studio: setup log styling#4494
Conversation
Summary of ChangesHello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly enhances the user experience during Unsloth Studio setup by standardizing and improving the terminal output. It introduces a consistent, step-based visual style for setup logs across different operating systems, making the process clearer and easier to follow. A new verbose mode provides detailed diagnostic information for advanced users, while making certain build steps optional prevents complete setup failures due to non-critical component issues. Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here. Footnotes
|
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b4e6ba32d0
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request significantly improves the setup experience by unifying the terminal output style across setup.sh, setup.ps1, and Python installation scripts. The new step-based format is much cleaner and easier to follow. The addition of a --verbose flag for detailed troubleshooting logs is a great feature. Making the llama.cpp build optional is also a smart move to improve user experience on systems with tricky toolchains.
I've found one issue in setup.ps1 where it exits on llama.cpp build failure, which is inconsistent with setup.sh and the PR's goal of making this step optional. My review includes a suggestion to fix this.
|
reverted this back to fail-fast behaviour in |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 9a691e4117
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Resolve merge conflicts in setup.sh and setup.ps1 while preserving both main's behavioral additions and the PR's styling refactor: setup.sh: - Keep main's _run_quiet/run_quiet/run_quiet_no_exit architecture with PR's step() styled error messages - Restore REQUESTED_PYTHON_VERSION support from main (install.sh contract) with substep() output style - Restore graceful run_quiet_no_exit || BUILD_OK=false for llama.cpp clone/cmake/build steps (instead of hard exit) - Keep PR's try_quiet for optional llama-quantize step - Keep PR's compact python version check one-liners setup.ps1: - Restore main's cpu-first/CUDA-else PyTorch install structure with PR's step/substep/verbose styling - Combine main's conda+URL detail in Python-not-found error with PR's step/substep format - Style main's stale-venv and conda-skip messages to match PR conventions Auto-merged from main (no conflicts): - _platform_compat import and UTF-8 reconfigure in run.py - Test-IsConda, py.exe launcher, Get-Command -All Python discovery - Stale-venv rebuild logic - Get-PytorchCudaTag with cu118/cpu fallbacks
|
Merged main into this branch to resolve conflicts in What was conflicting and how it was resolved:
Auto-merged without conflicts (from main):
All syntax checks pass ( |
- Bracket IPv6 display_host in external_url to produce clickable URLs - Redirect try_quiet failure log to stderr instead of stdout - Clamp _step label to column width to prevent negative padding
for more information, see https://pre-commit.ci
|
Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 7ed5b69c22
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Simulation harness (tests/simulate_pr4494.py) creates an isolated uv venv, copies the real source files into it, and runs subprocess tests for all three fixes with visual before/after demos and edge cases. Standalone bash test (tests/test_try_quiet.sh) validates try_quiet stderr redirect across 8 scenarios including broken-version contrast. 39 integration tests total (14 IPv6 + 15 try_quiet + 10 _step), all existing 75 unit tests still pass.
for more information, see https://pre-commit.ci
|
Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits. |
The %-15s printf format pads short labels but does not truncate long ones. Change to %-15.15s so labels wider than 15 chars are clipped, matching the PowerShell .Substring(0,15) and Python label[:15] logic.
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 83cab0c395
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| external_url = f"http://{display_host}:{port}" | ||
| listen_all = bind_host in ("0.0.0.0", "::") | ||
| loopback_bind = bind_host in ("127.0.0.1", "localhost", "::1") | ||
| api_base = local_url if listen_all or loopback_bind else external_url |
There was a problem hiding this comment.
When bind_host is 0.0.0.0/::, api_base is forced to local_url, so the banner advertises 127.0.0.1/::1 API endpoints even though the server is intentionally exposed on another host address. In remote/server setups, users copying the shown /api URL from the banner get a non-routable loopback address instead of the reachable network address, which is a regression from the prior display_host-based API links.
Useful? React with 👍 / 👎.
These test files are not part of the styling fix and should not ship with this PR.
Resolve conflicts in install_python_stack.py: keep the PR's column- layout output system (_step, _COL, _LABEL) and incorporate main's _safe_print Unicode fallback for Windows consoles.
- install_python_stack.py: restore _red for patch_package_file warnings (was downgraded to _dim) - setup.ps1: capture winget output and show on failure for CUDA, Node, Python, and OpenSSL installs (was piped to Out-Null) - setup.ps1: always show git pull failure warning, not just in verbose mode
|
/gemini review |
There was a problem hiding this comment.
Code Review
This pull request significantly refactors the terminal output for Unsloth Studio's setup and startup processes across various platforms (Linux/macOS, Windows, Colab). It introduces a standardized, color-coded logging system using step and substep functions for consistent and user-friendly feedback during installation and runtime. This includes centralizing the startup banner generation into a new startup_banner.py module and updating install_python_stack.py and the setup.sh/setup.ps1 scripts to use these new output helpers. The unsloth studio setup CLI command now supports a --verbose flag for detailed logging. Additionally, the setup scripts' logic for detecting and installing dependencies like Node.js, Python, CUDA Toolkit, and llama.cpp build has been refined for improved robustness and clarity. The stdout_supports_color function in studio/backend/startup_banner.py should be updated to include Windows Virtual Terminal processing for better consistency and color support on Windows, and its broad except Exception: block should be modified to log the exception, adhering to the repository's rule against silent exception handling.
| def stdout_supports_color() -> bool: | ||
| """True if we should emit ANSI colors.""" | ||
| if os.environ.get("NO_COLOR", "").strip(): | ||
| return False | ||
| if os.environ.get("FORCE_COLOR", "").strip(): | ||
| return True | ||
| try: | ||
| return sys.stdout.isatty() | ||
| except Exception: | ||
| return False | ||
|
|
||
|
|
||
| def print_port_in_use_notice(original_port: int, new_port: int) -> None: | ||
| """Message when the requested port is taken and another is chosen.""" | ||
| msg = f"Port {original_port} is in use, using port {new_port} instead." | ||
| if stdout_supports_color(): | ||
| print(f"\033[38;5;245m{msg}\033[0m") | ||
| else: | ||
| print(msg) | ||
|
|
||
|
|
||
| def print_studio_access_banner( | ||
| *, | ||
| port: int, | ||
| bind_host: str, | ||
| display_host: str, | ||
| ) -> None: | ||
| """Pretty-print URLs after the server is listening (beginner-friendly).""" |
There was a problem hiding this comment.
For consistency with install_python_stack.py and to ensure colors work correctly on Windows, this function should also attempt to enable virtual terminal (VT) processing. The current implementation only checks if stdout is a TTY, which is not sufficient on its own for modern Windows terminals. Additionally, the broad except Exception: blocks have been modified to log the exception, adhering to the repository rule against silent exception handling for better debugging.
def stdout_supports_color() -> bool:
"""True if we should emit ANSI colors."""
if os.environ.get("NO_COLOR", "").strip():
return False
if os.environ.get("FORCE_COLOR", "").strip():
return True
try:
if not sys.stdout.isatty():
return False
except Exception as e:
# Log the exception for debugging purposes as per repository rule.
import logging
logging.debug(f"stdout.isatty() check failed: {e}")
return False
if sys.platform == "win32":
try:
import ctypes
kernel32 = ctypes.windll.kernel32
handle = kernel32.GetStdHandle(-11) # STD_OUTPUT_HANDLE
mode = ctypes.c_ulong()
kernel32.GetConsoleMode(handle, ctypes.byref(mode))
kernel32.SetConsoleMode(handle, mode.value | 0x0004)
except Exception as e:
# Log the exception for debugging purposes as per repository rule.
import logging
logging.debug(f"Failed to enable VT processing on Windows: {e}")
return False
return TrueReferences
- Avoid using broad, silent exception handlers like
except Exception: pass. Instead, log the exception, even if at a debug level, to aid in future debugging.
Same capture-and-print-on-failure pattern already used for Node, Python, CUDA, and OpenSSL winget installs.
Resolve conflicts in studio/setup.sh, studio/setup.ps1, and unsloth_cli/commands/studio.py by taking main's logic as the base and applying the PR's styling changes (colors, step/substep helpers, banner/footer) on top. - setup.sh: kept main's Vite 8 node checks, bun install, prebuilt llama.cpp, Colab venv, ROCm support, version skip logic. Applied PR's color palette, step()/substep() helpers, styled banner/footer, and converted status messages. - setup.ps1: kept main's full logic (stop command, update command, prebuilt llama.cpp, etc.). Added PR's VT/ANSI infrastructure (Enable-StudioVirtualTerminal, Get-StudioAnsi, step, substep), styled banner/footer, and converted key status messages. - studio.py: took main's version entirely (stop, _run_setup_script, deprecated setup, update commands). The PR's --verbose flag is a feature addition beyond styling scope.
The step() helper writes to stdout, but _run_quiet's error header was originally sent to stderr (>&2). Without the redirect, callers that separate stdout/stderr would miss the failure headline while still seeing the log body on stderr. Add >&2 to both step calls inside _run_quiet to match main's behavior.
Wire UNSLOTH_VERBOSE=1 through _run_setup_script() so that 'unsloth studio update --verbose' (and the deprecated 'setup') passes the flag to setup.sh / setup.ps1 / install_python_stack.py.
There was a problem hiding this comment.
💡 Codex Review
Line 43 in 3e05a2a
Honor UNSLOTH_VERBOSE in Linux setup command runner
The new --verbose CLI flag only sets UNSLOTH_VERBOSE=1, but _run_quiet still unconditionally captures every command to a temp log ("$@" >"$tmplog" 2>&1). That means unsloth studio setup/update --verbose on Linux/macOS still hides npm/cmake/llama build output unless a step fails, so the troubleshooting mode is not actually providing full build logs as advertised.
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| function Write-SetupVerboseDetail { | ||
| param( | ||
| [Parameter(Mandatory = $true)][string]$Message, | ||
| [string]$Color = "Gray" | ||
| ) | ||
| if (-not $script:UnslothVerbose) { return } |
There was a problem hiding this comment.
$script:UnslothVerbose is introduced, but it is only checked inside Write-SetupVerboseDetail, and that helper is never invoked anywhere in the script. Since most setup/build commands are still piped to Out-Null, running with --verbose/UNSLOTH_VERBOSE=1 does not enable the promised full Windows setup logs outside the Python installer step.
Useful? React with 👍 / 👎.
|
/gemini review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 618b63c3a3
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| typer.echo("Error: Could not find setup script (setup.sh / setup.ps1).") | ||
| raise typer.Exit(1) | ||
|
|
||
| env = {**os.environ, "UNSLOTH_VERBOSE": "1"} if verbose else None |
There was a problem hiding this comment.
The new --verbose path only sets UNSLOTH_VERBOSE=1 before launching the setup script, but the Unix setup flow still sends npm/cmake/bundle commands through studio/setup.sh's quiet wrappers (_run_quiet), so successful build output remains suppressed. In practice, unsloth studio setup/update --verbose does not deliver the advertised "Full pip/build output" for Linux/WSL troubleshooting, which is the main reason users enable this flag.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
Code Review
This pull request standardizes the terminal output and logging across the Unsloth Studio setup and startup scripts. It introduces a consistent column-based layout with a unified ANSI color palette for Python, Bash, and PowerShell environments. Key additions include a new startup_banner.py module for pretty-printing access URLs and a --verbose flag in the CLI to provide detailed output for troubleshooting. The review feedback identifies several instances of broad exception handling in the color-detection logic that could be refined to improve debuggability.
| except Exception: | ||
| return False |
There was a problem hiding this comment.
The except Exception block is too broad and silently catches all exceptions. This can hide potential issues and make debugging difficult. It's best practice to catch specific exceptions or at least log the exception for future debugging, even if at a debug level. This aligns with the general rule: "Avoid using broad, silent exception handlers like except Exception: pass. Instead, log the exception, even if at a debug level, to aid in future debugging."
References
- Avoid using broad, silent exception handlers like
except Exception: pass. Instead, log the exception, even if at a debug level, to aid in future debugging.
| except Exception: | ||
| return False |
There was a problem hiding this comment.
The except Exception block is too broad and silently catches all exceptions. This can hide potential issues and make debugging difficult. It's best practice to catch specific exceptions or at least log the exception for future debugging, even if at a debug level. This aligns with the general rule: "Avoid using broad, silent exception handlers like except Exception: pass. Instead, log the exception, even if at a debug level, to aid in future debugging."
References
- Avoid using broad, silent exception handlers like
except Exception: pass. Instead, log the exception, even if at a debug level, to aid in future debugging.
| except Exception: | ||
| return False |
There was a problem hiding this comment.
The except Exception block is too broad and silently catches all exceptions. This can hide potential issues and make debugging difficult. It's best practice to catch specific exceptions or at least log the exception for future debugging, even if at a debug level. This aligns with the general rule: "Avoid using broad, silent exception handlers like except Exception: pass. Instead, log the exception, even if at a debug level, to aid in future debugging."
References
- Avoid using broad, silent exception handlers like
except Exception: pass. Instead, log the exception, even if at a debug level, to aid in future debugging.
…ls, and startup messaging (unslothai#4651) * refactor(studio): unify setup terminal output style and add verbose setup mode * studio(windows): align setup.ps1 banner/steps with setup.sh (ANSI, verbose) * studio(setup): revert nvcc path reordering to match main * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * studio(setup): restore fail-fast llama.cpp setup flow * studio(banner): use IPv6 loopback URL when binding :: or ::1 * Fix IPv6 URL bracketing, try_quiet stderr, _step label clamp - Bracket IPv6 display_host in external_url to produce clickable URLs - Redirect try_quiet failure log to stderr instead of stdout - Clamp _step label to column width to prevent negative padding * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Add sandbox integration tests for PR unslothai#4494 UX fixes Simulation harness (tests/simulate_pr4494.py) creates an isolated uv venv, copies the real source files into it, and runs subprocess tests for all three fixes with visual before/after demos and edge cases. Standalone bash test (tests/test_try_quiet.sh) validates try_quiet stderr redirect across 8 scenarios including broken-version contrast. 39 integration tests total (14 IPv6 + 15 try_quiet + 10 _step), all existing 75 unit tests still pass. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Truncate step() labels in setup.sh to match PS1 and Python The %-15s printf format pads short labels but does not truncate long ones. Change to %-15.15s so labels wider than 15 chars are clipped, matching the PowerShell .Substring(0,15) and Python label[:15] logic. * Remove sandbox integration tests from PR These test files are not part of the styling fix and should not ship with this PR. * Show error output on failure instead of suppressing it - install_python_stack.py: restore _red for patch_package_file warnings (was downgraded to _dim) - setup.ps1: capture winget output and show on failure for CUDA, Node, Python, and OpenSSL installs (was piped to Out-Null) - setup.ps1: always show git pull failure warning, not just in verbose mode * Show winget error output for Git and CMake installs on failure Same capture-and-print-on-failure pattern already used for Node, Python, CUDA, and OpenSSL winget installs. * fix: preserve stderr for _run_quiet error messages in setup.sh The step() helper writes to stdout, but _run_quiet's error header was originally sent to stderr (>&2). Without the redirect, callers that separate stdout/stderr would miss the failure headline while still seeing the log body on stderr. Add >&2 to both step calls inside _run_quiet to match main's behavior. * feat: add --verbose flag to setup and update commands Wire UNSLOTH_VERBOSE=1 through _run_setup_script() so that 'unsloth studio update --verbose' (and the deprecated 'setup') passes the flag to setup.sh / setup.ps1 / install_python_stack.py. * fix(studio): honor verbose logging and keep llama.cpp failures non-blocking * fix(studio): switch installer to 'studio update' and normalize Windows setup logs * chore(studio): refine localhost tip and remove skip-base setup nois * fix(studio): align Windows setup logs with Linux style and improve startup tips * fix(studio): align Windows setup logs with Linux style * refactor(windows-installer): align install/setup logs with Linux style and silence auto-launch output * refactor(windows): align installer/setup output with Linux style and reduce default verbosity * refactor(windows): match install.ps1 output style/colors to setup and quiet default logs * fix(studio-banner): update personal-computer localhost tip * fix(setup.sh): restore verbose llama.cpp build output while keeping default quiet mode * fix(install.sh): align installer logging with setup style and restore POSIX-safe color output * fix(install.sh): preserve installer reliability and launch visibility Export verbose mode for child setup processes, harden install command handling under set -e, and keep first-run studio launch non-silent so users can always see URL and port fallback output. * fix(windows installer): keep exit semantics and degrade status accurate Use quiet command redirection that preserves native exit codes, keep startup output visible on first launch, and report limited install status when llama.cpp is unavailable. * fix(setup.sh): improve log clarity and enforce GGUF degraded signaling Restore clean default setup output, add verbose-only diagnostics, fail fast on Colab dependency install errors, and return non-zero when GGUF prerequisites or llama.cpp artifacts are unavailable. * fix(installer): harden bash preflight and PowerShell GPU checks Fail fast when bash is unavailable before invoking setup.sh, and replace remaining nvidia-smi pipeline checks with stream redirection patterns that preserve reliable native exit-code handling. * fix(windows): keep verbose output visible while preserving exit codes Ensure PowerShell wrapper helpers in install/update stream native command output to host without returning it as function output, so npm logs no longer corrupt exit-code checks in verbose mode. * fix(windows): avoid sticky UNSLOTH_VERBOSE and gate studio update verbosity * Fix degraded llama.cpp exit code, PS verbose stderr, banner URLs, npm verbose - setup.sh: Do not exit non-zero when llama.cpp is unavailable; the footer already reports the limitation, and install.sh runs under set -e so a non-zero exit aborts the entire install including PATH/shortcuts/launch. - setup.ps1: Remove $? check in Invoke-SetupCommand verbose path; PS 5.1 sets $? = $false when native commands write to stderr even with exit 0. Merge stderr into stdout with 2>&1 and rely solely on $LASTEXITCODE. - startup_banner.py: Show the actual bound address when Studio is bound to a non-loopback interface instead of always showing 127.0.0.1/localhost. - setup.sh: Use run_quiet_no_exit instead of run_quiet_no_exit_always for npm install steps so --verbose correctly surfaces npm output. * Fix install.ps1 verbose stderr, propagate UNSLOTH_VERBOSE, fix git clone verbose - install.ps1: Apply same Invoke-InstallCommand fix as setup.ps1 -- merge stderr into stdout with 2>&1 and drop the $? check that misclassifies successful native commands on PS 5.1. - install.ps1 + setup.ps1: Export UNSLOTH_VERBOSE=1 to the process env when --verbose is passed so child processes like install_python_stack.py also run in verbose mode. - setup.sh: Use run_quiet_no_exit for git clone llama.cpp so --verbose correctly surfaces clone diagnostics during source-build fallback. * Surface prebuilt llama.cpp output in verbose mode, remove dead code, fix banner - setup.sh: Use tee in verbose mode for prebuilt llama.cpp installer so users can see download/validation progress while still capturing the log for structured error reporting on failure. - setup.ps1: Same fix for Windows -- use Tee-Object in verbose mode. - setup.sh: Remove run_quiet_no_exit_always() which has no remaining callers. - startup_banner.py: Avoid printing the same URL twice when Studio is bound to a specific non-loopback address that matches the display host. * Fix run_install_cmd exit code after failed if-statement The previous pattern 'if "$@"; then return 0; fi; _rc=$?' always captured $? = 0 because $? reflects the if-statement result, not the command's exit code. Switch to '"$@" && return 0; _rc=$?' which preserves the actual command exit code on failure. Applies to both verbose and quiet branches. * Fix _run_quiet exit code, double uv install, missing --local flag - setup.sh: Fix _run_quiet verbose path that always captured exit code 0 due to $? resetting after if-then-fi with no else. Switch to the same '"$@" && return 0; exit_code=$?' pattern used in install.sh. - setup.sh: Consolidate the two uv install branches (verbose + quiet) into a single attempt with conditional output. Previously, when verbose mode was on and the install failed, a second silent attempt was made. - install.ps1: Pass --local flag to 'unsloth studio update' when $StudioLocalInstall is true. Without this, studio.py's update() command overwrites STUDIO_LOCAL_INSTALL to "0", which could cause issues if setup.ps1 or install_python_stack.py later checks that variable. * Revert SKIP_STUDIO_BASE change for --no-torch, restore install banners - Revert SKIP_STUDIO_BASE from 0 to 1 for --no-torch. install.sh already installs unsloth+unsloth-zoo and no-torch-runtime.txt before calling setup.sh, so letting install_python_stack.py redo it was redundant and slowed down --no-torch installs for no benefit. - Restore the "Unsloth Studio installed!" success banner and "starting Unsloth Studio..." launch message so users get clear install completion feedback before the server starts. * Make llama.cpp build failure a hard error with proper cleanup - setup.sh: Restore exit 1 when _LLAMA_CPP_DEGRADED is true. GGUF inference requires a working llama.cpp build, so this should be a hard failure, not a silent degradation. - install.sh: Catch setup.sh's non-zero exit with '|| _SETUP_EXIT=$?' instead of letting set -e abort immediately. This ensures PATH setup, symlinks, and shortcuts still get created so the user can fix the build deps and retry with 'unsloth studio update'. After post-install steps, propagate the failure with a clear error message. * Revert install.ps1 to 'studio setup' to preserve SKIP_STUDIO_BASE 'studio update' pops SKIP_STUDIO_BASE from the environment, which defeats the fast-path version check added in PR unslothai#4667. When called from install.ps1 (which already installed packages), SKIP_STUDIO_BASE=1 must survive into setup.ps1 so it skips the redundant PyPI check and package reinstallation. 'studio setup' does not modify env vars. * Remove deprecation message from 'studio setup' command install.ps1 uses 'studio setup' (not 'studio update') to preserve SKIP_STUDIO_BASE. The deprecation message was confusing during first install since the user never typed the command. * Fix stale env vars, scope degraded exit, generic error message for PR unslothai#4651 - install.ps1: Always set STUDIO_LOCAL_INSTALL and clear STUDIO_LOCAL_REPO when not using --local, to prevent stale values from a previous --local run in the same PowerShell session. Fix log messages to say 'setup' not 'update' since we call 'studio setup'. - setup.sh: Only exit non-zero for degraded llama.cpp when called from the installer (SKIP_STUDIO_BASE=1). Direct 'unsloth studio update' keeps degraded installs successful since Studio is still usable for non-GGUF workflows and the footer already reports the limitation. - install.sh: Make the setup failure error message generic instead of GGUF-specific, so unrelated failures (npm, Python deps) do not show misleading cmake/git recovery advice. * Show captured output on failure in quiet mode for PR unslothai#4651 Both Invoke-InstallCommand (install.ps1) and Invoke-SetupCommand (setup.ps1) now capture command output in quiet mode and display it in red when the command fails. This matches the behavior of run_install_cmd in install.sh where failure output is surfaced even in quiet mode, making cross-platform error debugging consistent. * Match degraded llama.cpp exit on Windows, fix --local recovery hint for PR unslothai#4651 - setup.ps1: Exit non-zero for degraded llama.cpp when called from install.ps1 (SKIP_STUDIO_BASE=1), matching setup.sh behavior. Direct 'unsloth studio update' keeps degraded installs successful. - install.sh: Show 'unsloth studio update --local' in the recovery message when the install was run with --local, so users retry with the correct flag instead of losing local checkout context. --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* refactor(studio): unify setup terminal output style and add verbose setup mode * studio(windows): align setup.ps1 banner/steps with setup.sh (ANSI, verbose) * studio(setup): revert nvcc path reordering to match main * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * studio(setup): restore fail-fast llama.cpp setup flow * studio(banner): use IPv6 loopback URL when binding :: or ::1 * Fix IPv6 URL bracketing, try_quiet stderr, _step label clamp - Bracket IPv6 display_host in external_url to produce clickable URLs - Redirect try_quiet failure log to stderr instead of stdout - Clamp _step label to column width to prevent negative padding * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Add sandbox integration tests for PR unslothai#4494 UX fixes Simulation harness (tests/simulate_pr4494.py) creates an isolated uv venv, copies the real source files into it, and runs subprocess tests for all three fixes with visual before/after demos and edge cases. Standalone bash test (tests/test_try_quiet.sh) validates try_quiet stderr redirect across 8 scenarios including broken-version contrast. 39 integration tests total (14 IPv6 + 15 try_quiet + 10 _step), all existing 75 unit tests still pass. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Truncate step() labels in setup.sh to match PS1 and Python The %-15s printf format pads short labels but does not truncate long ones. Change to %-15.15s so labels wider than 15 chars are clipped, matching the PowerShell .Substring(0,15) and Python label[:15] logic. * Remove sandbox integration tests from PR These test files are not part of the styling fix and should not ship with this PR. * Show error output on failure instead of suppressing it - install_python_stack.py: restore _red for patch_package_file warnings (was downgraded to _dim) - setup.ps1: capture winget output and show on failure for CUDA, Node, Python, and OpenSSL installs (was piped to Out-Null) - setup.ps1: always show git pull failure warning, not just in verbose mode * Show winget error output for Git and CMake installs on failure Same capture-and-print-on-failure pattern already used for Node, Python, CUDA, and OpenSSL winget installs. * fix: preserve stderr for _run_quiet error messages in setup.sh The step() helper writes to stdout, but _run_quiet's error header was originally sent to stderr (>&2). Without the redirect, callers that separate stdout/stderr would miss the failure headline while still seeing the log body on stderr. Add >&2 to both step calls inside _run_quiet to match main's behavior. * feat: add --verbose flag to setup and update commands Wire UNSLOTH_VERBOSE=1 through _run_setup_script() so that 'unsloth studio update --verbose' (and the deprecated 'setup') passes the flag to setup.sh / setup.ps1 / install_python_stack.py. --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Daniel Han <danielhanchen@gmail.com>
…ls, and startup messaging (unslothai#4651) * refactor(studio): unify setup terminal output style and add verbose setup mode * studio(windows): align setup.ps1 banner/steps with setup.sh (ANSI, verbose) * studio(setup): revert nvcc path reordering to match main * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * studio(setup): restore fail-fast llama.cpp setup flow * studio(banner): use IPv6 loopback URL when binding :: or ::1 * Fix IPv6 URL bracketing, try_quiet stderr, _step label clamp - Bracket IPv6 display_host in external_url to produce clickable URLs - Redirect try_quiet failure log to stderr instead of stdout - Clamp _step label to column width to prevent negative padding * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Add sandbox integration tests for PR unslothai#4494 UX fixes Simulation harness (tests/simulate_pr4494.py) creates an isolated uv venv, copies the real source files into it, and runs subprocess tests for all three fixes with visual before/after demos and edge cases. Standalone bash test (tests/test_try_quiet.sh) validates try_quiet stderr redirect across 8 scenarios including broken-version contrast. 39 integration tests total (14 IPv6 + 15 try_quiet + 10 _step), all existing 75 unit tests still pass. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Truncate step() labels in setup.sh to match PS1 and Python The %-15s printf format pads short labels but does not truncate long ones. Change to %-15.15s so labels wider than 15 chars are clipped, matching the PowerShell .Substring(0,15) and Python label[:15] logic. * Remove sandbox integration tests from PR These test files are not part of the styling fix and should not ship with this PR. * Show error output on failure instead of suppressing it - install_python_stack.py: restore _red for patch_package_file warnings (was downgraded to _dim) - setup.ps1: capture winget output and show on failure for CUDA, Node, Python, and OpenSSL installs (was piped to Out-Null) - setup.ps1: always show git pull failure warning, not just in verbose mode * Show winget error output for Git and CMake installs on failure Same capture-and-print-on-failure pattern already used for Node, Python, CUDA, and OpenSSL winget installs. * fix: preserve stderr for _run_quiet error messages in setup.sh The step() helper writes to stdout, but _run_quiet's error header was originally sent to stderr (>&2). Without the redirect, callers that separate stdout/stderr would miss the failure headline while still seeing the log body on stderr. Add >&2 to both step calls inside _run_quiet to match main's behavior. * feat: add --verbose flag to setup and update commands Wire UNSLOTH_VERBOSE=1 through _run_setup_script() so that 'unsloth studio update --verbose' (and the deprecated 'setup') passes the flag to setup.sh / setup.ps1 / install_python_stack.py. * fix(studio): honor verbose logging and keep llama.cpp failures non-blocking * fix(studio): switch installer to 'studio update' and normalize Windows setup logs * chore(studio): refine localhost tip and remove skip-base setup nois * fix(studio): align Windows setup logs with Linux style and improve startup tips * fix(studio): align Windows setup logs with Linux style * refactor(windows-installer): align install/setup logs with Linux style and silence auto-launch output * refactor(windows): align installer/setup output with Linux style and reduce default verbosity * refactor(windows): match install.ps1 output style/colors to setup and quiet default logs * fix(studio-banner): update personal-computer localhost tip * fix(setup.sh): restore verbose llama.cpp build output while keeping default quiet mode * fix(install.sh): align installer logging with setup style and restore POSIX-safe color output * fix(install.sh): preserve installer reliability and launch visibility Export verbose mode for child setup processes, harden install command handling under set -e, and keep first-run studio launch non-silent so users can always see URL and port fallback output. * fix(windows installer): keep exit semantics and degrade status accurate Use quiet command redirection that preserves native exit codes, keep startup output visible on first launch, and report limited install status when llama.cpp is unavailable. * fix(setup.sh): improve log clarity and enforce GGUF degraded signaling Restore clean default setup output, add verbose-only diagnostics, fail fast on Colab dependency install errors, and return non-zero when GGUF prerequisites or llama.cpp artifacts are unavailable. * fix(installer): harden bash preflight and PowerShell GPU checks Fail fast when bash is unavailable before invoking setup.sh, and replace remaining nvidia-smi pipeline checks with stream redirection patterns that preserve reliable native exit-code handling. * fix(windows): keep verbose output visible while preserving exit codes Ensure PowerShell wrapper helpers in install/update stream native command output to host without returning it as function output, so npm logs no longer corrupt exit-code checks in verbose mode. * fix(windows): avoid sticky UNSLOTH_VERBOSE and gate studio update verbosity * Fix degraded llama.cpp exit code, PS verbose stderr, banner URLs, npm verbose - setup.sh: Do not exit non-zero when llama.cpp is unavailable; the footer already reports the limitation, and install.sh runs under set -e so a non-zero exit aborts the entire install including PATH/shortcuts/launch. - setup.ps1: Remove $? check in Invoke-SetupCommand verbose path; PS 5.1 sets $? = $false when native commands write to stderr even with exit 0. Merge stderr into stdout with 2>&1 and rely solely on $LASTEXITCODE. - startup_banner.py: Show the actual bound address when Studio is bound to a non-loopback interface instead of always showing 127.0.0.1/localhost. - setup.sh: Use run_quiet_no_exit instead of run_quiet_no_exit_always for npm install steps so --verbose correctly surfaces npm output. * Fix install.ps1 verbose stderr, propagate UNSLOTH_VERBOSE, fix git clone verbose - install.ps1: Apply same Invoke-InstallCommand fix as setup.ps1 -- merge stderr into stdout with 2>&1 and drop the $? check that misclassifies successful native commands on PS 5.1. - install.ps1 + setup.ps1: Export UNSLOTH_VERBOSE=1 to the process env when --verbose is passed so child processes like install_python_stack.py also run in verbose mode. - setup.sh: Use run_quiet_no_exit for git clone llama.cpp so --verbose correctly surfaces clone diagnostics during source-build fallback. * Surface prebuilt llama.cpp output in verbose mode, remove dead code, fix banner - setup.sh: Use tee in verbose mode for prebuilt llama.cpp installer so users can see download/validation progress while still capturing the log for structured error reporting on failure. - setup.ps1: Same fix for Windows -- use Tee-Object in verbose mode. - setup.sh: Remove run_quiet_no_exit_always() which has no remaining callers. - startup_banner.py: Avoid printing the same URL twice when Studio is bound to a specific non-loopback address that matches the display host. * Fix run_install_cmd exit code after failed if-statement The previous pattern 'if "$@"; then return 0; fi; _rc=$?' always captured $? = 0 because $? reflects the if-statement result, not the command's exit code. Switch to '"$@" && return 0; _rc=$?' which preserves the actual command exit code on failure. Applies to both verbose and quiet branches. * Fix _run_quiet exit code, double uv install, missing --local flag - setup.sh: Fix _run_quiet verbose path that always captured exit code 0 due to $? resetting after if-then-fi with no else. Switch to the same '"$@" && return 0; exit_code=$?' pattern used in install.sh. - setup.sh: Consolidate the two uv install branches (verbose + quiet) into a single attempt with conditional output. Previously, when verbose mode was on and the install failed, a second silent attempt was made. - install.ps1: Pass --local flag to 'unsloth studio update' when $StudioLocalInstall is true. Without this, studio.py's update() command overwrites STUDIO_LOCAL_INSTALL to "0", which could cause issues if setup.ps1 or install_python_stack.py later checks that variable. * Revert SKIP_STUDIO_BASE change for --no-torch, restore install banners - Revert SKIP_STUDIO_BASE from 0 to 1 for --no-torch. install.sh already installs unsloth+unsloth-zoo and no-torch-runtime.txt before calling setup.sh, so letting install_python_stack.py redo it was redundant and slowed down --no-torch installs for no benefit. - Restore the "Unsloth Studio installed!" success banner and "starting Unsloth Studio..." launch message so users get clear install completion feedback before the server starts. * Make llama.cpp build failure a hard error with proper cleanup - setup.sh: Restore exit 1 when _LLAMA_CPP_DEGRADED is true. GGUF inference requires a working llama.cpp build, so this should be a hard failure, not a silent degradation. - install.sh: Catch setup.sh's non-zero exit with '|| _SETUP_EXIT=$?' instead of letting set -e abort immediately. This ensures PATH setup, symlinks, and shortcuts still get created so the user can fix the build deps and retry with 'unsloth studio update'. After post-install steps, propagate the failure with a clear error message. * Revert install.ps1 to 'studio setup' to preserve SKIP_STUDIO_BASE 'studio update' pops SKIP_STUDIO_BASE from the environment, which defeats the fast-path version check added in PR unslothai#4667. When called from install.ps1 (which already installed packages), SKIP_STUDIO_BASE=1 must survive into setup.ps1 so it skips the redundant PyPI check and package reinstallation. 'studio setup' does not modify env vars. * Remove deprecation message from 'studio setup' command install.ps1 uses 'studio setup' (not 'studio update') to preserve SKIP_STUDIO_BASE. The deprecation message was confusing during first install since the user never typed the command. * Fix stale env vars, scope degraded exit, generic error message for PR unslothai#4651 - install.ps1: Always set STUDIO_LOCAL_INSTALL and clear STUDIO_LOCAL_REPO when not using --local, to prevent stale values from a previous --local run in the same PowerShell session. Fix log messages to say 'setup' not 'update' since we call 'studio setup'. - setup.sh: Only exit non-zero for degraded llama.cpp when called from the installer (SKIP_STUDIO_BASE=1). Direct 'unsloth studio update' keeps degraded installs successful since Studio is still usable for non-GGUF workflows and the footer already reports the limitation. - install.sh: Make the setup failure error message generic instead of GGUF-specific, so unrelated failures (npm, Python deps) do not show misleading cmake/git recovery advice. * Show captured output on failure in quiet mode for PR unslothai#4651 Both Invoke-InstallCommand (install.ps1) and Invoke-SetupCommand (setup.ps1) now capture command output in quiet mode and display it in red when the command fails. This matches the behavior of run_install_cmd in install.sh where failure output is surfaced even in quiet mode, making cross-platform error debugging consistent. * Match degraded llama.cpp exit on Windows, fix --local recovery hint for PR unslothai#4651 - setup.ps1: Exit non-zero for degraded llama.cpp when called from install.ps1 (SKIP_STUDIO_BASE=1), matching setup.sh behavior. Direct 'unsloth studio update' keeps degraded installs successful. - install.sh: Show 'unsloth studio update --local' in the recovery message when the install was run with --local, so users retry with the correct flag instead of losing local checkout context. --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Daniel Han <danielhanchen@gmail.com>
2 participants
Unify Studio terminal output styling across setup flows with a cleaner, step-based format and shared banner treatment.
Update Windows setup (
studio/setup.ps1) to match the new visual style while keeping behavior intact.Add
unsloth studio setup --verbose(-v) to enable full dependency/build logs for troubleshooting.Windows:
WSL:
Launch:
