unslothai--unsloth/.github/workflows/lint-ci.yml

# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.

# Whole-repo, multi-language source-lint gate. Runs on every PR
# (no path filter) because each step is sub-second to a few seconds
# and together they catch a class of breakage the focused build
# workflows would miss:
#
#   - Python syntax + ruff + leftover debugger calls (across 350+
#     committed .py files, not just studio/backend).
#   - Shell `bash -n` parse for every committed *.sh.
#   - `yaml.safe_load` and `json.loads` round-trip for every
#     committed YAML / JSON config.
#
# TypeScript and Rust are NOT duplicated here on purpose:
#   - Studio 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
#     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
# fast-fail duplicate here would only burn cache; the dedicated
# workflows already block merges on Rust / TS regressions.

name: Lint CI

on:
  pull_request:
  push:
    branches: [main, pip]

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

permissions:
  contents: read

jobs:
  source-lint:
    name: Source lint (Python + shell + YAML + JSON + safety nets)
    runs-on: ubuntu-latest
    timeout-minutes: 5
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
        with:
          persist-credentials: false

      - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
        with:
          python-version: '3.12'
          cache: 'pip'

      # Pin ruff to match .pre-commit-config.yaml so a CI-only ruff
      # bump cannot disagree with what pre-commit accepted.
      # codespell is pinned for the same reason: a reviewer should
      # never see a typo report appear and disappear depending on
      # which codespell version the runner happened to install.
      - run: pip install 'ruff==0.15.12' 'pyyaml>=6' 'codespell>=2.3,<3'

      - name: Linux deps for shellcheck
        run: sudo apt-get update -qq && sudo apt-get install -y --no-install-recommends shellcheck

      - name: Python AST/syntax check (every committed .py must compile)
        # python -m compileall uses the same parser the interpreter
        # uses, so anything broken here would also crash at
        # `import X` on a user's machine. Sub-second across 350+
        # files. Hard gate.
        run: |
          python -m compileall -q -j 0 \
            unsloth unsloth_cli studio tests cli.py unsloth-cli.py

      - name: Python ruff check (whole repo)
        # The narrow rule set in pyproject.toml [tool.ruff.lint]
        # selects E9 / F63 / F7 / F82 -- syntax errors, broken
        # comparisons, undefined names. The whole repo passes today,
        # so this is a hard gate.
        run: |
          ruff check unsloth unsloth_cli studio tests cli.py unsloth-cli.py

      - name: Import-hoist verifier self-test
        # scripts/verify_import_hoist.py is a scope-aware (LEGB) AST
        # resolver that gates import-hoisting / alias-rename refactors
        # against two bugs ruff and pyflakes both miss:
        #   1. dangling alias  -- `from a import b as _b` hoisted to
        #      `from a import b` but a leftover `_b` reference now
        #      resolves to nothing (or to some other module-level `_b`).
        #   2. rename clash    -- `_b -> b` silently re-points at a
        #      different object already named `b` in that scope.
        # This step runs the tool's 8 negative-control cases so a
        # regression in the verifier itself fails before we trust it on
        # a diff. Hermetic, stdlib-only, sub-second. Hard gate.
        run: |
          python scripts/verify_import_hoist.py --self-test

      - name: Import-hoist / alias-rename safety (changed Python files)
        # Runs the verifier in compare mode on every in-place-modified
        # .py in the PR: parses each file BEFORE (base branch) and AFTER
        # (this diff), resolves every name load, and fails on a BLOCKER
        # (dangling alias / rename clash / re-pointed import). INFO
        # findings (a helper relocated to another file) do not fail.
        #
        # --diff-filter=M (in-place edits only) is deliberate: that is
        # exactly where a hoist refactor lives, and it skips brand-new
        # files whose re-export imports would otherwise look "unused".
        #
        # Diff against the true merge-base, not the base tip. A two-dot
        # diff against the tip re-lints every file the base branch
        # changed after the PR branched, comparing newer base code
        # (BEFORE) against the PR's older snapshot (AFTER) - a
        # time-reversed comparison that flags the base branch's own
        # refactors as blockers on PRs that never touched those files.
        # The compare API returns the merge-base without needing local
        # history, and fetching that single commit by SHA keeps the
        # shallow (fetch-depth: 1) clone.
        if: github.event_name == 'pull_request'
        env:
          GH_TOKEN: ${{ github.token }}
        run: |
          MERGE_BASE=$(gh api \
            "repos/${{ github.repository }}/compare/${{ github.event.pull_request.base.sha }}...${{ github.event.pull_request.head.sha }}" \
            --jq .merge_base_commit.sha)
          git fetch --no-tags --depth=1 origin "$MERGE_BASE"
          mapfile -t CHANGED < <(
            git diff --name-only --diff-filter=M \
              "$MERGE_BASE" HEAD -- '*.py' \
              | grep -vE '(^|/)(unsloth_compiled_cache|node_modules|build|dist)/' || true
          )
          if [ "${#CHANGED[@]}" -eq 0 ]; then
            echo "no in-place-modified Python files to check"
            exit 0
          fi
          printf 'merge base: %s\n' "$MERGE_BASE"
          printf 'checking %d file(s):\n' "${#CHANGED[@]}"
          printf '  %s\n' "${CHANGED[@]}"
          python scripts/verify_import_hoist.py \
            --before "$MERGE_BASE" --after HEAD "${CHANGED[@]}"

      - name: No leftover debugger / pdb / breakpoint calls
        # Catches the "I'll just stick a breakpoint() here" mistake
        # before it ships. AST-based so commented-out debugger
        # markers don't false-positive (a bare grep would; there
        # are three commented `# breakpoint()` markers in
        # unsloth/models/rl* today). Sub-second.
        run: |
          python <<'PY'
          import ast, pathlib, sys

          SKIP_PARTS = {".venv", "venv", "build", "dist", ".git",
                        "unsloth_compiled_cache", "node_modules",
                        "unsloth.egg-info"}

          bad = []
          scanned = 0
          for path in sorted(pathlib.Path(".").rglob("*.py")):
              if any(part in SKIP_PARTS for part in path.parts):
                  continue
              scanned += 1
              try:
                  tree = ast.parse(path.read_text(encoding="utf-8", errors="replace"))
              except SyntaxError:
                  continue   # compileall step above already failed this
              for node in ast.walk(tree):
                  if not isinstance(node, ast.Call):
                      continue
                  fn = node.func
                  if isinstance(fn, ast.Name) and fn.id == "breakpoint":
                      bad.append((path, node.lineno, "breakpoint()"))
                  elif (isinstance(fn, ast.Attribute) and fn.attr == "set_trace"
                        and isinstance(fn.value, ast.Name)
                        and fn.value.id in {"pdb", "ipdb"}):
                      bad.append((path, node.lineno, f"{fn.value.id}.set_trace()"))

          if bad:
              for path, lineno, what in bad:
                  print(f"::error file={path},line={lineno}::leftover {what} -- remove before merging")
              sys.exit(1)
          print(f"no leftover debugger calls (scanned {scanned} files)")
          PY

      - name: License-header drift (informational; whole repo)
        # Three header families are accepted across the repo:
        #   1. SPDX one-liner: `# SPDX-License-Identifier: ...`
        #      Used across studio/ (AGPL-3.0-only) and a few new
        #      files elsewhere.
        #   2. Apache-2.0 long form, marker phrase
        #      "Licensed under the Apache License". Used across
        #      unsloth/ and unsloth_cli/.
        #   3. GNU long form, marker phrase "General Public License".
        #      That single substring covers GPL, LGPL ("GNU Lesser
        #      General Public License") and AGPL ("GNU Affero
        #      General Public License") preambles, all three of
        #      which appear in unsloth/kernels/* (LGPL/AGPL) without
        #      the SPDX line.
        # Empty files (mainly empty __init__.py) are skipped.
        # Surfaced as a warning; cleaning up the actual misses is a
        # follow-up PR, not a CI fix.
        continue-on-error: true
        run: |
          python <<'PY'
          import pathlib

          ACCEPTED = (
              "SPDX-License-Identifier",        # any SPDX line
              "Licensed under the Apache License",  # Apache-2.0 long form
              "General Public License",         # GPL / LGPL / AGPL long form
          )
          SKIP_PARTS = {".venv", "venv", "build", "dist", ".git",
                        "unsloth_compiled_cache", "node_modules",
                        "unsloth.egg-info"}

          studio_missing = []
          other_missing  = []
          for path in sorted(pathlib.Path(".").rglob("*.py")):
              if any(part in SKIP_PARTS for part in path.parts):
                  continue
              text = path.read_text(encoding="utf-8", errors="replace")
              if not text.strip():
                  continue  # empty __init__.py etc.
              head = "\n".join(text.splitlines()[:25])
              if any(marker in head for marker in ACCEPTED):
                  continue
              if "studio" in path.parts:
                  studio_missing.append(path)
              else:
                  other_missing.append(path)

          total = len(studio_missing) + len(other_missing)
          if total == 0:
              print("every committed .py has a recognised license header")
          else:
              print(f"::warning::{total} Python files have no recognised license "
                    f"header (SPDX / Apache-2.0 / GNU long form): "
                    f"studio={len(studio_missing)}, other={len(other_missing)}")
              for path in (studio_missing + other_missing)[:30]:
                  print(f"  {path}")
              if total > 30:
                  print(f"  ... and {total - 30} more")
          PY

      - name: Shell scripts parse cleanly (`bash -n`)
        # Same idea as Python's compileall: parse-only check that
        # every committed *.sh would not blow up at `bash script.sh`
        # invocation time on a release box. tests/sh/ is the largest
        # cluster (the install.sh shape tests).
        run: |
          shopt -s globstar
          fail=0
          for f in $(git ls-files '*.sh'); do
              if ! bash -n "$f"; then
                  echo "::error file=$f::shell parse error"
                  fail=1
              fi
          done
          if [ "$fail" -ne 0 ]; then
              exit 1
          fi
          n=$(git ls-files '*.sh' | wc -l)
          echo "$n shell scripts parse cleanly"

      - name: YAML files parse cleanly (yaml.safe_load)
        # Catches truncated workflow files, broken indents in
        # dependabot.yml / pre-commit configs, etc. Includes
        # .github/workflows/*.yml so a typo in the file we just
        # added shows up immediately.
        run: |
          python <<'PY'
          import pathlib, sys, yaml

          SKIP_PARTS = {".venv", "venv", "build", "dist", ".git",
                        "node_modules", "unsloth_compiled_cache",
                        "unsloth.egg-info"}

          bad = []
          scanned = 0
          for path in sorted(list(pathlib.Path(".").rglob("*.yml"))
                             + list(pathlib.Path(".").rglob("*.yaml"))):
              if any(part in SKIP_PARTS for part in path.parts):
                  continue
              scanned += 1
              try:
                  with path.open("r", encoding="utf-8") as fh:
                      list(yaml.safe_load_all(fh))
              except Exception as exc:
                  bad.append((path, exc))

          if bad:
              for path, exc in bad:
                  print(f"::error file={path}::YAML parse failed: {exc}")
              sys.exit(1)
          print(f"{scanned} YAML files parse cleanly")
          PY

      - name: JSON files parse cleanly (json.loads)
        # Catches malformed package.json, biome.json, etc. Skips:
        #   - huge npm/bun lockfiles (machine-generated, slow to
        #     parse, no value).
        #   - tsconfig*.json: TypeScript convention is JSONC (JSON
        #     with `/* ... */` comments), which standard json.loads
        #     rejects. Strip-and-validate would need json5 or a
        #     hand-rolled comment scrubber for marginal value, since
        #     `tsc --noEmit` already validates these in Frontend CI.
        run: |
          python <<'PY'
          import fnmatch, json, pathlib, sys

          SKIP_PARTS = {".venv", "venv", "build", "dist", ".git",
                        "node_modules", "unsloth_compiled_cache",
                        "unsloth.egg-info"}
          SKIP_NAMES = {"package-lock.json", "bun.lock"}
          SKIP_PATTERNS = ("tsconfig*.json",)

          bad = []
          scanned = 0
          for path in sorted(pathlib.Path(".").rglob("*.json")):
              if any(part in SKIP_PARTS for part in path.parts):
                  continue
              if path.name in SKIP_NAMES:
                  continue
              if any(fnmatch.fnmatch(path.name, pat) for pat in SKIP_PATTERNS):
                  continue
              scanned += 1
              try:
                  json.loads(path.read_text(encoding="utf-8"))
              except Exception as exc:
                  bad.append((path, exc))

          if bad:
              for path, exc in bad:
                  print(f"::error file={path}::JSON parse failed: {exc}")
              sys.exit(1)
          print(f"{scanned} JSON files parse cleanly")
          PY

      - name: codespell typo check (informational)
        # Catches typos in code, comments, and docs across the repo.
        # Skips lockfiles, generated assets, binary artefacts, and
        # the LICENSE files (US/UK spelling drift in legal text is
        # not ours to second-guess). The ignore-words-list pulls
        # out short identifiers + valid technical terms that
        # codespell's default dictionary would otherwise flag
        # (e.g. `ans` as a math-quiz variable name in
        # tests/utils/aime_eval.py, `parm`/`parms` in PyTorch
        # nn.Module idioms). Non-blocking until the surfaced typos
        # are fixed; drop continue-on-error after the cleanup.
        continue-on-error: true
        run: |
          codespell \
            --skip='*.lock,*.lockb,*.json,*.svg,*.png,*.jpg,*.jpeg,*.gif,*.ico,*.woff*,*.ttf,*.eot,*.zip,*.gz,*.gguf,*.safetensors,*.bin,node_modules,.git,build,dist,unsloth_compiled_cache,unsloth.egg-info,target,studio/frontend/dist,*.pyc,*-licenses.txt,LICENSE*' \
            --ignore-words-list='ans,bu,hel,fo,te,ot,hist,ned,sav,recurser,datas,nin,parm,parms,checkin,nd,fr,inout,donot,uint' \
            --quiet-level=2

      - name: shellcheck on committed *.sh (informational)
        # Goes beyond `bash -n` (which only parses): catches subtle
        # shell bugs like unquoted variable expansions, useless
        # `cat`, command substitutions inside `[[`, etc. The
        # install/setup scripts are critical-path so the signal is
        # worth surfacing. Non-blocking until install.sh's
        # hand-rolled patterns get cleaned up; drop continue-on-error
        # afterwards.
        continue-on-error: true
        run: |
          # Exclude SC1090 ("source not followable") -- legitimate
          # for installer scripts that source files at runtime
          # paths shellcheck cannot resolve statically.
          # SC2034 ("variable assigned but never used") fires on
          # the export-only assignment idiom we use in install.sh.
          shellcheck -e SC1090,SC2034 $(git ls-files '*.sh')

      - name: ruff format drift (informational)
        # The canonical formatter is scripts/run_ruff_format.py
        # = ruff format + scripts/enforce_kwargs_spacing.py, so plain
        # `ruff format --check` reports the kwarg-spacing diff as
        # drift. Surface the count for visibility but keep
        # non-blocking until the custom pipeline is wired in here.
        continue-on-error: true
        run: |
          ruff format --check unsloth unsloth_cli studio tests cli.py unsloth-cli.py