebrew = Apple Silicon, /usr/local = Intel; harmless on Linux.
                 runner_lines.append('export PATH="$HOME/.local/bin:$HOME/bin:$HOME/llama.cpp/build/bin:/opt/homebrew/bin:/usr/local/bin:$PATH"')
-                runner_lines.append('if [ -d /data/data/com.termux ]; then')
-                runner_lines.append('  # Termux: no native build — use the Python bindings (CPU).')
-                runner_lines.append('  if ! python3 -c "import llama_cpp" 2>/dev/null; then')
-                runner_lines.append('    pkg install -y cmake 2>/dev/null')
-                runner_lines.append('    pip install numpy diskcache jinja2 2>/dev/null')
-                runner_lines.append('    CMAKE_ARGS="-DGGML_BLAS=OFF -DGGML_LLAMAFILE=OFF" pip install \'llama-cpp-python[server]\' --no-build-isolation --no-cache-dir 2>&1 || true')
-                runner_lines.append('  fi')
-                runner_lines.append('elif ! command -v llama-server &>/dev/null; then')
-                runner_lines.append('  echo "Native llama-server not found — building from source (one-time, may take a few minutes)..."')
-                runner_lines.append('  mkdir -p ~/bin')
-                runner_lines.append('  cd ~ && [ -d llama.cpp ] || git clone --depth 1 https://github.com/ggml-org/llama.cpp')
-                # Build with the right accelerator: Metal on macOS (llama.cpp
-                # enables it automatically, no flag), CUDA on Linux when present,
-                # else a plain CPU build. nproc is Linux-only — fall back to
-                # `sysctl hw.ncpu` on macOS. (Tip: `brew install llama.cpp` ships
-                # a prebuilt llama-server and skips this whole source build.)
-                runner_lines.append('  NPROC="$(nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 4)"')
-                runner_lines.append('  if [ "$(uname -s)" = "Darwin" ]; then')
-                runner_lines.append('    command -v cmake >/dev/null 2>&1 || echo "WARNING: cmake not found — install it with: brew install cmake (or: brew install llama.cpp for a prebuilt llama-server)."')
-                # Start from a clean cache: a prior failed configure (e.g. a CUDA
-                # attempt) poisons build/CMakeCache.txt, so a plain `cmake -B build`
-                # would reuse the bad settings and fail again. CMAKE_BUILD_TYPE is
-                # explicit so the binary is optimized (Metal auto-enables on macOS).
-                runner_lines.append('    cd ~/llama.cpp && rm -rf build && cmake -B build -DCMAKE_BUILD_TYPE=Release \\')
-                runner_lines.append('      && cmake --build build -j"$NPROC" --target llama-server \\')
-                runner_lines.append('      && ln -sf ~/llama.cpp/build/bin/llama-server ~/bin/llama-server')
-                runner_lines.append('  else')
-                _append_llama_cpp_linux_accel_build_lines(runner_lines)
-                runner_lines.append('  fi')
-                runner_lines.append('  # If the native build failed, fall back to the Python bindings.')
-                runner_lines.append('  if ! command -v llama-server &>/dev/null && ! python3 -c "import llama_cpp" 2>/dev/null; then')
-                runner_lines.append('    echo "llama-server build failed — installing Python bindings as fallback..."')
-                runner_lines.append(f"    {_pip_install_fallback_chain('llama-cpp-python[server]', python_cmd='pip')} || true")
-                runner_lines.append('  fi')
-                runner_lines.append('  if ! command -v llama-server &>/dev/null && ! python3 -c "import llama_cpp" 2>/dev/null; then')
-                runner_lines.append('    echo "ERROR: llama.cpp serving is not available after install/build attempts."')
-                runner_lines.append('    ODYSSEUS_PREFLIGHT_EXIT=127')
-                runner_lines.append('  fi')
-                runner_lines.append('fi')
+                if local_windows:
+                    # LOCAL Windows: no native source compilation (no cmake/compiler on Git Bash).
+                    # Just check python bindings (using native `python` binary) and fall back to pip install.
+                    runner_lines.append('if ! command -v llama-server &>/dev/null && ! python -c "import llama_cpp" 2>/dev/null; then')
+                    runner_lines.append('  echo "llama-server not found — installing Python bindings..."')
+                    runner_lines.append(f"  {_pip_install_fallback_chain('llama-cpp-python[server]', python_cmd='python')} || true")
+                    runner_lines.append('fi')
+                    runner_lines.append('if ! command -v llama-server &>/dev/null && ! python -c "import llama_cpp" 2>/dev/null; then')
+                    runner_lines.append('  echo "ERROR: llama.cpp serving is not available after install attempts."')
+                    runner_lines.append('  ODYSSEUS_PREFLIGHT_EXIT=127')
+                    runner_lines.append('fi')
+                else:
+                    runner_lines.append('if [ -d /data/data/com.termux ]; then')
+                    runner_lines.append('  # Termux: no native build — use the Python bindings (CPU).')
+                    runner_lines.append('  if ! python3 -c "import llama_cpp" 2>/dev/null; then')
+                    runner_lines.append('    pkg install -y cmake 2>/dev/null')
+                    runner_lines.append('    pip install numpy diskcache jinja2 2>/dev/null')
+                    runner_lines.append('    CMAKE_ARGS="-DGGML_BLAS=OFF -DGGML_LLAMAFILE=OFF" pip install \'llama-cpp-python[server]\' --no-build-isolation --no-cache-dir 2>&1 || true')
+                    runner_lines.append('  fi')
+                    runner_lines.append('elif ! command -v llama-server &>/dev/null; then')
+                    runner_lines.append('  echo "Native llama-server not found — building from source (one-time, may take a few minutes)..."')
+                    runner_lines.append('  mkdir -p ~/bin')
+                    runner_lines.append('  cd ~ && [ -d llama.cpp ] || git clone --depth 1 https://github.com/ggml-org/llama.cpp')
+                    # Build with the right accelerator: Metal on macOS (llama.cpp
+                    # enables it automatically, no flag), CUDA on Linux when present,
+                    # else a plain CPU build. nproc is Linux-only — fall back to
+                    # `sysctl hw.ncpu` on macOS. (Tip: `brew install llama.cpp` ships
+                    # a prebuilt llama-server and skips this whole source build.)
+                    runner_lines.append('  NPROC="$(nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 4)"')
+                    runner_lines.append('  if [ "$(uname -s)" = "Darwin" ]; then')
+                    runner_lines.append('    command -v cmake >/dev/null 2>&1 || echo "WARNING: cmake not found — install it with: brew install cmake (or: brew install llama.cpp for a prebuilt llama-server)."')
+                    # Start from a clean cache: a prior failed configure (e.g. a CUDA
+                    # attempt) poisons build/CMakeCache.txt, so a plain `cmake -B build`
+                    # would reuse the bad settings and fail again. CMAKE_BUILD_TYPE is
+                    # explicit so the binary is optimized (Metal auto-enables on macOS).
+                    runner_lines.append('    cd ~/llama.cpp && rm -rf build && cmake -B build -DCMAKE_BUILD_TYPE=Release \\')
+                    runner_lines.append('      && cmake --build build -j"$NPROC" --target llama-server \\')
+                    runner_lines.append('      && ln -sf ~/llama.cpp/build/bin/llama-server ~/bin/llama-server')
+                    runner_lines.append('  else')
+                    _append_llama_cpp_linux_accel_build_lines(runner_lines)
+                    runner_lines.append('  fi')
+                    # If the native build failed, fall back to the Python bindings.
+                    runner_lines.append('  if ! command -v llama-server &>/dev/null && ! python3 -c "import llama_cpp" 2>/dev/null; then')
+                    runner_lines.append('    echo "llama-server build failed — installing Python bindings as fallback..."')
+                    runner_lines.append(f"    {_pip_install_fallback_chain('llama-cpp-python[server]', python_cmd='pip')} || true")
+                    runner_lines.append('  fi')
+                    runner_lines.append('  if ! command -v llama-server &>/dev/null && ! python3 -c "import llama_cpp" 2>/dev/null; then')
+                    runner_lines.append('    echo "ERROR: llama.cpp serving is not available after install/build attempts."')
+                    runner_lines.append('    ODYSSEUS_PREFLIGHT_EXIT=127')
+                    runner_lines.append('  fi')
+                    runner_lines.append('fi')
             elif "ollama" in req.cmd:
                 handled_ollama_serve = True
                 _ollama_default_host = "0.0.0.0" if remote else "127.0.0.1"
@@ -2076,7 +2104,11 @@ def setup_cookbook_routes() -> APIRouter:
                 "inc=os.path.isdir(blobs) and any(x.endswith('.incomplete') for x in os.listdir(blobs));"
                 "sys.exit(0 if ok and not inc else 1)"
             )
-            cmd = ["python3", "-c", py, repo_id]
+            if not remote_host:
+                import sys
+                cmd = [sys.executable, "-c", py, repo_id]
+            else:
+                cmd = ["python3", "-c", py, repo_id]
             try:
                 if remote_host:
                     ssh_base = ["ssh"]

routes/shell_routes.py

@@ -37,6 +37,7 @@ from core.platform_compat import (
     IS_WINDOWS,
     detached_popen_kwargs,
     find_bash,
+    git_bash_path,
 )
 
 
@@ -368,8 +369,12 @@ async def _create_shell(command: str, **kwargs):
     POSIX: /bin/sh via create_subprocess_shell (unchanged behaviour).
     Windows: prefer a real bash (Git Bash/WSL) so bash-syntax commands behave
     the same as on Linux; fall back to cmd.exe when no bash is installed.
+    Powershell commands are executed directly via cmd.exe /c to avoid quoting
+    and env variable expansion errors under Git Bash.
     """
     if IS_WINDOWS:
+        if command.strip().lower().startswith("powershell"):
+            return await asyncio.create_subprocess_shell(command, **kwargs)
         bash = find_bash()
         if bash:
             return await asyncio.create_subprocess_exec(bash, "-c", command, **kwargs)
@@ -672,8 +677,8 @@ async def _generate_win_detached(cmd: str, request: Request):
     if bash:
         script_path = TMUX_LOG_DIR / f"{session_id}.sh"
         script_path.write_text(
-            f"{cmd} > {shlex.quote(str(log_path))} 2>&1\n"
-            f"echo $? > {shlex.quote(str(exit_path))}\n",
+            f"{cmd} > {shlex.quote(git_bash_path(log_path))} 2>&1\n"
+            f"echo $? > {shlex.quote(git_bash_path(exit_path))}\n",
             encoding="utf-8",
         )
         argv = [bash, str(script_path)]