ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge remote-tracking branch 'origin/main' into r5748

Browse source
This commit is contained in:
Daniel Han 2026-07-19 13:20:20 +00:00
commit f051e46415
336 changed files with 8319 additions and 1784 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.github/workflows/consolidated-tests-ci.yml vendored
View file

@ -268,6 +268,7 @@ jobs:
tests/saving/test_save_shell_injection.py \
tests/saving/test_patch_saving_none_tokenizer.py \
tests/saving/test_fix_sentencepiece_gguf_robustness.py \
tests/saving/test_fix_sentencepiece_tokenizer_guard.py \
tests/saving/test_compressed_export_schemes.py \
tests/saving/test_export_api_surface.py \
tests/saving/test_export_dispatch.py \
@ -358,6 +359,7 @@ jobs:
tests/saving/test_save_shell_injection.py \
tests/saving/test_patch_saving_none_tokenizer.py \
tests/saving/test_fix_sentencepiece_gguf_robustness.py \
tests/saving/test_fix_sentencepiece_tokenizer_guard.py \
tests/saving/test_compressed_export_schemes.py \
tests/saving/test_export_api_surface.py \
tests/saving/test_export_dispatch.py \

4
.github/workflows/lint-ci.yml vendored
View file

@ -13,10 +13,10 @@
# committed YAML / JSON config.
#
# TypeScript and Rust are NOT duplicated here on purpose:
# - Studio Frontend CI runs `npm run typecheck` (= `tsc --noEmit`)
# - Unsloth Frontend CI runs `npm run typecheck` (= `tsc --noEmit`)
# and `npm run build` (vite/swc) on every studio/frontend/**
# change, which is a full TS AST + type check.
# - Studio Tauri CI runs `tauri build --debug --no-bundle` on
# - Unsloth Tauri CI runs `tauri build --debug --no-bundle` on
# every studio/src-tauri/** or studio/frontend/** change, which
# compiles the Rust crate (= cargo check + cargo build).
# Each is a stricter check than a parse-only step would be, so a

16
.github/workflows/local-agent-guides-ci.yml vendored
View file

@ -154,7 +154,7 @@ jobs:
path: gguf-cache
key: ${{ runner.os }}-gguf-${{ env.GGUF_REPO }}-${{ env.GGUF_FILE }}-v1
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Gated off PR (see note above); public GGUF still downloads.
@ -256,7 +256,7 @@ jobs:
done
fi
- name: Stop Studio
- name: Stop Unsloth
if: always()
run: |
# Guard the PID: an unset/zero UNSLOTH_SERVER_PID would make
@ -359,7 +359,7 @@ jobs:
path: gguf-cache
key: ${{ runner.os }}-gguf-${{ env.GGUF_REPO }}-${{ env.GGUF_FILE }}-v1
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Gated off PR (see note above); public GGUF still downloads.
@ -448,7 +448,7 @@ jobs:
done
fi
- name: Stop Studio
- name: Stop Unsloth
if: always()
run: |
# Guard the PID: an unset/zero UNSLOTH_SERVER_PID would make
@ -543,7 +543,7 @@ jobs:
path: gguf-cache
key: ${{ runner.os }}-gguf-${{ env.GGUF_REPO }}-${{ env.GGUF_FILE }}-v1
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
HF_TOKEN: ${{ secrets.HF_TOKEN }}
@ -620,7 +620,7 @@ jobs:
done
fi
- name: Stop Studio
- name: Stop Unsloth
if: always()
run: |
if [ -n "${UNSLOTH_SERVER_PID:-}" ] && [ "${UNSLOTH_SERVER_PID}" != "0" ]; then
@ -706,7 +706,7 @@ jobs:
path: hf-cache
key: ${{ runner.os }}-hf-${{ env.GGUF_REPO }}-${{ env.GGUF_VARIANT }}-v2
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Gated off PR (see note above); public GGUF still downloads.
@ -764,7 +764,7 @@ jobs:
done
fi
- name: Stop Studio
- name: Stop Unsloth
if: always()
run: |
# Guard the PID: an unset/zero UNSLOTH_SERVER_PID would make

12
.github/workflows/mlx-ci.yml vendored
View file

@ -130,7 +130,7 @@ jobs:
# MLX support landed after the most recent unsloth-zoo PyPI
# release; the wheel still raises NotImplementedError on
# Apple Silicon when device_type.get_device_type() runs
# unguarded. Studio's own install.sh overlays unsloth-zoo
# unguarded. Unsloth's own install.sh overlays unsloth-zoo
# from git main for the same reason. Pulling deps lets pip
# resolve the platform-conditional MLX-only wheels (mlx,
# mlx-lm, mlx-vlm gated on darwin+arm64 in unsloth-zoo's
@ -317,13 +317,13 @@ jobs:
echo
done
# Validates the macOS prebuilt path Studio's setup.sh uses (#5963): install the
# Validates the macOS prebuilt path Unsloth's setup.sh uses (#5963): install the
# unslothai/llama.cpp fork's latest release, download a small public GGUF, and
# check llama-server /completion end to end. Split and placed last so the
# untrusted binary runs only in the final smoke step, after every HF_TOKEN step,
# leaving no token-bearing step or shared workspace for a tampered prebuilt to
# corrupt. GH_TOKEN: releases API; HF_TOKEN (withheld on PR): probe + GGUF fetch.
- name: Studio prebuilt llama.cpp install + GGUF download (Mac M1)
- name: Unsloth prebuilt llama.cpp install + GGUF download (Mac M1)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@ -344,12 +344,12 @@ jobs:
# Final step: runs the downloaded binaries with no secrets present, and clears
# the GitHub Actions command files so a tampered prebuilt cannot influence the job.
- name: Studio prebuilt llama.cpp GGUF inference smoke (Mac M1)
- name: Unsloth prebuilt llama.cpp GGUF inference smoke (Mac M1)
run: |
set -euo pipefail
unset GITHUB_ENV GITHUB_PATH GITHUB_OUTPUT GITHUB_STEP_SUMMARY
INSTALL_DIR="$HOME/.unsloth-studio-prebuilt-test/llama.cpp"
# Studio bundles only llama-server + llama-quantize (not llama-cli);
# Unsloth bundles only llama-server + llama-quantize (not llama-cli);
# inference goes through llama-server's HTTP /completion endpoint.
LLAMA_SERVER="$INSTALL_DIR/build/bin/llama-server"
LLAMA_QUANT="$INSTALL_DIR/build/bin/llama-quantize"
@ -400,4 +400,4 @@ jobs:
tail -40 /tmp/llama-server.log
exit 1
fi
echo "OK: Studio prebuilt llama.cpp on Mac M1 + GGUF /completion works"
echo "OK: Unsloth prebuilt llama.cpp on Mac M1 + GGUF /completion works"

8
.github/workflows/release-desktop.yml vendored
View file

@ -4,7 +4,7 @@ on:
workflow_dispatch:
inputs:
studio_version:
description: 'Studio version tag to release (for example, v0.1.39-beta)'
description: 'Unsloth version tag to release (for example, v0.1.39-beta)'
type: string
required: true
pypi_version:
@ -69,7 +69,7 @@ jobs:
if not studio_version:
sys.exit('studio_version is required, for example v0.1.39-beta')
if re.fullmatch(r'v?20\d{2}\.\d+\.\d+(?:[-+][0-9A-Za-z.-]+)?', studio_version):
sys.exit(f'studio_version must be a Studio SemVer tag, not a date-style backend version: {studio_version}')
sys.exit(f'studio_version must be an Unsloth SemVer tag, not a date-style backend version: {studio_version}')
semver_tag = re.compile(
r'^v(0|[1-9]\d*)\.(0|[1-9]\d*)\.(0|[1-9]\d*)'
@ -146,7 +146,7 @@ jobs:
print(f'pypi_version={pypi_version}', file=output)
PY
- name: Verify PyPI package and Studio stamp
- name: Verify PyPI package and Unsloth stamp
shell: bash
env:
STUDIO_VERSION: ${{ steps.prepare.outputs.studio_version }}
@ -211,7 +211,7 @@ jobs:
fi
python3 scripts/stamp_studio_release.py --verify-dist "$RUNNER_TEMP/pypi-unsloth-dist" --expected "$STUDIO_VERSION"
else
echo "scripts/stamp_studio_release.py not found; release-desktop requires #5308 to verify the PyPI Studio stamp." >&2
echo "scripts/stamp_studio_release.py not found; release-desktop requires #5308 to verify the PyPI Unsloth stamp." >&2
exit 1
fi

30
.github/workflows/security-audit.yml vendored
View file

@ -36,8 +36,8 @@
# - unsloth `huggingfacenotorch` extras (the canonical install path
# for fine-tuning users; pulls transformers / peft / accelerate /
# trl / datasets / diffusers / sentence-transformers / etc.)
# - all six Studio backend requirements files
# - Studio frontend (npm) and Tauri shell (cargo)
# - all six Unsloth backend requirements files
# - Unsloth frontend (npm) and Tauri shell (cargo)
# Each Python step builds a filtered dep list from pyproject.toml +
# requirements/*.txt before auditing. We do NOT install any of these
# -- pip-audit resolves through PyPI metadata, scan_packages.py
@ -218,7 +218,7 @@ jobs:
# on the runner). A comment line is left in place so the
# skipped specs are obvious in the artifact.
# The `huggingface` extra is `huggingfacenotorch` plus torch /
# torchvision / triton, deliberately skipped: Studio backend
# torchvision / triton, deliberately skipped: Unsloth backend
# already pins a torch and the +cu* / +cpu local-version tags
# trip up the PyPI resolver in `-r` mode.
run: |
@ -253,7 +253,7 @@ jobs:
# `-r requirements.txt` resolves the requirements through pip's
# dependency resolver against PyPI metadata and audits the
# resolved tree without ever executing setup.py / install
# hooks. Way faster than installing the full Studio runtime
# hooks. Way faster than installing the full Unsloth runtime
# and -- critically -- safer: an attacker who has compromised
# a transitive dep cannot run code in this job.
#
@ -326,9 +326,9 @@ jobs:
} >> "$GITHUB_STEP_SUMMARY"
# ─────────────────────────────────────────────────────────────
# npm: Studio frontend
# npm: Unsloth frontend
# ─────────────────────────────────────────────────────────────
- name: npm audit (Studio frontend)
- name: npm audit (Unsloth frontend)
# `npm audit` resolves the lockfile through the npmjs.com
# advisory DB. `--audit-level=high` filters the noise floor
# to only HIGH and CRITICAL. We do NOT pass --omit=dev: a
@ -342,7 +342,7 @@ jobs:
# Always also write the full JSON for grep-ability.
npm audit --json > ../../logs-npm-audit.json || true
{
echo "## npm audit (Studio frontend)"
echo "## npm audit (Unsloth frontend)"
echo
echo '```'
tail -200 ../../logs-npm-audit.txt
@ -350,9 +350,9 @@ jobs:
} >> "$GITHUB_STEP_SUMMARY"
# ─────────────────────────────────────────────────────────────
# cargo: Studio Tauri shell
# cargo: Unsloth Tauri shell
# ─────────────────────────────────────────────────────────────
- name: cargo audit (Studio Tauri)
- name: cargo audit (Unsloth Tauri)
# `--deny warnings` would make the job fail on any advisory.
# Keep non-blocking initially; drop continue-on-error after
# the baseline closes.
@ -362,7 +362,7 @@ jobs:
set +e
cargo audit | tee ../../logs-cargo-audit.txt
{
echo "## cargo audit (Studio Tauri)"
echo "## cargo audit (Unsloth Tauri)"
echo
echo '```'
tail -200 ../../logs-cargo-audit.txt
@ -559,7 +559,7 @@ jobs:
# ─────────────────────────────────────────────────────────────
# CycloneDX SBOM. Lets downstream consumers audit what's
# actually shipped in unsloth wheels and the Studio backend
# actually shipped in unsloth wheels and the Unsloth backend
# runtime. Generates one JSON file per requirements input plus
# a combined SBOM keyed off pyproject.toml; uploads as a build
# artifact (and a future step can attest it via SLSA).
@ -740,7 +740,7 @@ jobs:
# `--with-deps` makes the scan transitive: every package the
# declared set resolves to gets fetched and pattern-scanned, not
# just the top-level pins. Resolving the full transitive closure
# of the unsloth + Studio dep tree downloads several hundred
# of the unsloth + Unsloth dep tree downloads several hundred
# archives, hence the longer timeout.
#
# Sharded across runners for wall-clock parallelism. Each shard
@ -749,7 +749,7 @@ jobs:
# composition tries to balance load:
# - hf-stack: pyproject extras + no-torch-runtime
# (~150 archives, transformers/peft/accelerate/...)
# - studio: FastAPI/Studio backend + overrides + extras-no-deps
# - studio: FastAPI/Unsloth backend + overrides + extras-no-deps
# (~150 archives, smaller scientific stack)
# - extras: the heavy openai-whisper / scikit-learn / librosa
# stack (~250 archives, dominant cost)
@ -964,7 +964,7 @@ jobs:
# documented at scripts/scan_npm_packages.py top-of-file. The
# script is stdlib-only so adding it does not increase the
# transitive supply-chain surface.
name: npm scan-packages (Studio frontend tarballs)
name: npm scan-packages (Unsloth frontend tarballs)
runs-on: ubuntu-latest
timeout-minutes: 30
needs: []
@ -1173,7 +1173,7 @@ jobs:
with:
python-version: '3.12'
- name: Install Studio frontend deps (--ignore-scripts)
- name: Install Unsloth frontend deps (--ignore-scripts)
# `npm audit signatures` requires node_modules to be populated.
# `--ignore-scripts` is mandatory: this is exactly the lever the
# new-install-script gate below protects against, and we must

14
.github/workflows/studio-api-smoke.yml vendored
View file

@ -1,7 +1,7 @@
# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
# Studio API & Auth Tests -- HTTP-level integration tests for the
# Unsloth API & Auth Tests -- HTTP-level integration tests for the
# FastAPI surface. No Playwright, no model UI; tests/studio/test_studio_api_smoke.py
# runs ~30 s and asserts:
# - CORS hardening (no wildcard + credentials, no bootstrap leak)
@ -15,7 +15,7 @@
# Reuses the GGUF cache key from studio-ui-smoke.yml so the model
# download is one cache-hit on the second job.
name: Studio API CI
name: Unsloth API CI
on:
pull_request:
@ -40,7 +40,7 @@ permissions:
jobs:
api-smoke:
name: Studio API & Auth Tests
name: Unsloth API & Auth Tests
runs-on: ubuntu-latest
timeout-minutes: 12
env:
@ -98,7 +98,7 @@ jobs:
path: hf-cache
key: ${{ runner.os }}-hf-${{ env.GGUF_REPO }}-${{ env.GGUF_VARIANT }}-v2
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Withheld on PR: this step runs checked-out PR code; public GGUF still downloads.
@ -111,7 +111,7 @@ jobs:
- name: Install pyjwt for the JWT-expiry forge test
run: pip install 'pyjwt>=2.6'
- name: Reset auth + boot Studio (API-only)
- name: Reset auth + boot Unsloth (API-only)
run: |
unsloth studio reset-password
mkdir -p logs
@ -144,7 +144,7 @@ jobs:
echo "STUDIO_NEW_PW=$NEW" >> "$GITHUB_ENV"
echo "STUDIO_NEW2_PW=$NEW2" >> "$GITHUB_ENV"
- name: Run Studio API & Auth tests
- name: Run Unsloth API & Auth tests
# The script is named WITHOUT a `test_` prefix so it isn't
# auto-collected by pytest in Backend CI's `tests/` walk
# (which doesn't set BASE_URL and would crash at import).
@ -153,7 +153,7 @@ jobs:
STUDIO_AUTH_DIR: /home/runner/.unsloth/studio/auth
run: python tests/studio/studio_api_smoke.py
- name: Stop Studio
- name: Stop Unsloth
if: always()
run: |
kill "${STUDIO_PID}" 2>/dev/null || true

2
.github/workflows/studio-backend-ci.yml vendored
View file

@ -69,7 +69,7 @@ jobs:
- name: Install backend test dependencies (CPU only)
run: |
python -m pip install --upgrade pip
# Studio's declared backend deps:
# Unsloth's declared backend deps:
pip install -r studio/backend/requirements/studio.txt
# Extras that studio.txt does not list but the import chain needs
# (python-multipart for FastAPI form/file uploads, sqlalchemy/cryptography

2
.github/workflows/studio-export-capability-ci.yml vendored
View file

@ -9,7 +9,7 @@
# export is validated separately. No GPU / model / llama.cpp: the tests mock the probes and block
# torch/unsloth, so the job installs only a CPU PyTorch plus import deps.
name: Studio export capability
name: Unsloth export capability
on:
pull_request:

4
.github/workflows/studio-frontend-ci.yml vendored
View file

@ -136,7 +136,7 @@ jobs:
- name: Build
run: npm run build
- name: Built bundle must not contain Studio's unstable_Provider call site
- name: Built bundle must not contain Unsloth's unstable_Provider call site
run: |
set -e
JS=$(ls dist/assets/index-*.js | head -1)
@ -144,7 +144,7 @@ jobs:
echo "main bundle: $JS"
echo "unstable_Provider: hits=$HITS (assistant-ui internals contribute up to 3)"
if [ "$HITS" -gt 3 ]; then
echo "::error file=studio/frontend/src/features/chat/runtime-provider.tsx::Studio bundle still passes unstable_Provider through useRemoteThreadListRuntime; this is the 2026.5.1 chat-history regression. Pass adapters directly into useLocalRuntime instead."
echo "::error file=studio/frontend/src/features/chat/runtime-provider.tsx::Unsloth bundle still passes unstable_Provider through useRemoteThreadListRuntime; this is the 2026.5.1 chat-history regression. Pass adapters directly into useLocalRuntime instead."
exit 1
fi

56
.github/workflows/studio-inference-smoke.yml vendored
View file

@ -1,7 +1,7 @@
# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
# Three end-to-end smoke jobs that boot a freshly-installed Studio and
# Three end-to-end smoke jobs that boot a freshly-installed Unsloth and
# exercise the surfaces real users hit through the OpenAI / Anthropic
# SDKs and curl. Each job picks the smallest model that exercises the
# behaviour under test, primes HF_HOME via actions/cache, and shares
@ -27,7 +27,7 @@
# All three jobs run in parallel. Total wall time is dominated by job 3
# on a cold cache; warm cache cuts that to ~3 min.
name: Studio GGUF CI
name: Unsloth GGUF CI
on:
pull_request:
@ -112,7 +112,7 @@ jobs:
path: hf-cache
key: ${{ runner.os }}-hf-${{ env.GGUF_REPO }}-${{ env.GGUF_VARIANT }}-v2
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Withheld on PR: this step runs checked-out PR code; public GGUF still downloads.
@ -125,7 +125,7 @@ jobs:
- name: Install OpenAI + Anthropic Python SDKs
run: pip install 'openai>=1.50' 'anthropic>=0.40'
- name: Reset auth + boot Studio (API-only)
- name: Reset auth + boot Unsloth (API-only)
run: |
unsloth studio reset-password
mkdir -p logs
@ -142,7 +142,7 @@ jobs:
fi
sleep 1
done
echo "Studio did not become healthy in 180s"
echo "Unsloth did not become healthy in 180s"
tail -200 logs/studio.log
exit 1
@ -229,11 +229,11 @@ jobs:
return replies
def run_anthropic():
# Two SDK quirks vs. Studio:
# Two SDK quirks vs. Unsloth:
# 1. base_url must NOT include /v1 -- the SDK appends
# /v1/messages itself; otherwise the request hits
# /v1/v1/messages and 405s.
# 2. The SDK sends `x-api-key` by default, but Studio's
# 2. The SDK sends `x-api-key` by default, but Unsloth's
# auth layer is HTTPBearer-only. Override via
# default_headers so Authorization: Bearer ... is
# sent instead.
@ -276,7 +276,7 @@ jobs:
print(
f"[{label}] WARN non-determinism at temperature=0.0 across "
f"{len(determinism_failures)} of {len(first)} turn(s); "
f"small-quant model drift, not a Studio regression. "
f"small-quant model drift, not an Unsloth regression. "
f"Details: " + " | ".join(determinism_failures)
)
# Sanity: turn-2 reply should mention the earlier question, and
@ -290,7 +290,7 @@ jobs:
print(f"[{label}] {status_word} -- 4 turns, history grounded ('paris' present)")
PY
- name: Stop Studio
- name: Stop Unsloth
if: always()
run: |
kill "${STUDIO_PID}" 2>/dev/null || true
@ -323,7 +323,7 @@ jobs:
# store xet chunks + blobs + snapshots = ~4 GiB compressed --
# 4-5x file-size inflation, dominated by xet chunks. Use main's
# `--local-dir gguf-cache` pattern to cache the flat .gguf only.
# Studio's /api/inference/load accepts either a HF repo (which
# Unsloth's /api/inference/load accepts either a HF repo (which
# uses HF_HOME) or an absolute file path; passing the absolute
# path keeps the test off HF_HOME entirely so the cache size
# tracks the GGUF file 1:1. The OpenAI/Anth and JSON+images
@ -380,7 +380,7 @@ jobs:
path: gguf-cache
key: ${{ runner.os }}-gguf-${{ env.GGUF_REPO }}-${{ env.GGUF_FILE }}-v1
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Withheld on PR: this step runs checked-out PR code; public GGUF still downloads.
@ -390,7 +390,7 @@ jobs:
set -o pipefail
bash install.sh --local --no-torch 2>&1 | tee logs/install.log
- name: Reset auth + boot Studio (API-only, default tool policy)
- name: Reset auth + boot Unsloth (API-only, default tool policy)
# We deliberately use the API-only mode rather than
# `unsloth studio run` because the latter calls
# `set_tool_policy(...)` with a resolved bool: on loopback the
@ -503,7 +503,7 @@ jobs:
that the tool path executed.
A shared CI runner can stall the stream transport (the
connection opening, or a mid-stream read) even when Studio
connection opening, or a mid-stream read) even when Unsloth
is healthy, so retry a stall once with a fresh request
capped at 300s. A stall means the stream did NOT complete,
so partial events are normally NOT returned (an early
@ -575,11 +575,11 @@ jobs:
def _tool_invoked(events):
"""Structural check: True iff some SSE payload is a real
tool envelope (Studio tool_start/tool_end, Anthropic
tool envelope (Unsloth tool_start/tool_end, Anthropic
tool_use/tool_result, OpenAI non-empty delta.tool_calls /
message.tool_calls / finish_reason='tool_calls' /
role:'tool' / function_call). tool_status is NOT
evidence: Studio emits empty tool_status events on
evidence: Unsloth emits empty tool_status events on
iteration boundaries even when no tool ran.
"""
for raw in events:
@ -698,7 +698,7 @@ jobs:
attempt has structural invocation evidence. WARN (not
FAIL) if invoked but no attempt produces the expected
literal in tool_end.result -- small-quant Qwen3.5-2B can
emit OpenAI tool_calls deltas without Studio's GGUF
emit OpenAI tool_calls deltas without Unsloth's GGUF
agentic loop intercepting them, and that GGUF-vs-OpenAI
format mismatch is out of scope for #5642.
"""
@ -811,7 +811,7 @@ jobs:
# because (a) the search may legitimately return no results,
# and (b) DuckDuckGo upstream blocks GHA IP ranges often
# enough that requiring a tool_call marker would create
# red-herring failures from infra rather than from Studio.
# red-herring failures from infra rather than from Unsloth.
try:
# Best-effort and bounded: a single 180s attempt keeps a stall
# from eating the job's timeout-minutes (it already WARNs, so a
@ -834,7 +834,7 @@ jobs:
print(f"[tools] WARN web_search probe failed (non-blocking): {exc}")
# ── 5. Thinking on / off ─────────────────────────────────────
# Studio strips think blocks from message.content for tools-mode
# Unsloth strips think blocks from message.content for tools-mode
# responses, so we toggle plain chat (no enable_tools) and look
# at the surfaced reasoning_content / message.thinking field.
def thinking_call(enable):
@ -848,7 +848,7 @@ jobs:
})
assert status == 200
msg = data["choices"][0]["message"]
# Studio surfaces thinking via reasoning_content (OpenAI
# Unsloth surfaces thinking via reasoning_content (OpenAI
# extension). Fall back to inline <think> markers for
# robustness across template versions.
raw = (msg.get("content") or "") + (msg.get("reasoning_content") or "")
@ -868,7 +868,7 @@ jobs:
print(f"[tools] PASS thinking on/off (on={len(on_text)} chars, off={len(off_text)} chars)")
PY
- name: Stop Studio
- name: Stop Unsloth
if: always()
run: |
kill "${STUDIO_PID}" 2>/dev/null || true
@ -960,7 +960,7 @@ jobs:
path: hf-cache
key: ${{ runner.os }}-hf-${{ env.GGUF_REPO }}-${{ env.GGUF_VARIANT }}-${{ env.MMPROJ_FILE }}-v2
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Withheld on PR: this step runs checked-out PR code; public GGUF still downloads.
@ -973,7 +973,7 @@ jobs:
- name: Install OpenAI + Anthropic Python SDKs
run: pip install 'openai>=1.50' 'anthropic>=0.40'
- name: Reset auth + boot Studio (API-only)
- name: Reset auth + boot Unsloth (API-only)
# See Job 2's comment: API-only mode keeps tool_policy=None so
# response_format requests aren't routed through the agentic
# tool loop.
@ -1076,13 +1076,13 @@ jobs:
# llama.cpp's HTTP server supports OpenAI-compatible JSON
# mode: `response_format: {"type": "json_object"}` constrains
# the model to emit syntactically-valid JSON. We use raw HTTP
# rather than the OpenAI SDK so that the field shape Studio
# rather than the OpenAI SDK so that the field shape Unsloth
# forwards to llama-server is unambiguous (the SDK rewrites
# response_format depending on which variant it recognises).
# We deliberately do NOT pass a strict JSON schema -- on
# small Gemma-4 quants the GBNF-from-schema path occasionally
# produces empty output, and JSON mode is the surface we care
# about exposing through Studio.
# about exposing through Unsloth.
status, data = post("/v1/chat/completions", {
"model": "default",
"messages": [
@ -1112,7 +1112,7 @@ jobs:
print(f"[json] PASS json_object -> {parsed}")
# ── 2. OpenAI image_url (data URI base64) ───────────────────
# 64x64 solid-red PNG. stb_image (used by Studio's image
# 64x64 solid-red PNG. stb_image (used by Unsloth's image
# normaliser at routes/inference.py:3410) rejects 4x4 or
# smaller PNGs as truncated, so we go up to 64x64 -- still
# tiny in token cost. The assertion is loose: any non-empty
@ -1148,9 +1148,9 @@ jobs:
print("[image/openai] PASS image_url accepted, non-empty response")
# ── 3. Anthropic source/base64 image ────────────────────────
# Two SDK quirks vs. Studio: base_url must NOT include /v1
# Two SDK quirks vs. Unsloth: base_url must NOT include /v1
# (the SDK appends it itself; otherwise /v1/v1/messages -> 405),
# and Studio's auth is HTTPBearer-only so the SDK's default
# and Unsloth's auth is HTTPBearer-only so the SDK's default
# x-api-key header is ignored -- send Authorization: Bearer
# via default_headers.
anthropic = Anthropic(
@ -1184,7 +1184,7 @@ jobs:
print("[image/anthropic] PASS source/base64 accepted, non-empty response")
PY
- name: Stop Studio
- name: Stop Unsloth
if: always()
run: |
kill "${STUDIO_PID}" 2>/dev/null || true

4
.github/workflows/studio-load-orchestrator-ci.yml vendored
View file

@ -1,7 +1,7 @@
# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
#
# Event-loop regression test for the Studio model-load orchestrator.
# Event-loop regression test for the Unsloth model-load orchestrator.
# Pins down issue #5642 (Win10 UI freeze on model load): the /load
# route calls LlamaCppBackend.detect_audio_type synchronously, blocking
# the FastAPI event loop on a chain of sync httpx.Client.post() probes.
@ -14,7 +14,7 @@
# danielhanchen/unsloth-staging-2 (Ubuntu / macOS / Windows all
# green at PR time).
name: Studio load-orchestrator CI
name: Unsloth load-orchestrator CI
on:
pull_request:

10
.github/workflows/studio-mac-api-smoke.yml vendored
View file

@ -33,7 +33,7 @@ permissions:
jobs:
api-smoke:
name: Studio API & Auth Tests
name: Unsloth API & Auth Tests
runs-on: macos-14
timeout-minutes: 25
env:
@ -83,7 +83,7 @@ jobs:
path: hf-cache
key: ${{ runner.os }}-hf-${{ env.GGUF_REPO }}-${{ env.GGUF_VARIANT }}-v2
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Withheld on PR: this step runs checked-out PR code; public GGUF still downloads.
@ -99,7 +99,7 @@ jobs:
- name: Install pyjwt for the JWT-expiry forge test
run: pip install 'pyjwt>=2.6'
- name: Reset auth + boot Studio (API-only)
- name: Reset auth + boot Unsloth (API-only)
run: |
unsloth studio reset-password
mkdir -p logs
@ -129,13 +129,13 @@ jobs:
echo "STUDIO_NEW_PW=$NEW" >> "$GITHUB_ENV"
echo "STUDIO_NEW2_PW=$NEW2" >> "$GITHUB_ENV"
- name: Run Studio API & Auth tests
- name: Run Unsloth API & Auth tests
env:
BASE_URL: http://127.0.0.1:18895
STUDIO_AUTH_DIR: /Users/runner/.unsloth/studio/auth
run: python tests/studio/studio_api_smoke.py
- name: Stop Studio
- name: Stop Unsloth
if: always()
run: |
kill "${STUDIO_PID}" 2>/dev/null || true

58
.github/workflows/studio-mac-inference-smoke.yml vendored
View file

@ -1,7 +1,7 @@
# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
# Three end-to-end smoke jobs that boot a freshly-installed Studio and
# Three end-to-end smoke jobs that boot a freshly-installed Unsloth and
# exercise the surfaces real users hit through the OpenAI / Anthropic
# SDKs and curl. Each job picks the smallest model that exercises the
# behaviour under test, primes a model cache via actions/cache, and
@ -108,7 +108,7 @@ jobs:
path: hf-cache
key: ${{ runner.os }}-hf-${{ env.GGUF_REPO }}-${{ env.GGUF_VARIANT }}-v2
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Withheld on PR: this step runs checked-out PR code; public GGUF still downloads.
@ -124,7 +124,7 @@ jobs:
- name: Install OpenAI + Anthropic Python SDKs
run: pip install 'openai>=1.50' 'anthropic>=0.40'
- name: Reset auth + boot Studio (API-only)
- name: Reset auth + boot Unsloth (API-only)
run: |
unsloth studio reset-password
mkdir -p logs
@ -141,7 +141,7 @@ jobs:
fi
sleep 1
done
echo "Studio did not become healthy in 180s"
echo "Unsloth did not become healthy in 180s"
tail -200 logs/studio.log
exit 1
@ -228,11 +228,11 @@ jobs:
return replies
def run_anthropic():
# Two SDK quirks vs. Studio:
# Two SDK quirks vs. Unsloth:
# 1. base_url must NOT include /v1 -- the SDK appends
# /v1/messages itself; otherwise the request hits
# /v1/v1/messages and 405s.
# 2. The SDK sends `x-api-key` by default, but Studio's
# 2. The SDK sends `x-api-key` by default, but Unsloth's
# auth layer is HTTPBearer-only. Override via
# default_headers so Authorization: Bearer ... is
# sent instead.
@ -283,7 +283,7 @@ jobs:
print(f"[{label}] OK -- 4 turns, run1 == run2, history grounded")
PY
- name: Stop Studio
- name: Stop Unsloth
if: always()
run: |
kill "${STUDIO_PID}" 2>/dev/null || true
@ -363,7 +363,7 @@ jobs:
path: gguf-cache
key: ${{ runner.os }}-gguf-${{ env.GGUF_REPO }}-${{ env.GGUF_FILE }}-v1
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Withheld on PR: this step runs checked-out PR code; public GGUF still downloads.
@ -376,7 +376,7 @@ jobs:
- name: Assert llama.cpp loads on this macOS
run: bash .github/scripts/assert-llama-loads.sh
- name: Reset auth + boot Studio (API-only, default tool policy)
- name: Reset auth + boot Unsloth (API-only, default tool policy)
# We deliberately use the API-only mode rather than
# `unsloth studio run` because the latter calls
# `set_tool_policy(...)` with a resolved bool: on loopback the
@ -478,7 +478,7 @@ jobs:
call with enable_tools=true must use this helper.
A shared CI runner can stall the stream transport (the
connection opening, or a mid-stream read) even when Studio
connection opening, or a mid-stream read) even when Unsloth
is healthy, so harden the read three ways: retry a stall
once with a fresh request capped at 300s; return any text
already streamed before a stall (a stall on the trailing
@ -574,11 +574,11 @@ jobs:
assert status == 200, f"tool call status {status}: {data}"
choice = data["choices"][0]
tool_calls = (choice.get("message") or {}).get("tool_calls") or []
# Studio's contract: when tool_choice='required', llama.cpp's
# Unsloth's contract: when tool_choice='required', llama.cpp's
# grammar should force a tool_calls payload. On Mac that
# contract is sometimes broken by the underlying quant; the
# PASS path is "tool_calls present + correct schema", the
# WARN path documents Studio still returned 200 with a
# WARN path documents Unsloth still returned 200 with a
# well-formed choices[] envelope.
if tool_calls:
tc = tool_calls[0]
@ -660,7 +660,7 @@ jobs:
print(f"[tools] WARN web_search probe failed (non-blocking): {exc}")
# ── 4. Thinking on / off ─────────────────────────────────────
# Studio strips think blocks from message.content for tools-mode
# Unsloth strips think blocks from message.content for tools-mode
# responses, so we toggle plain chat (no enable_tools) and look
# at the surfaced reasoning_content / message.thinking field.
def thinking_call(enable):
@ -678,7 +678,7 @@ jobs:
}, timeout = 180)
assert status == 200
msg = data["choices"][0]["message"]
# Studio surfaces thinking via reasoning_content (OpenAI
# Unsloth surfaces thinking via reasoning_content (OpenAI
# extension). Fall back to inline <think> markers for
# robustness across template versions.
raw = (msg.get("content") or "") + (msg.get("reasoning_content") or "")
@ -704,7 +704,7 @@ jobs:
print(f"[tools] PASS thinking on/off (on={len(on_text)} chars, off={len(off_text)} chars)")
PY
- name: Stop Studio
- name: Stop Unsloth
if: always()
run: |
kill "${STUDIO_PID}" 2>/dev/null || true
@ -810,7 +810,7 @@ jobs:
path: gguf-cache
key: ${{ runner.os }}-gguf-${{ env.GGUF_REPO }}-${{ env.GGUF_FILE }}-${{ env.MMPROJ_FILE }}-v2
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Withheld on PR: this step runs checked-out PR code; public GGUF still downloads.
@ -826,7 +826,7 @@ jobs:
- name: Install OpenAI + Anthropic Python SDKs
run: pip install 'openai>=1.50' 'anthropic>=0.40'
- name: Reset auth + boot Studio (API-only)
- name: Reset auth + boot Unsloth (API-only)
# See Job 2's comment: API-only mode keeps tool_policy=None so
# response_format requests aren't routed through the agentic
# tool loop.
@ -929,13 +929,13 @@ jobs:
# llama.cpp's HTTP server supports OpenAI-compatible JSON
# mode: `response_format: {"type": "json_object"}` constrains
# the model to emit syntactically-valid JSON. We use raw HTTP
# rather than the OpenAI SDK so that the field shape Studio
# rather than the OpenAI SDK so that the field shape Unsloth
# forwards to llama-server is unambiguous (the SDK rewrites
# response_format depending on which variant it recognises).
# We deliberately do NOT pass a strict JSON schema -- on
# small Gemma-4 quants the GBNF-from-schema path occasionally
# produces empty output, and JSON mode is the surface we care
# about exposing through Studio.
# about exposing through Unsloth.
status, data = post("/v1/chat/completions", {
"model": "default",
"messages": [
@ -1007,7 +1007,7 @@ jobs:
)
# ── 2. OpenAI image_url (data URI base64) ───────────────────
# 64x64 solid-red PNG. stb_image (used by Studio's image
# 64x64 solid-red PNG. stb_image (used by Unsloth's image
# normaliser at routes/inference.py:3410) rejects 4x4 or
# smaller PNGs as truncated, so we go up to 64x64 -- still
# tiny in token cost. The assertion is loose: any non-empty
@ -1023,11 +1023,11 @@ jobs:
# The Mac prebuilt llama.cpp server has a known crash when
# processing image inputs alongside the gemma-4-E2B mmproj
# (server disconnects mid-completion). This is upstream
# llama.cpp behaviour, not Studio. Wrap both SDK calls in
# llama.cpp behaviour, not Unsloth. Wrap both SDK calls in
# try/except so an upstream crash registers as a WARN rather
# than failing the whole job. Studio's contract (OpenAI/
# than failing the whole job. Unsloth's contract (OpenAI/
# Anthropic image fields are accepted and forwarded) is
# validated by the request body Studio constructs, not by
# validated by the request body Unsloth constructs, not by
# whether llama.cpp can decode it on Mac Metal.
client = OpenAI(base_url = f"{BASE}/v1", api_key = KEY)
try:
@ -1053,14 +1053,14 @@ jobs:
except Exception as exc:
print(
f"[image/openai] WARN image_url SDK call raised: {type(exc).__name__}: "
f"{exc}. Likely upstream llama.cpp Mac+vision crash, NOT a Studio "
f"regression. Studio successfully forwarded the request."
f"{exc}. Likely upstream llama.cpp Mac+vision crash, NOT an Unsloth "
f"regression. Unsloth successfully forwarded the request."
)
# ── 3. Anthropic source/base64 image ────────────────────────
# Two SDK quirks vs. Studio: base_url must NOT include /v1
# Two SDK quirks vs. Unsloth: base_url must NOT include /v1
# (the SDK appends it itself; otherwise /v1/v1/messages -> 405),
# and Studio's auth is HTTPBearer-only so the SDK's default
# and Unsloth's auth is HTTPBearer-only so the SDK's default
# x-api-key header is ignored -- send Authorization: Bearer
# via default_headers.
anthropic = Anthropic(
@ -1099,11 +1099,11 @@ jobs:
print(
f"[image/anthropic] WARN anthropic image SDK call raised: "
f"{type(exc).__name__}: {exc}. Likely upstream llama.cpp Mac+vision "
f"crash, NOT a Studio regression."
f"crash, NOT an Unsloth regression."
)
PY
- name: Stop Studio
- name: Stop Unsloth
if: always()
run: |
kill "${STUDIO_PID}" 2>/dev/null || true

4
.github/workflows/studio-mac-install-matrix.yml vendored
View file

@ -1,7 +1,7 @@
# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
# Proves Studio's llama.cpp install loads on every supported macOS. The heavy
# Proves Unsloth's llama.cpp install loads on every supported macOS. The heavy
# app smokes stay single-OS; this matrix covers the OS-version dimension cheaply
# (install.sh + binary-load assert). Regression guard for the macOS-version
# selection in studio/install_llama_prebuilt.py.
@ -60,7 +60,7 @@ jobs:
with:
python-version: '3.12'
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Withheld on PR: this step runs checked-out PR code; public GGUF still downloads.

18
.github/workflows/studio-mac-ui-smoke.yml vendored
View file

@ -83,7 +83,7 @@ jobs:
path: hf-cache
key: ${{ runner.os }}-hf-${{ env.GGUF_REPO }}-${{ env.GGUF_VARIANT }}-v2
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Withheld on PR: this step runs checked-out PR code; public GGUF still downloads.
@ -143,7 +143,7 @@ jobs:
print(f"pipeTransport.js: patched JSON.parse calls in {path}")
PY
- name: Reset auth + boot Studio
- name: Reset auth + boot Unsloth
run: |
unsloth studio reset-password
mkdir -p logs
@ -188,7 +188,7 @@ jobs:
# dies mid-test, (2) Chromium net::ERR_NO_BUFFER_SPACE when the
# runner's kernel briefly runs out of socket buffers, and (3) a
# goto 'interrupted by another navigation' when the SPA auth
# guard redirects mid-navigation. The retry FULLY resets Studio
# guard redirects mid-navigation. The retry FULLY resets Unsloth
# (kill, reset-password, reboot, wait /api/health, re-export
# bootstrap pw) before re-running the script. A real test failure
# (assertion / timeout) does NOT match any pattern so it bypasses
@ -209,7 +209,7 @@ jobs:
|| grep -q "ERR_NO_BUFFER_SPACE" logs/playwright_attempt_${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..."
echo "::warning::Playwright flake on attempt ${attempt}; resetting Unsloth and retrying..."
kill "${STUDIO_PID}" 2>/dev/null || true
sleep 2
unsloth studio reset-password
@ -238,13 +238,13 @@ jobs:
exit "$rc"
done
- name: Stop Studio (chat-ui ends with Shutdown click; this is belt-and-suspenders)
- name: Stop Unsloth (chat-ui ends with Shutdown click; this is belt-and-suspenders)
if: always()
run: |
kill "${STUDIO_PID}" 2>/dev/null || true
sleep 2
- name: Reset auth + boot Studio for extra UI tests (port 18897)
- name: Reset auth + boot Unsloth for extra UI tests (port 18897)
run: |
unsloth studio reset-password
mkdir -p logs
@ -271,7 +271,7 @@ jobs:
echo "STUDIO_EXTRA_OLD_PW=$OLD" >> "$GITHUB_ENV"
echo "STUDIO_EXTRA_NEW_PW=$NEW" >> "$GITHUB_ENV"
- name: Drive Compare/Recipes/Export/Studio/Settings with Playwright
- name: Drive Compare/Recipes/Export/Unsloth/Settings with Playwright
env:
BASE_URL: http://127.0.0.1:18897
STUDIO_OLD_PW: ${{ env.STUDIO_EXTRA_OLD_PW }}
@ -300,7 +300,7 @@ jobs:
|| grep -q "ERR_NO_BUFFER_SPACE" logs/playwright_extra_attempt_${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..."
echo "::warning::Playwright flake on attempt ${attempt}; resetting Unsloth and retrying..."
kill "${STUDIO_EXTRA_PID}" 2>/dev/null || true
sleep 2
unsloth studio reset-password
@ -327,7 +327,7 @@ jobs:
exit "$rc"
done
- name: Stop second Studio
- name: Stop second Unsloth
if: always()
run: |
kill "${STUDIO_EXTRA_PID}" 2>/dev/null || true

16
.github/workflows/studio-mac-update-smoke.yml vendored
View file

@ -4,15 +4,15 @@
# Mac counterpart to studio-update-smoke.yml. Verifies that on a real
# Apple Silicon (macos-14, M1) runner:
#
# 1. install.sh --local --no-torch installs Studio AND auto-fetches
# 1. install.sh --local --no-torch installs Unsloth AND auto-fetches
# the prebuilt llama.cpp Mac binary (llama-bNNNN-bin-macos-arm64
# from ggml-org/llama.cpp). Hitting the source-build fallback is
# treated as an Unsloth bug -- Studio must always pick the
# treated as an Unsloth bug -- Unsloth must always pick the
# prebuilt on Mac.
# 2. unsloth studio update --local is idempotent. Two consecutive
# runs both report "prebuilt up to date and validated", no
# source-build fallback.
# 3. The installed Studio still boots and /api/health returns
# 3. The installed Unsloth still boots and /api/health returns
# healthy after the update path.
name: Mac Studio Update CI
@ -42,7 +42,7 @@ permissions:
jobs:
update-idempotency:
name: Studio Updating Tests
name: Unsloth Updating Tests
runs-on: macos-14
timeout-minutes: 30
steps:
@ -59,7 +59,7 @@ jobs:
python-version: '3.12'
cache: 'pip'
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Withheld on PR: this step runs checked-out PR code; public GGUF still downloads.
@ -106,7 +106,7 @@ jobs:
grep -qE "prebuilt up to date and validated|prebuilt installed and validated" logs/update2.log
echo "second update was clean"
- name: Boot Studio briefly to confirm the install is still usable
- name: Boot Unsloth briefly to confirm the install is still usable
run: |
mkdir -p logs
UNSLOTH_API_ONLY=1 unsloth studio -H 127.0.0.1 -p 18891 \
@ -123,13 +123,13 @@ jobs:
sleep 1
done
if [ -z "$HEALTHY" ]; then
echo "Studio failed to come up after \`update\`"
echo "Unsloth failed to come up after \`update\`"
tail -200 logs/studio.log
kill "$PID" 2>/dev/null || true
exit 1
fi
kill "$PID" 2>/dev/null || true
echo "post-update Studio /api/health OK"
echo "post-update Unsloth /api/health OK"
- name: Uninstall and verify clean
# Round-trip through scripts/uninstall.sh on real macOS. As a side

2
.github/workflows/studio-tauri-smoke.yml vendored
View file

@ -12,7 +12,7 @@
# stay in release-desktop.yml (manual `workflow_dispatch`) because they need
# code-signing secrets and ~30 min of runner time each.
name: Studio Tauri CI
name: Unsloth Tauri CI
on:
pull_request:

34
.github/workflows/studio-ui-smoke.yml vendored
View file

@ -1,8 +1,8 @@
# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
# End-to-end Studio chat UI smoke via Playwright + Chromium against a
# headless Linux runner. Boots Studio with the smallest GGUF
# End-to-end Unsloth chat UI smoke via Playwright + Chromium against a
# headless Linux runner. Boots Unsloth with the smallest GGUF
# (gemma-3-270m-it UD-Q4_K_XL, ~254 MiB), drives the actual frontend
# bundle, and asserts the full bootstrap-password / change-password /
# send-message / persist-on-reload journey works end to end.
@ -14,7 +14,7 @@
# frontend-only CI happily pass while the actual user-visible UI is
# broken (cf. the 2026.5.1 chat-history release).
name: Studio UI CI
name: Unsloth UI CI
on:
pull_request:
@ -97,7 +97,7 @@ jobs:
path: hf-cache
key: ${{ runner.os }}-hf-${{ env.GGUF_REPO }}-${{ env.GGUF_VARIANT }}-v2
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# Withheld on PR: this step runs checked-out PR code; public GGUF still downloads.
@ -115,7 +115,7 @@ jobs:
# warm runner.
python -m playwright install --with-deps chromium
- name: Reset auth + boot Studio
- name: Reset auth + boot Unsloth
run: |
unsloth studio reset-password
mkdir -p logs
@ -147,7 +147,7 @@ jobs:
# NEW + NEW2 are generated freshly per CI run via secrets.token_urlsafe
# rather than hardcoded. If a workflow gets compromised, the
# attacker can't replay a known-good rotated password against
# any future / parallel Studio install -- the rotated value
# any future / parallel Unsloth install -- the rotated value
# only ever exists for the lifetime of this single job, masked
# in the log via ::add-mask::.
run: |
@ -165,18 +165,18 @@ jobs:
env:
BASE_URL: http://127.0.0.1:18892
# The test file lives in the repo so it can be run locally
# against a freshly-installed Studio (BASE_URL=...; STUDIO_OLD_PW=
# against a freshly-installed Unsloth (BASE_URL=...; STUDIO_OLD_PW=
# $(cat ~/.unsloth/studio/auth/.bootstrap_password); python ...).
PW_ART_DIR: logs/playwright
# Strict mode: in CI a missing button / nav / dialog must
# FAIL the test. Locally the test still runs against partial
# Studio installs without STUDIO_UI_STRICT.
# Unsloth installs without STUDIO_UI_STRICT.
STUDIO_UI_STRICT: '1'
run: |
mkdir -p logs/playwright
python tests/studio/playwright_chat_ui.py
- name: Stop Studio (chat-ui ends with Shutdown click; this is belt-and-suspenders)
- name: Stop Unsloth (chat-ui ends with Shutdown click; this is belt-and-suspenders)
if: always()
run: |
kill "${STUDIO_PID}" 2>/dev/null || true
@ -184,10 +184,10 @@ jobs:
# The chat UI test ends by clicking the Shutdown menuitem, which
# leaves the server dead. The extra UI test (Compare / Recipes /
# Export / Studio / Settings) needs a fresh Studio, so we boot a
# Export / Unsloth / Settings) needs a fresh Unsloth, so we boot a
# second one on a different port. Boot is fast (~3-5s on the
# warm install we already did) so this adds little wall time.
- name: Reset auth + boot Studio for extra UI tests (port 18894)
- name: Reset auth + boot Unsloth for extra UI tests (port 18894)
run: |
unsloth studio reset-password
mkdir -p logs
@ -214,7 +214,7 @@ jobs:
echo "STUDIO_EXTRA_OLD_PW=$OLD" >> "$GITHUB_ENV"
echo "STUDIO_EXTRA_NEW_PW=$NEW" >> "$GITHUB_ENV"
- name: Drive Compare/Recipes/Export/Studio/Settings with Playwright
- name: Drive Compare/Recipes/Export/Unsloth/Settings with Playwright
env:
BASE_URL: http://127.0.0.1:18894
STUDIO_OLD_PW: ${{ env.STUDIO_EXTRA_OLD_PW }}
@ -227,16 +227,16 @@ jobs:
mkdir -p logs/playwright_extra
python tests/studio/playwright_extra_ui.py
- name: Stop second Studio
- name: Stop second Unsloth
if: always()
run: |
kill "${STUDIO_EXTRA_PID}" 2>/dev/null || true
sleep 2
# IME + multilingual paste regression (issue #5318 / PR #5327).
# Third Studio on its own port so a hang here cannot poison the
# Third Unsloth on its own port so a hang here cannot poison the
# earlier UI tests. No GGUF -- the bug surface is the composer.
- name: Reset auth + boot Studio for IME / i18n tests (port 18896)
- name: Reset auth + boot Unsloth for IME / i18n tests (port 18896)
run: |
unsloth studio reset-password
mkdir -p logs
@ -256,7 +256,7 @@ jobs:
- name: Pass bootstrap pw for IME / i18n test
# IME smoke does the change-password against the bootstrap that
# Studio's frontend injects into the page, so it only needs the
# Unsloth's frontend injects into the page, so it only needs the
# NEW password.
run: |
NEW="CIIme-$(python -c 'import secrets; print(secrets.token_urlsafe(16))')"
@ -273,7 +273,7 @@ jobs:
mkdir -p logs/playwright_ime
python tests/studio/playwright_chat_ime_i18n.py
- name: Stop third Studio
- name: Stop third Unsloth
if: always()
run: |
kill "${STUDIO_IME_PID}" 2>/dev/null || true

12
.github/workflows/studio-update-smoke.yml vendored
View file

@ -9,7 +9,7 @@
# This catches regressions in setup.sh's update path that the existing
# GGUF / wheel jobs would miss because they only invoke install.sh once.
name: Studio Update CI
name: Unsloth Update CI
on:
pull_request:
@ -36,7 +36,7 @@ permissions:
jobs:
update-idempotency:
name: Studio Updating Tests
name: Unsloth Updating Tests
runs-on: ubuntu-latest
timeout-minutes: 15
steps:
@ -63,7 +63,7 @@ jobs:
# post-step then fatal-errors with "Cache folder path is
# retrieved for pip but doesn't exist on disk".
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
# Pass the workflow token so the llama.cpp prebuilt installer's
# GitHub-API call to list releases isn't rate-limited (60/hr
# unauthenticated). Without this, three consecutive install +
@ -122,7 +122,7 @@ jobs:
grep -qE "prebuilt up to date and validated|prebuilt installed and validated" logs/update2.log
echo "second update was clean"
- name: Boot Studio briefly to confirm the install is still usable
- name: Boot Unsloth briefly to confirm the install is still usable
# If `update --local` accidentally broke the venv or wiped the
# llama-server binary, the server would fail to start here.
run: |
@ -138,13 +138,13 @@ jobs:
sleep 1
done
if ! jq -e '.status == "healthy"' /tmp/health.json 2>/dev/null; then
echo "Studio failed to come up after `update`"
echo "Unsloth failed to come up after `update`"
tail -200 logs/studio.log
kill "$PID" 2>/dev/null || true
exit 1
fi
kill "$PID" 2>/dev/null || true
echo "post-update Studio /api/health OK"
echo "post-update Unsloth /api/health OK"
- name: Uninstall and verify clean
# Round-trip the installer through scripts/uninstall.sh: confirms the

16
.github/workflows/studio-windows-api-smoke.yml vendored
View file

@ -9,7 +9,7 @@
# (Section 6) is Linux-only and short-circuits on non-POSIX; the rest
# is platform-portable.
name: Windows Studio API CI
name: Windows Unsloth API CI
on:
pull_request:
@ -34,7 +34,7 @@ permissions:
jobs:
api-smoke:
name: Studio API & Auth Tests
name: Unsloth API & Auth Tests
runs-on: windows-latest
timeout-minutes: 30
defaults:
@ -105,7 +105,7 @@ jobs:
# studio-windows-update-smoke.yml for the full rationale --
# creating an empty studio/frontend/dist trips setup.ps1's
# mtime-based staleness check into "frontend up to date, skip
# rebuild" and Studio boots with an empty dist directory.
# rebuild" and Unsloth boots with an empty dist directory.
# Add-MpPreference accepts paths that do not yet exist.
foreach ($p in @(
"$env:USERPROFILE\.unsloth",
@ -121,7 +121,7 @@ jobs:
}
}
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
shell: pwsh
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@ -161,7 +161,7 @@ jobs:
echo "install.ps1 installed the Windows prebuilt llama.cpp:"
cat "$INFO"
- name: Add Studio shim to GITHUB_PATH
- name: Add Unsloth shim to GITHUB_PATH
# install.ps1's User-PATH update doesn't propagate to a
# running Git Bash session; export the shim dir so the
# next `unsloth ...` invocation finds it.
@ -177,7 +177,7 @@ jobs:
- name: Install pyjwt for the JWT-expiry forge test
run: python -m pip install 'pyjwt>=2.6'
- name: Reset auth + boot Studio (API-only)
- name: Reset auth + boot Unsloth (API-only)
run: |
unsloth studio reset-password
mkdir -p logs
@ -207,7 +207,7 @@ jobs:
echo "STUDIO_NEW_PW=$NEW" >> "$GITHUB_ENV"
echo "STUDIO_NEW2_PW=$NEW2" >> "$GITHUB_ENV"
- name: Run Studio API & Auth tests
- name: Run Unsloth API & Auth tests
# Do NOT pin STUDIO_AUTH_DIR here. The Mac/Linux mirrors
# hardcode runner-specific paths (/Users/runner/...,
# /home/runner/...), but on Windows the path is
@ -219,7 +219,7 @@ jobs:
BASE_URL: http://127.0.0.1:18895
run: python tests/studio/studio_api_smoke.py
- name: Stop Studio
- name: Stop Unsloth
if: always()
run: |
kill "${STUDIO_PID}" 2>/dev/null || true

90
.github/workflows/studio-windows-inference-smoke.yml vendored
View file

@ -1,7 +1,7 @@
# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
# Three end-to-end smoke jobs that boot a freshly-installed Studio and
# Three end-to-end smoke jobs that boot a freshly-installed Unsloth and
# exercise the surfaces real users hit through the OpenAI / Anthropic
# SDKs and curl, on the FREE windows-latest runner. Each job picks the
# smallest model that exercises the behaviour under test, primes
@ -16,7 +16,7 @@
# Qwen3-VL-2B-Instruct UD-IQ2_XXS + mmproj-F16 (~1.4 GiB total).
# Within the 14 GB windows-latest SSD budget.
name: Windows Studio GGUF CI
name: Windows Unsloth GGUF CI
on:
pull_request:
@ -57,7 +57,7 @@ jobs:
STUDIO_PORT: '18888'
HF_HOME: ${{ github.workspace }}/hf-cache
# Force UTF-8 for stdio (Windows defaults to cp1252; hf
# download / Studio CLI print "✓" checkmarks and crash
# download / Unsloth CLI print "✓" checkmarks and crash
# otherwise).
PYTHONIOENCODING: utf-8
PYTHONUTF8: '1'
@ -160,7 +160,7 @@ jobs:
# studio-windows-update-smoke.yml for the full rationale --
# creating an empty studio/frontend/dist trips setup.ps1's
# mtime-based staleness check into "frontend up to date, skip
# rebuild" and Studio boots with an empty dist directory.
# rebuild" and Unsloth boots with an empty dist directory.
# Add-MpPreference accepts paths that do not yet exist.
foreach ($p in @(
"$env:USERPROFILE\.unsloth",
@ -176,7 +176,7 @@ jobs:
}
}
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
shell: pwsh
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@ -214,7 +214,7 @@ jobs:
echo "install.ps1 installed the Windows prebuilt llama.cpp:"
cat "$INFO"
- name: Add Studio shim to GITHUB_PATH
- name: Add Unsloth shim to GITHUB_PATH
run: |
SHIM_DIR=~/.unsloth/studio/bin
if [ ! -f "$SHIM_DIR/unsloth.exe" ]; then
@ -227,7 +227,7 @@ jobs:
- name: Install OpenAI + Anthropic Python SDKs
run: python -m pip install 'openai>=1.50' 'anthropic>=0.40'
- name: Reset auth + boot Studio (API-only)
- name: Reset auth + boot Unsloth (API-only)
run: |
unsloth studio reset-password
mkdir -p logs
@ -244,7 +244,7 @@ jobs:
fi
sleep 1
done
echo "Studio did not become healthy in 180s"
echo "Unsloth did not become healthy in 180s"
tail -200 logs/studio.log
exit 1
@ -281,7 +281,7 @@ jobs:
# Retry the load step a few times so a transient TCP RST during
# llama-server warm-up (Windows runner image churn,
# windows-latest -> windows-2025-vs2026 rollout) doesn't fail
# the whole job. The Studio backend's _wait_for_health now
# the whole job. The Unsloth backend's _wait_for_health now
# catches httpx.ReadError too; this retry layer covers the
# cases the backend can't recover from on its own.
LOAD_OK=0
@ -382,15 +382,15 @@ jobs:
print(f"[{label}] OK -- 4 turns, run1 == run2, history grounded")
PY
- name: Stop Studio
- name: Stop Unsloth
if: always()
# Run as cmd so we are not running through the Git Bash shell;
# Git Bash on windows-latest has been observed to exit 143
# (SIGTERM) from any inline kill/sleep block, masking a green
# test run. The runner reclaims the Studio child process at
# test run. The runner reclaims the Unsloth child process at
# job end either way, so just emit a marker and exit 0.
shell: cmd
run: echo Stop Studio (no-op; runner reclaims STUDIO_PID=%STUDIO_PID% at job end)
run: echo Stop Unsloth (no-op; runner reclaims STUDIO_PID=%STUDIO_PID% at job end)
- name: Collect llama-server logs
if: always()
@ -398,10 +398,10 @@ jobs:
# copy must not fail an otherwise-green job.
continue-on-error: true
shell: bash
# Copy llama-server's own stdout/stderr (teed by Studio under
# Copy llama-server's own stdout/stderr (teed by Unsloth under
# ~/.unsloth/studio/logs/llama-server/) into the workspace so
# upload-artifact can pick it up. Crucial for diagnosing a
# subprocess crash where Studio's traceback only shows the
# subprocess crash where Unsloth's traceback only shows the
# symptom (httpx ReadError) but not the cause.
run: |
mkdir -p logs/llama-server
@ -439,14 +439,14 @@ jobs:
# (211 s on first run; subsequent runs hit the cache, but the
# one-time cost recurs every time the cache key bumps). Use
# main's `--local-dir gguf-cache` pattern: cache the flat .gguf
# only, pass an absolute path to Studio's /api/inference/load.
# only, pass an absolute path to Unsloth's /api/inference/load.
# The OpenAI/Anth and JSON+images jobs still cover the
# gguf_variant resolution path.
GGUF_REPO: unsloth/Qwen3.5-2B-GGUF
GGUF_FILE: Qwen3.5-2B-UD-Q4_K_XL.gguf
STUDIO_PORT: '18898'
# Force UTF-8 for stdio (Windows defaults to cp1252; hf
# download / Studio CLI print "✓" checkmarks and crash
# download / Unsloth CLI print "✓" checkmarks and crash
# otherwise).
PYTHONIOENCODING: utf-8
PYTHONUTF8: '1'
@ -507,7 +507,7 @@ jobs:
# studio-windows-update-smoke.yml for the full rationale --
# creating an empty studio/frontend/dist trips setup.ps1's
# mtime-based staleness check into "frontend up to date, skip
# rebuild" and Studio boots with an empty dist directory.
# rebuild" and Unsloth boots with an empty dist directory.
# Add-MpPreference accepts paths that do not yet exist.
foreach ($p in @(
"$env:USERPROFILE\.unsloth",
@ -523,7 +523,7 @@ jobs:
}
}
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
shell: pwsh
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@ -561,7 +561,7 @@ jobs:
echo "install.ps1 installed the Windows prebuilt llama.cpp:"
cat "$INFO"
- name: Add Studio shim to GITHUB_PATH
- name: Add Unsloth shim to GITHUB_PATH
run: |
SHIM_DIR=~/.unsloth/studio/bin
if [ ! -f "$SHIM_DIR/unsloth.exe" ]; then
@ -571,7 +571,7 @@ jobs:
fi
cygpath -w "$SHIM_DIR" >> "$GITHUB_PATH"
- name: Reset auth + boot Studio (API-only, default tool policy)
- name: Reset auth + boot Unsloth (API-only, default tool policy)
run: |
unsloth studio reset-password
mkdir -p logs
@ -607,7 +607,7 @@ jobs:
# raw string, but we cannot embed `\a` etc. in JSON without
# JSON-string-escaping every backslash. Replace `\` with `/`
# via bash parameter expansion -- pathlib.Path on Windows
# accepts forward slashes natively, so Studio's loader sees
# accepts forward slashes natively, so Unsloth's loader sees
# a normal path.
GGUF_PATH="${GITHUB_WORKSPACE//\\//}/gguf-cache/${GGUF_FILE}"
ls -lh "$GGUF_PATH"
@ -680,7 +680,7 @@ jobs:
def post_sse(path, body, *, timeout = 600, retries = 1, soft = False):
# The server-side agentic loop always answers over SSE. A
# shared CI runner can stall the stream transport (the
# connection opening, or a mid-stream read) even when Studio
# connection opening, or a mid-stream read) even when Unsloth
# is healthy, so harden the read three ways:
# * retry a transport stall once with a fresh request,
# capped at 300s (a healthy server answers a retry
@ -882,15 +882,15 @@ jobs:
print(f"[tools] PASS thinking on/off (on={len(on_text)} chars, off={len(off_text)} chars)")
PY
- name: Stop Studio
- name: Stop Unsloth
if: always()
# Run as cmd so we are not running through the Git Bash shell;
# Git Bash on windows-latest has been observed to exit 143
# (SIGTERM) from any inline kill/sleep block, masking a green
# test run. The runner reclaims the Studio child process at
# test run. The runner reclaims the Unsloth child process at
# job end either way, so just emit a marker and exit 0.
shell: cmd
run: echo Stop Studio (no-op; runner reclaims STUDIO_PID=%STUDIO_PID% at job end)
run: echo Stop Unsloth (no-op; runner reclaims STUDIO_PID=%STUDIO_PID% at job end)
- name: Collect llama-server logs
if: always()
@ -898,10 +898,10 @@ jobs:
# copy must not fail an otherwise-green job.
continue-on-error: true
shell: bash
# Copy llama-server's own stdout/stderr (teed by Studio under
# Copy llama-server's own stdout/stderr (teed by Unsloth under
# ~/.unsloth/studio/logs/llama-server/) into the workspace so
# upload-artifact can pick it up. Crucial for diagnosing a
# subprocess crash where Studio's traceback only shows the
# subprocess crash where Unsloth's traceback only shows the
# symptom (httpx ReadError) but not the cause.
run: |
mkdir -p logs/llama-server
@ -939,7 +939,7 @@ jobs:
STUDIO_PORT: '18899'
HF_HOME: ${{ github.workspace }}/hf-cache
# Force UTF-8 for stdio (Windows defaults to cp1252; hf
# download / Studio CLI print "✓" checkmarks and crash
# download / Unsloth CLI print "✓" checkmarks and crash
# otherwise).
PYTHONIOENCODING: utf-8
PYTHONUTF8: '1'
@ -1005,7 +1005,7 @@ jobs:
# studio-windows-update-smoke.yml for the full rationale --
# creating an empty studio/frontend/dist trips setup.ps1's
# mtime-based staleness check into "frontend up to date, skip
# rebuild" and Studio boots with an empty dist directory.
# rebuild" and Unsloth boots with an empty dist directory.
# Add-MpPreference accepts paths that do not yet exist.
foreach ($p in @(
"$env:USERPROFILE\.unsloth",
@ -1021,7 +1021,7 @@ jobs:
}
}
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
shell: pwsh
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@ -1059,7 +1059,7 @@ jobs:
echo "install.ps1 installed the Windows prebuilt llama.cpp:"
cat "$INFO"
- name: Add Studio shim to GITHUB_PATH
- name: Add Unsloth shim to GITHUB_PATH
run: |
SHIM_DIR=~/.unsloth/studio/bin
if [ ! -f "$SHIM_DIR/unsloth.exe" ]; then
@ -1072,7 +1072,7 @@ jobs:
- name: Install OpenAI + Anthropic Python SDKs
run: python -m pip install 'openai>=1.50' 'anthropic>=0.40'
- name: Reset auth + boot Studio (API-only)
- name: Reset auth + boot Unsloth (API-only)
run: |
unsloth studio reset-password
mkdir -p logs
@ -1262,7 +1262,7 @@ jobs:
except Exception as exc:
print(
f"[image/openai] WARN image_url SDK call raised: {type(exc).__name__}: "
f"{exc}. Studio successfully forwarded the request; failure here is "
f"{exc}. Unsloth successfully forwarded the request; failure here is "
f"upstream llama.cpp vision behaviour."
)
@ -1303,19 +1303,19 @@ jobs:
print(
f"[image/anthropic] WARN anthropic image SDK call raised: "
f"{type(exc).__name__}: {exc}. Likely upstream llama.cpp vision "
f"behaviour, NOT a Studio regression."
f"behaviour, NOT an Unsloth regression."
)
PY
- name: Stop Studio
- name: Stop Unsloth
if: always()
# Run as cmd so we are not running through the Git Bash shell;
# Git Bash on windows-latest has been observed to exit 143
# (SIGTERM) from any inline kill/sleep block, masking a green
# test run. The runner reclaims the Studio child process at
# test run. The runner reclaims the Unsloth child process at
# job end either way, so just emit a marker and exit 0.
shell: cmd
run: echo Stop Studio (no-op; runner reclaims STUDIO_PID=%STUDIO_PID% at job end)
run: echo Stop Unsloth (no-op; runner reclaims STUDIO_PID=%STUDIO_PID% at job end)
- name: Collect llama-server logs
if: always()
@ -1323,10 +1323,10 @@ jobs:
# copy must not fail an otherwise-green job.
continue-on-error: true
shell: bash
# Copy llama-server's own stdout/stderr (teed by Studio under
# Copy llama-server's own stdout/stderr (teed by Unsloth under
# ~/.unsloth/studio/logs/llama-server/) into the workspace so
# upload-artifact can pick it up. Crucial for diagnosing a
# subprocess crash where Studio's traceback only shows the
# subprocess crash where Unsloth's traceback only shows the
# symptom (httpx ReadError) but not the cause.
run: |
mkdir -p logs/llama-server
@ -1348,7 +1348,7 @@ jobs:
# ── folded from studio-windows-no-vs-smoke.yml: install + run with no Visual Studio ──
no-vs-cpu:
name: Studio install + inference without Visual Studio
name: Unsloth install + inference without Visual Studio
runs-on: windows-latest
timeout-minutes: 35
defaults:
@ -1502,7 +1502,7 @@ jobs:
python -m pip install torch --index-url https://download.pytorch.org/whl/cpu --extra-index-url https://pypi.org/simple
python -c "import torch; print('torch', torch.__version__, 'cuda?', torch.cuda.is_available())"
- name: Install Studio (--local, --no-torch) with no build tools present
- name: Install Unsloth (--local, --no-torch) with no build tools present
shell: pwsh
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@ -1538,13 +1538,13 @@ jobs:
echo "Prebuilt installed with no build tools:"
cat "$INFO"
- name: Add Studio shim to GITHUB_PATH
- name: Add Unsloth shim to GITHUB_PATH
run: |
SHIM_DIR=~/.unsloth/studio/bin
[ -f "$SHIM_DIR/unsloth.exe" ] || { echo "::error::unsloth.exe shim not found"; ls -la ~/.unsloth/studio/ || true; exit 1; }
cygpath -w "$SHIM_DIR" >> "$GITHUB_PATH"
- name: Reset auth + boot Studio (API-only)
- name: Reset auth + boot Unsloth (API-only)
run: |
unsloth studio reset-password
mkdir -p logs
@ -1613,10 +1613,10 @@ jobs:
}
Remove-Item -LiteralPath $root -Recurse -Force -ErrorAction SilentlyContinue
- name: Stop Studio
- name: Stop Unsloth
if: always()
shell: cmd
run: echo Stop Studio (no-op; runner reclaims STUDIO_PID=%STUDIO_PID% at job end)
run: echo Stop Unsloth (no-op; runner reclaims STUDIO_PID=%STUDIO_PID% at job end)
- name: Collect llama-server logs
if: always()

32
.github/workflows/studio-windows-ui-smoke.yml vendored
View file

@ -4,11 +4,11 @@
# Windows counterpart to studio-ui-smoke.yml / studio-mac-ui-smoke.yml.
# Same Playwright + Chromium end-to-end chat UI flow + extra UI flow,
# but on the FREE windows-latest runner so we catch Windows-specific
# regressions in the install path (install.ps1), the Studio CLI's
# regressions in the install path (install.ps1), the Unsloth CLI's
# Windows process-management branches, and the llama.cpp prebuilt's
# Windows HTTP layer.
name: Windows Studio UI CI
name: Windows Unsloth UI CI
on:
pull_request:
@ -49,7 +49,7 @@ jobs:
GGUF_FILE: gemma-3-270m-it-UD-Q4_K_XL.gguf
STUDIO_PORT: '18896'
HF_HOME: ${{ github.workspace }}/hf-cache
# Force UTF-8 for stdio so Python tools (hf download, Studio
# Force UTF-8 for stdio so Python tools (hf download, Unsloth
# CLI, etc.) can print Unicode characters like the success
# checkmark "✓". Windows defaults to cp1252 / charmap and
# any tool that prints "OK ✓" hits a UnicodeEncodeError.
@ -121,7 +121,7 @@ jobs:
# studio-windows-update-smoke.yml for the full rationale --
# creating an empty studio/frontend/dist trips setup.ps1's
# mtime-based staleness check into "frontend up to date, skip
# rebuild" and Studio boots with an empty dist directory.
# rebuild" and Unsloth boots with an empty dist directory.
# Add-MpPreference accepts paths that do not yet exist.
foreach ($p in @(
"$env:USERPROFILE\.unsloth",
@ -148,7 +148,7 @@ jobs:
Set-Content -LiteralPath (Join-Path $appDir 'launch-studio.vbs') -Value 'WScript.Echo "legacy"' -Encoding Unicode
Write-Host "seeded legacy launch-studio.vbs at $appDir"
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
# install.ps1 is the supported Windows installer. install.sh
# has no Windows branch (apt-get / brew calls). The PS1
# script's `Install-UnslothStudio @args` line at the bottom
@ -205,7 +205,7 @@ jobs:
echo "install.ps1 installed the Windows prebuilt llama.cpp:"
cat "$INFO"
- name: Assert Studio launcher chain (no VBS, hidden PowerShell shortcut)
- name: Assert Unsloth launcher chain (no VBS, hidden PowerShell shortcut)
# The shortcut launch path is otherwise untested here (the steps below
# boot `unsloth studio` directly). Guard against re-introducing the VBS
# that tripped Kaspersky HEUR:Trojan.VBS.Agent.gen and against the .lnk
@ -234,7 +234,7 @@ jobs:
}
Write-Host "launcher chain OK (no VBS; hidden powershell over launch-studio.ps1)"
- name: Launch Studio via the shortcut and assert health
- name: Launch Unsloth via the shortcut and assert health
# Run the exact command the .lnk stores (hidden PowerShell over
# launch-studio.ps1) and confirm it brings the backend up. This is the
# only step that proves the shortcut launch is not silently broken.
@ -265,10 +265,10 @@ jobs:
$owner = (Get-NetTCPConnection -LocalPort $foundPort -State Listen -ErrorAction Stop | Select-Object -First 1).OwningProcess
if ($owner) { taskkill /PID $owner /T /F 2>$null | Out-Null }
} catch {}
if (-not $foundPort) { throw "Studio did not become healthy when launched via the shortcut" }
Write-Host "Studio healthy on port $foundPort (launched via the shortcut)"
if (-not $foundPort) { throw "Unsloth did not become healthy when launched via the shortcut" }
Write-Host "Unsloth healthy on port $foundPort (launched via the shortcut)"
- name: Add Studio shim to GITHUB_PATH
- name: Add Unsloth shim to GITHUB_PATH
# install.ps1 puts unsloth.exe at $StudioHome\bin\unsloth.exe
# and adds that dir to the User PATH via the Windows registry.
# Registry-level PATH updates don't propagate to a running
@ -284,7 +284,7 @@ jobs:
fi
# GITHUB_PATH wants Windows-style paths; convert via cygpath.
cygpath -w "$SHIM_DIR" >> "$GITHUB_PATH"
echo "Added Studio shim dir to PATH: $(cygpath -w "$SHIM_DIR")"
echo "Added Unsloth shim dir to PATH: $(cygpath -w "$SHIM_DIR")"
- name: Install Playwright + Chromium
# No --with-deps on Windows: that flag installs Linux apt
@ -294,7 +294,7 @@ jobs:
python -m pip install 'playwright>=1.45'
python -m playwright install chromium
- name: Reset auth + boot Studio
- name: Reset auth + boot Unsloth
run: |
unsloth studio reset-password
mkdir -p logs
@ -339,13 +339,13 @@ jobs:
mkdir -p logs/playwright
python tests/studio/playwright_chat_ui.py
- name: Stop Studio (chat-ui ends with Shutdown click; this is belt-and-suspenders)
- name: Stop Unsloth (chat-ui ends with Shutdown click; this is belt-and-suspenders)
if: always()
run: |
kill "${STUDIO_PID}" 2>/dev/null || true
sleep 2
- name: Reset auth + boot Studio for extra UI tests (port 18897)
- name: Reset auth + boot Unsloth for extra UI tests (port 18897)
run: |
unsloth studio reset-password
mkdir -p logs
@ -372,7 +372,7 @@ jobs:
echo "STUDIO_EXTRA_OLD_PW=$OLD" >> "$GITHUB_ENV"
echo "STUDIO_EXTRA_NEW_PW=$NEW" >> "$GITHUB_ENV"
- name: Drive Compare/Recipes/Export/Studio/Settings with Playwright
- name: Drive Compare/Recipes/Export/Unsloth/Settings with Playwright
env:
BASE_URL: http://127.0.0.1:18897
STUDIO_OLD_PW: ${{ env.STUDIO_EXTRA_OLD_PW }}
@ -386,7 +386,7 @@ jobs:
mkdir -p logs/playwright_extra
python tests/studio/playwright_extra_ui.py
- name: Stop second Studio
- name: Stop second Unsloth
if: always()
run: |
kill "${STUDIO_EXTRA_PID}" 2>/dev/null || true

26
.github/workflows/studio-windows-update-smoke.yml vendored
View file

@ -5,19 +5,19 @@
# studio-mac-update-smoke.yml. Verifies that on the FREE
# windows-latest runner:
#
# 1. install.ps1 --local --no-torch installs Studio AND auto-fetches
# 1. install.ps1 --local --no-torch installs Unsloth AND auto-fetches
# the prebuilt llama.cpp Windows binary (app-<tag>-windows-x64-cpu
# from unslothai/llama.cpp). Hitting the source-build fallback is
# treated as an Unsloth bug -- Studio must always pick the
# treated as an Unsloth bug -- Unsloth must always pick the
# prebuilt on Windows.
# 2. unsloth studio update --local is idempotent. Two consecutive
# runs both report "prebuilt up to date and validated", no
# source-build fallback. The CLI's _find_setup_script picks
# setup.ps1 on Windows automatically.
# 3. The installed Studio still boots and /api/health returns
# 3. The installed Unsloth still boots and /api/health returns
# healthy after the update path.
name: Windows Studio Update CI
name: Windows Unsloth Update CI
on:
pull_request:
@ -45,7 +45,7 @@ permissions:
jobs:
update-idempotency:
name: Studio Updating Tests
name: Unsloth Updating Tests
runs-on: windows-latest
timeout-minutes: 30
defaults:
@ -53,7 +53,7 @@ jobs:
shell: bash
env:
# Force UTF-8 for stdio (Windows defaults to cp1252; hf
# download / Studio CLI print "✓" checkmarks and crash
# download / Unsloth CLI print "✓" checkmarks and crash
# otherwise).
PYTHONIOENCODING: utf-8
PYTHONUTF8: '1'
@ -90,7 +90,7 @@ jobs:
# reuses the existing Node with no download.
#
# (2) Defender. windows-latest's real-time scan opens / hashes
# every file Studio writes during install (Vite output =
# every file Unsloth writes during install (Vite output =
# thousands of small chunks, uv pip = wheel-extraction =
# thousands of small files). The latency dominates the
# 200 s frontend build and the 90 s deps install. Adding
@ -109,7 +109,7 @@ jobs:
# setup.ps1 line 1281-1296's mtime-based "is the frontend
# stale?" check into "up to date, skip rebuild", because the
# newly-created dist's mtime is younger than every source
# file. Studio then boots with an empty dist and 500s on
# file. Unsloth then boots with an empty dist and 500s on
# GET / with FileNotFoundError: dist\index.html. See run
# 25546676715 / job 74984469728.
# Add-MpPreference accepts paths that do not yet exist; the
@ -129,7 +129,7 @@ jobs:
}
}
- name: Install Studio (--local, --no-torch)
- name: Install Unsloth (--local, --no-torch)
shell: pwsh
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@ -168,7 +168,7 @@ jobs:
echo "install.ps1 installed the Windows prebuilt llama.cpp:"
cat "$INFO"
- name: Add Studio shim to GITHUB_PATH
- name: Add Unsloth shim to GITHUB_PATH
run: |
SHIM_DIR=~/.unsloth/studio/bin
if [ ! -f "$SHIM_DIR/unsloth.exe" ]; then
@ -212,7 +212,7 @@ jobs:
grep -qE "prebuilt up to date and validated|prebuilt installed and validated" logs/update2.log
echo "second update was clean"
- name: Boot Studio briefly to confirm the install is still usable
- name: Boot Unsloth briefly to confirm the install is still usable
run: |
mkdir -p logs
UNSLOTH_API_ONLY=1 unsloth studio -H 127.0.0.1 -p 18891 \
@ -239,13 +239,13 @@ jobs:
sleep 1
done
if [ -z "$HEALTHY" ]; then
echo "Studio failed to come up after \`update\`"
echo "Unsloth failed to come up after \`update\`"
tail -200 logs/studio.log
kill "$PID" 2>/dev/null || true
exit 1
fi
kill "$PID" 2>/dev/null || true
echo "post-update Studio /api/health OK"
echo "post-update Unsloth /api/health OK"
- name: Uninstall and verify clean
# Round-trip through scripts/uninstall.ps1 against the default

10
.github/workflows/wheel-smoke.yml vendored
View file

@ -3,7 +3,7 @@
# Builds the PyPI wheel from the PR branch, then verifies the built wheel
# actually contains what we expect to ship and does NOT contain the broken
# Studio bundle that 2026.5.1 published. This is the single workflow that
# Unsloth bundle that 2026.5.1 published. This is the single workflow that
# would have blocked the 2026.5.1 release before twine upload.
#
# Verified locally end-to-end against this branch:
@ -12,7 +12,7 @@
# lockfile shipped, frontend dist shipped,
# no node_modules in wheel, no bun.lock in wheel,
# main bundle has unstable_Provider hits=1 (assistant-ui internals only).
# - Studio backend imports cleanly from the installed wheel with the
# - Unsloth backend imports cleanly from the installed wheel with the
# lightweight dep set below.
name: Wheel CI
@ -101,7 +101,7 @@ jobs:
hits = data.count("unstable_Provider:")
print(f"main bundle: {js[0]}")
print(f"unstable_Provider hits: {hits} (>=4 indicates 2026.5.1 regression)")
checks["bundle has no Studio unstable_Provider call site"] = (hits < 4)
checks["bundle has no Unsloth unstable_Provider call site"] = (hits < 4)
print()
for k, v in checks.items():
@ -109,7 +109,7 @@ jobs:
sys.exit(0 if all(checks.values()) else 1)
PY
- name: Studio backend import smoke
- name: Unsloth backend import smoke
# Imports `studio.backend.main:app` from the freshly-installed wheel in
# a clean venv. This catches the class of bug that 2026.5.1 shipped with:
# frontend dist missing, package-lock.json missing, or the wheel's Python
@ -125,7 +125,7 @@ jobs:
/tmp/v/bin/pip install --no-deps dist/unsloth-*.whl
# Run from /tmp so Python imports the installed package, not the source tree.
cd /tmp
/tmp/v/bin/python -c "from studio.backend.main import app; print('Studio backend OK:', app.title)"
/tmp/v/bin/python -c "from studio.backend.main import app; print('Unsloth backend OK:', app.title)"
- name: Upload wheel on failure
if: failure()