chore: import upstream snapshot with attribution

.github/actions/cache-hf/action.yml

@@ -0,0 +1,11 @@
+name: "cache-hf"
+description: "Cache HuggingFace Hub artifacts to avoid 429s in CI"
+runs:
+  using: "composite"
+  steps:
+    - uses: actions/cache@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
+      with:
+        path: ~/.cache/huggingface/hub/datasets--*
+        key: ${{ runner.os }}-hf-datasets-${{ hashFiles('tests/data/test_huggingface_dataset_and_source.py') }}
+        restore-keys: |
+          ${{ runner.os }}-hf-datasets

.github/actions/check-component-ids/action.yml

@@ -0,0 +1,8 @@
+name: "check-component-ids"
+description: "Verify that all componentIds in the MLflow UI are registered in the componentId registry and vice versa."
+runs:
+  using: "composite"
+  steps:
+    - uses: ./.github/actions/setup-node
+    - run: node ${GITHUB_ACTION_PATH}/index.js
+      shell: bash

.github/actions/check-component-ids/index.js

@@ -0,0 +1,41 @@
+const { extractComponentIdsFromSource } = require("./utils");
+
+const registry = require("./componentId-registry");
+
+// --- Main ---
+const codeIds = extractComponentIdsFromSource(__dirname);
+const registryKeys = new Set(Object.keys(registry));
+
+// Check 1: componentIds in code but not in registry
+const unregistered = [...codeIds].filter((id) => !registryKeys.has(id)).sort();
+
+// Check 2: componentIds in registry but not in code (stale)
+const stale = [...registryKeys].filter((id) => !codeIds.has(id)).sort();
+
+let failed = false;
+
+if (unregistered.length > 0) {
+  failed = true;
+  console.error(
+    `\n❌ Found ${unregistered.length} componentId(s) in code but NOT in the registry:\n`
+  );
+  for (const id of unregistered) {
+    console.error(`  + ${id}`);
+  }
+  console.error("\nAdd these to .github/actions/check-component-ids/componentId-registry.js");
+}
+
+if (stale.length > 0) {
+  failed = true;
+  console.error(`\n❌ Found ${stale.length} stale componentId(s) in registry but NOT in code:\n`);
+  for (const id of stale) {
+    console.error(`  - ${id}`);
+  }
+  console.error("\nRemove these from .github/actions/check-component-ids/componentId-registry.js");
+}
+
+if (failed) {
+  process.exit(1);
+} else {
+  console.log(`✅ componentId registry is in sync. ${registryKeys.size} entries verified.`);
+}

.github/actions/check-component-ids/regenerate.js

@@ -0,0 +1,70 @@
+#!/usr/bin/env node
+
+/**
+ * Regenerates the componentId registry from source code.
+ *
+ * Usage (from repo root):
+ *   node .github/actions/check-component-ids/regenerate.js
+ */
+
+const fs = require("fs");
+const path = require("path");
+const { extractComponentIdsFromSource } = require("./utils");
+
+const codeIds = extractComponentIdsFromSource(__dirname);
+const sorted = [...codeIds].sort();
+
+// Group by prefix for readability
+const groups = {};
+for (const id of sorted) {
+  let prefix;
+  if (id.startsWith("codegen_")) {
+    prefix = "Codegen (auto-generated)";
+  } else if (id.startsWith("mlflow.")) {
+    const parts = id.split(".");
+    prefix = parts[0] + "." + parts[1];
+  } else if (id.startsWith("shared.")) {
+    const parts = id.split(".");
+    prefix = parts[0] + "." + parts[1];
+  } else {
+    prefix = "Other";
+  }
+  if (!groups[prefix]) groups[prefix] = [];
+  groups[prefix].push(id);
+}
+
+// Load existing registry to preserve descriptions
+let existingDescriptions = {};
+try {
+  existingDescriptions = require("./componentId-registry");
+} catch {
+  // First run or broken registry — start fresh
+}
+
+let output = `/**
+ * Curated registry of all componentIds used in the MLflow UI.
+ *
+ * Every static componentId string literal in non-test source files must
+ * have an entry here. The CI job \`check-component-ids\` verifies this
+ * bidirectionally: code IDs must be in the registry, and registry
+ * entries must exist in code.
+ *
+ * Format: key = componentId string, value = optional description of the
+ * component (blank by default, especially for generated entries)
+ */
+module.exports = {\n`;
+
+for (const gk of Object.keys(groups).sort()) {
+  output += `  // -- ${gk} --\n`;
+  for (const id of groups[gk]) {
+    const escaped = id.replace(/"/g, '\\"');
+    const desc = (existingDescriptions[id] || "").replace(/"/g, '\\"');
+    output += `  "${escaped}": "${desc}",\n`;
+  }
+  output += "\n";
+}
+output += "};\n";
+
+const outPath = path.join(__dirname, "componentId-registry.js");
+fs.writeFileSync(outPath, output);
+console.log(`✅ Registry regenerated with ${sorted.length} entries at ${outPath}`);

.github/actions/check-component-ids/utils.js

@@ -0,0 +1,66 @@
+const fs = require("fs");
+const path = require("path");
+
+const EXTENSIONS = [".js", ".jsx", ".ts", ".tsx"];
+// Skip test files — they don't need registered componentIds
+const TEST_PATTERN = /\.test\.[jt]sx?$/;
+
+const EXTRACT_PATTERNS = [
+  /(?:componentId|data-component-id)=["']([^"']+)["']/g,
+  /componentId:\s*["']([^"']+)["']/g,
+  // Match static strings inside JSX expressions like componentId={"value"},
+  // componentId={cond ?? "fallback"}, componentId={cond ? "a" : "b"}, etc.
+  // Uses [^\n}]* to avoid matching across lines.
+  /componentId=\{[^\n}]*["']([^"'\n`]+)["'][^\n}]*\}/g,
+];
+
+function findFiles(dir) {
+  const results = [];
+  function walk(d) {
+    for (const entry of fs.readdirSync(d, { withFileTypes: true })) {
+      const full = path.join(d, entry.name);
+      if (entry.isDirectory() && !entry.name.startsWith(".") && entry.name !== "node_modules") {
+        walk(full);
+      } else if (
+        entry.isFile() &&
+        EXTENSIONS.some((ext) => full.endsWith(ext)) &&
+        !TEST_PATTERN.test(full)
+      ) {
+        results.push(full);
+      }
+    }
+  }
+  walk(dir);
+  return results;
+}
+
+function extractComponentIds(files) {
+  const ids = new Set();
+  for (const file of files) {
+    const content = fs.readFileSync(file, "utf8");
+    for (const pat of EXTRACT_PATTERNS) {
+      pat.lastIndex = 0;
+      let m;
+      while ((m = pat.exec(content)) !== null) {
+        ids.add(m[1]);
+      }
+    }
+  }
+  return ids;
+}
+
+/**
+ * Extract all static componentIds from the MLflow UI source directory.
+ * @param {string} actionDir - path to this action's directory (used to resolve the repo root)
+ * @returns {Set<string>} set of componentId strings found in source
+ */
+function extractComponentIdsFromSource(actionDir) {
+  const srcDir = path.resolve(
+    process.env.GITHUB_WORKSPACE || path.join(actionDir, "../../.."),
+    "mlflow/server/js/src"
+  );
+  const files = findFiles(srcDir);
+  return extractComponentIds(files);
+}
+
+module.exports = { extractComponentIdsFromSource };

.github/actions/free-disk-space/action.yml

@@ -0,0 +1,9 @@
+name: "free-disk-space"
+description: "free disk space"
+runs:
+  using: "composite"
+  steps:
+    - shell: bash
+      run: |
+        # Run in background to save time
+        sudo rm -rf /usr/local/lib/android &

.github/actions/setup-java/action.yml

@@ -0,0 +1,27 @@
+name: "setup-java"
+description: "Set up Java"
+inputs:
+  java-version:
+    description: "java-version"
+    default: "17"
+    required: false
+
+  distribution:
+    description: "distribution"
+    default: temurin
+    required: false
+
+runs:
+  using: "composite"
+  steps:
+    - uses: actions/setup-java@be666c2fcd27ec809703dec50e508c2fdc7f6654 # v5.2.0
+      with:
+        java-version: ${{ inputs.java-version }}
+        distribution: ${{ inputs.distribution }}
+
+    - name: Set MLFLOW_DOCKER_OPENJDK_VERSION
+      shell: bash
+      env:
+        JAVA_VERSION: ${{ inputs.java-version }}
+      run: |
+        echo "MLFLOW_DOCKER_OPENJDK_VERSION=$JAVA_VERSION" >> $GITHUB_ENV

.github/actions/setup-node/action.yml

@@ -0,0 +1,19 @@
+name: "setup-node"
+description: "Set up Node"
+inputs:
+  node-version:
+    description: "Node version to use."
+    default: "24"
+    required: false
+
+runs:
+  using: "composite"
+  steps:
+    - uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0
+      with:
+        node-version: ${{ inputs.node-version }}
+    - run: |
+        # allowScripts opt-in install-script policy requires npm >= 11.16.0
+        # (https://github.com/npm/cli/pull/9360)
+        npm install -g npm@"^11.16.0"
+      shell: bash

.github/actions/setup-pyenv/action.yml

@@ -0,0 +1,62 @@
+name: "setup-pyenv"
+description: "Setup pyenv"
+runs:
+  using: "composite"
+  steps:
+    ########## Ubuntu ##########
+    - name: Install python build tools
+      if: runner.os == 'Linux'
+      shell: bash
+      # Ref: https://github.com/pyenv/pyenv/wiki#suggested-build-environment
+      # Note: llvm is optional (required only for building PyPy/clang)
+      run: |
+        sudo apt-get update
+        sudo apt-get purge -y man-db || true
+        sudo apt-get install -y --no-install-recommends make build-essential libssl-dev zlib1g-dev \
+        libbz2-dev libreadline-dev libsqlite3-dev wget curl \
+        libncursesw5-dev xz-utils libffi-dev liblzma-dev
+    - name: Install pyenv
+      if: runner.os == 'Linux'
+      shell: bash
+      run: |
+        # Pin to pyenv v2.6.25 by tag + SHA verification for reproducible builds
+        git clone --branch v2.6.25 --depth 1 https://github.com/pyenv/pyenv.git "$HOME/.pyenv"
+        actual_sha=$(git -C "$HOME/.pyenv" rev-parse HEAD)
+        expected_sha="aa2e8b82605b8ba085dd15f7a31fe1990fabdcfa"
+        if [ "$actual_sha" != "$expected_sha" ]; then
+          echo "::error::pyenv SHA mismatch: expected $expected_sha, got $actual_sha"
+          exit 1
+        fi
+    - name: Setup environment variables
+      if: runner.os == 'Linux'
+      shell: bash
+      run: |
+        PYENV_ROOT="$HOME/.pyenv"
+        PYENV_BIN="$PYENV_ROOT/bin"
+        echo "$PYENV_BIN" >> $GITHUB_PATH
+        echo "PYENV_ROOT=$PYENV_ROOT" >> $GITHUB_ENV
+    - name: Check pyenv version
+      if: runner.os == 'Linux'
+      shell: bash
+      run: |
+        pyenv --version
+
+    ########## Windows ##########
+    - name: Install pyenv
+      if: runner.os == 'Windows'
+      shell: bash
+      run: |
+        uv pip install --system pyenv-win --target $HOME\\.pyenv
+    - name: Setup environment variables
+      if: runner.os == 'Windows'
+      shell: bash
+      run: |
+        echo "PYENV=$USERPROFILE\.pyenv\pyenv-win\\" >> $GITHUB_ENV
+        echo "PYENV_ROOT=$USERPROFILE\.pyenv\pyenv-win\\" >> $GITHUB_ENV
+        echo "PYENV_HOME=$USERPROFILE\.pyenv\pyenv-win\\" >> $GITHUB_ENV
+        echo "$USERPROFILE\.pyenv\pyenv-win\\bin\\" >> $GITHUB_PATH
+    - name: Check pyenv version
+      if: runner.os == 'Windows'
+      shell: bash
+      run: |
+        pyenv --version

.github/actions/setup-python/action.yml

@@ -0,0 +1,79 @@
+name: "setup-python"
+description: "Ensures to install a python version that's available on Anaconda"
+inputs:
+  python-version:
+    description: "The python version to install. If unspecified, install the minimum python version mlflow supports."
+    required: false
+  pin-micro-version:
+    description: "Whether to pin to a specific micro version for Anaconda compatibility. Set to false for workflows that don't need conda/pyenv to hit the runner's pre-installed Python cache and avoid a ~9s download."
+    required: false
+    default: "true"
+outputs:
+  python-version:
+    description: "The installed python version"
+    value: ${{ steps.get-python-version.outputs.version }}
+runs:
+  using: "composite"
+  steps:
+    - name: get-python-version
+      id: get-python-version
+      shell: bash
+      # We used to use `conda search python=3.x` to dynamically fetch the latest available version
+      # in 3.x on Anaconda, but it turned out `conda search` is very slow (takes 40 ~ 50 seconds).
+      # This overhead sums up to a significant amount of delay in the cross version tests
+      # where we trigger more than 100 GitHub Actions runs.
+      env:
+        PYTHON_VERSION_INPUT: ${{ inputs.python-version }}
+        PIN_MICRO_VERSION: ${{ inputs.pin-micro-version }}
+      run: |
+        python_version="$PYTHON_VERSION_INPUT"
+        if [ -z "$python_version" ]; then
+          python_version=$(cat .python-version)
+        fi
+        if [[ "$PIN_MICRO_VERSION" == "true" ]]; then
+          if [[ "$python_version" == "3.10" ]]; then
+            if [ "$RUNNER_OS" == "Linux" ]; then
+              python_version="3.10.20"
+            else
+              python_version="3.10.11"
+            fi
+          elif [[ "$python_version" == "3.11" ]]; then
+            if [ "$RUNNER_OS" == "Windows" ]; then
+              python_version="3.11.9"
+            else
+              python_version="3.11.15"
+            fi
+          elif [[ "$python_version" == "3.12" ]]; then
+            if [ "$RUNNER_OS" == "Windows" ]; then
+              python_version="3.12.10"
+            else
+              python_version="3.12.13"
+            fi
+          else
+            echo "Invalid python version: '$python_version'. Must be '3.10', '3.11', or '3.12'."
+            exit 1
+          fi
+        fi
+        echo "version=$python_version" >> $GITHUB_OUTPUT
+    - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
+      with:
+        python-version: ${{ steps.get-python-version.outputs.version }}
+    - uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7.6.0
+      with:
+        version: "0.11.14"
+        # Caching disabled to avoid cache-poisoning exposure across CI workflows.
+        enable-cache: false
+    - run: |
+        # The default `first-index` strategy is too strict. Use `unsafe-first-match` instead.
+        # https://docs.astral.sh/uv/configuration/environment/#uv_index_strategy
+        echo "UV_INDEX_STRATEGY=unsafe-first-match" >> $GITHUB_ENV
+        # Disable progress bars and spinners to reduce CI log clutter
+        # https://docs.astral.sh/uv/reference/environment/#uv_no_progress
+        echo "UV_NO_PROGRESS=1" >> $GITHUB_ENV
+        # Exclude packages newer than 7 days to guard against supply chain attacks
+        # https://docs.astral.sh/uv/reference/environment/#uv_exclude_newer
+        echo "UV_EXCLUDE_NEWER=P7D" >> $GITHUB_ENV
+        # Disable Hugging Face download progress bars to reduce CI log clutter
+        # https://huggingface.co/docs/huggingface_hub/package_reference/environment_variables#hfhubdisableprogressbars
+        echo "HF_HUB_DISABLE_PROGRESS_BARS=1" >> $GITHUB_ENV
+      shell: bash

.github/actions/show-versions/action.yml

@@ -0,0 +1,21 @@
+name: "show-versions"
+description: "Show python package versions sorted by release date"
+runs:
+  using: "composite"
+  steps:
+    - shell: bash
+      run: |
+        # Activate the virtual environment if .venv exists
+        if [ -d .venv ]; then
+          if [ "$RUNNER_OS" == "Windows" ]; then
+            source .venv/Scripts/activate
+          else
+            source .venv/bin/activate
+          fi
+        fi
+        pip --disable-pip-version-check install ./dev/pypi > /dev/null
+        echo ">>> package versions"
+        status=0
+        python dev/show_package_release_dates.py || status=$?
+        echo "<<< package versions"
+        exit $status

.github/actions/untracked/action.yml

@@ -0,0 +1,6 @@
+name: "untracked"
+description: "Detect untracked files"
+runs:
+  using: "node24"
+  main: "index.js"
+  post: "post.js"

.github/actions/untracked/index.js

@@ -0,0 +1 @@
+// Does nothing

.github/actions/untracked/post.js

@@ -0,0 +1,20 @@
+const { exec } = require("child_process");
+
+exec("git ls-files --others --exclude-standard", (error, stdout, stderr) => {
+  if (error) {
+    console.error(`An error occurred: ${error}`);
+    process.exit(error.code || 1);
+  }
+
+  const untrackedFiles = stdout.trim();
+
+  if (untrackedFiles === "") {
+    console.log("No untracked files found.");
+    process.exit(0);
+  } else {
+    console.log("Untracked files found:");
+    console.log(untrackedFiles);
+    console.log("Consider adding them to .gitignore.");
+    process.exit(1);
+  }
+});

.github/actions/update-requirements/action.yml

@@ -0,0 +1,24 @@
+name: "update-requirements"
+description: "Update requirements YAML specifications and re-generate requirements text files"
+
+outputs:
+  updated:
+    description: "Indicates whether the requirements have been updated"
+    value: ${{ steps.update-requirements.outputs.updated }}
+
+runs:
+  using: "composite"
+  steps:
+    - name: Update requirements
+      id: update-requirements
+      shell: bash --noprofile --norc -exo pipefail {0}
+      run: |
+        python bin/install.py
+        python dev/update_requirements.py --requirements-yaml-location requirements
+        if [ -z "$(git status --porcelain)" ]; then
+          echo "updated=false" >> $GITHUB_OUTPUT
+        else
+          python dev/pyproject.py
+          git diff --color=always
+          echo "updated=true" >> $GITHUB_OUTPUT
+        fi